From 9d3878242ca8190950ce637973af9b5e567bebc9 Mon Sep 17 00:00:00 2001 From: Ben Hutchings Date: Mon, 27 Aug 2018 15:32:32 +0100 Subject: [PATCH] [rt] Update to 4.18-rc8-rt1 and re-enable --- debian/changelog | 1 + debian/config/defines | 2 +- ...M-at91-add-TCB-registers-definitions.patch | 236 ++++ ...d-zone-lock-while-freeing-pages-from.patch | 167 +++ ..._t-for-reference-counting-instead-at.patch | 103 ++ ...list_lru_walk_one-in-list_lru_walk_n.patch | 31 + ...move-local_irq_disable-from-count_sh.patch | 46 + ...d-zone-lock-while-freeing-pages-from.patch | 166 +++ ...ers-Add-a-new-driver-for-the-Atmel-A.patch | 672 ++++++++++ ...-Use-irqsave-variant-of-atomic_dec_a.patch | 37 + ...-locking-from-__list_lru_walk_one-to.patch | 65 + ...ke-shadow_lru_isolate-use-locking-su.patch | 45 + ...unt_t-for-reference-counting-instead.patch | 83 ++ ...drivers-atmel-pit-make-option-silent.patch | 30 + ...-Do-not-disable-irq-on-release_inact.patch | 31 + ...B-change-list_lock-to-raw_spinlock_t.patch | 609 +++++++++ ...-struct-list_lru_node-as-an-argument.patch | 56 + ...at91-Implement-clocksource-selection.patch | 49 + ...ving-back-empty-slubs-to-IRQ-enabled.patch | 217 +++ ...u-Introduce-list_lru_shrink_walk_irq.patch | 107 ++ ...onfigs-at91-use-new-TCB-timer-driver.patch | 35 + ...ave-variant-of-refcount_dec_and_lock.patch | 31 + .../0006-ARM-configs-at91-unselect-PIT.patch | 36 + ...ave-variant-of-refcount_dec_and_lock.patch | 31 + ...n-translation-section-permission-fau.patch | 86 ++ ...intk-drop-the-logbuf_lock-more-often.patch | 77 ++ ...wngrade-preempt_disable-d-region-to-.patch | 52 + ...-replace-seqcount_t-with-a-seqlock_t.patch | 128 ++ ...-remove-irq-save-in-sas_ata_qc_issue.patch | 49 + ...2xxx-remove-irq-save-in-qla2x00_poll.patch | 42 + .../features/all/rt/add_migrate_disable.patch | 252 ++++ ...-a-locallock-instead-preempt_disable.patch | 77 ++ .../arch-arm64-Add-lazy-preempt-support.patch | 119 ++ .../all/rt/arm-convert-boot-lock-to-raw.patch | 412 ++++++ .../rt/arm-disable-NEON-in-kernel-mode.patch | 165 +++ .../all/rt/arm-enable-highmem-for-rt.patch | 174 +++ .../rt/arm-highmem-flush-tlb-on-unmap.patch | 28 + ...arm-include-definition-for-cpumask_t.patch | 25 + ...probe-replace-patch_lock-to-raw-lock.patch | 70 + .../all/rt/arm-preempt-lazy-support.patch | 152 +++ .../all/rt/arm-unwind-use_raw_lock.patch | 84 ++ ...e_layout-before-altenates-are-applie.patch | 72 + ...-preemp_disable-in-addition-to-local.patch | 165 +++ .../rt/at91_dont_enable_disable_clock.patch | 92 ++ ...e-blk_queue_usage_counter_release-in.patch | 112 ++ ...k-mq-don-t-complete-requests-via-IPI.patch | 107 ++ .../rt/block-mq-drop-preempt-disable.patch | 52 + .../all/rt/block-mq-use-cpu_light.patch | 30 + .../features/all/rt/block-use-cpu-chill.patch | 46 + ...ove-taking-of-spin-lock-out-of-trace.patch | 271 ++++ ...irqsave-in-cgroup_rstat_flush_locked.patch | 44 + ...roups-use-simple-wait-in-css_release.patch | 87 ++ ...source-tclib-allow-higher-clockrates.patch | 158 +++ .../completion-use-simple-wait-queues.patch | 336 +++++ .../all/rt/cond-resched-lock-rt-tweak.patch | 27 + ...c-Protect-send_msg-with-a-local-lock.patch | 68 + .../cpu-hotplug--Implement-CPU-pinning.patch | 111 ++ ...rop-K8-s-driver-from-beeing-selected.patch | 33 + .../rt/cpumask-disable-offstack-on-rt.patch | 68 + ...vert-callback_lock-to-raw_spinlock_t.patch | 287 ++++ ...-preempt-disabled-regions-more-algos.patch | 255 ++++ ...d-a-lock-instead-preempt_disable-loc.patch | 79 ++ ...ypto-limit-more-FPU-enabled-sections.patch | 98 ++ ...-serialize-RT-percpu-scratch-buffer-.patch | 77 ++ .../features/all/rt/debugobjects-rt.patch | 26 + ...rq-remove-BUG_ON-irqs_disabled-check.patch | 31 + ...am-Replace-bit-spinlocks-with-rtmute.patch | 86 ++ .../rt/drivers-tty-fix-omap-lock-crap.patch | 43 + ...rivers-tty-pl011-irq-disable-madness.patch | 48 + ...-t-disable-preemption-in-zcomp_strea.patch | 97 ++ ...-zcomp_stream_get-smp_processor_id-u.patch | 38 + ...rq()_in_intel_pipe_update_startend().patch | 113 ++ ...disableenable_rt()_where_recommended.patch | 52 + .../all/rt/efi-Allow-efi-runtime.patch | 27 + .../efi-Disable-runtime-services-on-RT.patch | 40 + .../all/rt/epoll-use-get-cpu-light.patch | 31 + .../all/rt/fs-aio-simple-simple-work.patch | 83 ++ ...-back-explicit-INIT_HLIST_BL_HEAD-in.patch | 54 + ...e-preemption-on-i_dir_seq-s-write-si.patch | 119 ++ ...cache-use-cpu-chill-in-trylock-loops.patch | 59 + ...use-swait_queue-instead-of-waitqueue.patch | 215 +++ .../all/rt/fs-jbd-replace-bh_state-lock.patch | 97 ++ ...-nfs-turn-rmdir_sem-into-a-semaphore.patch | 139 ++ .../fs-replace-bh_uptodate_lock-for-rt.patch | 208 +++ ...lize-cookie-hash-table-raw-spinlocks.patch | 55 + .../ftrace-Fix-trace-header-alignment.patch | 46 + .../rt/ftrace-migrate-disable-tracing.patch | 74 + ...k-unlock-symetry-versus-pi_lock-and-.patch | 43 + .../all/rt/futex-requeue-pi-fix.patch | 113 ++ ...-migrate_disable-enable-in-different.patch | 59 + .../all/rt/genirq-disable-irqpoll-on-rt.patch | 38 + ...voke-the-affinity-callback-via-a-wor.patch | 122 ++ .../all/rt/genirq-force-threading.patch | 46 + ...-irq_set_irqchip_state-documentation.patch | 26 + ...duct-tape-RT-rwlock-usage-for-non-RT.patch | 96 ++ .../rt/hotplug-light-get-online-cpus.patch | 91 ++ ...-schedule_work-call-to-helper-thread.patch | 92 ++ ...-by-default-into-the-softirq-context.patch | 210 +++ ...ate-hrtimer_init-hrtimer_init_sleepe.patch | 252 ++++ .../rt/hrtimers-prepare-full-preemption.patch | 273 ++++ ...iommu-amd-drop-irqs_disabled-warn_on.patch | 53 + ...irq-processing-in-irq-thread-context.patch | 147 ++ ...-its-Make-its_lock-a-raw_spin_lock_t.patch | 90 ++ ...ts-Move-ITS-pend_page-allocation-int.patch | 129 ++ ...-push_most_work_into_softirq_context.patch | 222 +++ .../features/all/rt/jump-label-rt.patch | 36 + .../rt/kconfig-disable-a-few-options-rt.patch | 34 + .../all/rt/kconfig-preempt-rt-full.patch | 59 + ...n-t-try-to-print-from-IRQ-NMI-region.patch | 42 + ...vide-a-pointer-to-the-valid-CPU-mask.patch | 722 ++++++++++ ...e-stack-kprobe-clean-up-to-__put_tas.patch | 62 + .../all/rt/kgb-serial-hackaround.patch | 77 ++ ...ds-trigger-disable-CPU-trigger-on-RT.patch | 36 + ...ibata-remove-ata_sff_data_xfer_noirq.patch | 197 +++ .../list_bl-fixup-bogus-lockdep-warning.patch | 98 ++ ..._bl.h-make-list-head-locking-RT-safe.patch | 115 ++ ...provide-get-put-_locked_ptr-variants.patch | 43 + .../features/all/rt/localversion.patch | 14 + .../all/rt/lockdep-disable-self-test.patch | 29 + .../lockdep-no-softirq-accounting-on-rt.patch | 70 + ...-fix-warnings-due-to-missing-PREEMPT.patch | 142 ++ ...ardirq-context-test-for-raw-spinlock.patch | 57 + ...eck-for-__LINUX_SPINLOCK_TYPES_H-on-.patch | 158 +++ ...ure-Do-NOT-include-rwlock.h-directly.patch | 27 + ...-fix-deadlock-in-device-mapper-block.patch | 74 + ...re-init-the-wait_lock-in-rt_mutex_in.patch | 33 + .../features/all/rt/md-disable-bcache.patch | 32 + .../md-raid5-percpu-handling-rt-aware.patch | 70 + .../all/rt/mips-disable-highmem-on-rt.patch | 23 + .../rt/mm-convert-swap-to-percpu-locked.patch | 200 +++ .../features/all/rt/mm-disable-sloub-rt.patch | 32 + .../features/all/rt/mm-enable-slub.patch | 36 + .../all/rt/mm-make-vmstat-rt-aware.patch | 137 ++ ...n-t-call-schedule_work_on-in-preempt.patch | 69 + .../rt/mm-memcontrol-do_not_disable_irq.patch | 117 ++ ...page_alloc-rt-friendly-per-cpu-pages.patch | 233 ++++ ...m-perform-lru_add_drain_all-remotely.patch | 103 ++ .../rt/mm-protect-activate-switch-mm.patch | 72 + .../all/rt/mm-rt-kmap-atomic-scheduling.patch | 307 +++++ ...-scatterlist-dont-disable-irqs-on-RT.patch | 24 + .../all/rt/mm-vmalloc-use-get-cpu-light.patch | 66 + ...oc_copy_with_get_cpu_var_and_locking.patch | 197 +++ .../features/all/rt/mutex-no-spin-on-rt.patch | 29 + ...schedule_irqoff-disable-interrupts-o.patch | 69 + ...Qdisc-use-a-seqlock-instead-seqcount.patch | 272 ++++ .../rt/net-add-a-lock-around-icmp_sk.patch | 59 + ...-missing-serialization-in-ip_send_un.patch | 93 ++ ...al-irq-disable-alloc-atomic-headache.patch | 59 + ...-users-of-napi_alloc_cache-against-r.patch | 113 ++ ...-use-local_bh_disable-in-netif_rx_ni.patch | 35 + ...ake-qdisc-s-busylock-in-__dev_xmit_s.patch | 35 + ...ble-xt-write-recseq-begin-rt-fallout.patch | 76 ++ .../net-make-devnet_rename_seq-a-mutex.patch | 107 ++ ...recursion-to-per-task-variable-on-RT.patch | 266 ++++ ...y-to-delegate-processing-a-softirq-t.patch | 79 ++ ...activate_many-use-msleep-1-instead-o.patch | 58 + .../features/all/rt/net-use-cpu-chill.patch | 63 + .../all/rt/net_disable_NET_RX_BUSY_POLL.patch | 29 + ...abling-interrupts-during-kmap_atomic.patch | 52 + .../features/all/rt/oleg-signal-rt-fix.patch | 143 ++ .../all/rt/panic-disable-random-on-rt.patch | 27 + ...ce-rcu-bh-qs-where-safe-from-softirq.patch | 99 ++ ...ec-Don-t-use-completion-s-wait-queue.patch | 109 ++ .../all/rt/peter_zijlstra-frob-rcu.patch | 167 +++ .../all/rt/peterz-percpu-rwsem-rt.patch | 219 +++ .../all/rt/pid.h-include-atomic.h.patch | 37 + ...timers-thread-posix-cpu-timers-on-rt.patch | 258 ++++ .../all/rt/power-disable-highmem-on-rt.patch | 23 + .../rt/power-use-generic-rwsem-on-rt.patch | 27 + ...ble-in-kernel-MPIC-emulation-for-PRE.patch | 38 + .../all/rt/powerpc-preempt-lazy-support.patch | 164 +++ ...ce-init.c-adapt-to-completions-using.patch | 32 + .../all/rt/preempt-lazy-support.patch | 624 +++++++++ .../all/rt/preempt-nort-rt-variants.patch | 48 + ...27-boot-param-to-help-with-debugging.patch | 32 + .../patches/features/all/rt/printk-kill.patch | 164 +++ .../features/all/rt/printk-rt-aware.patch | 108 ++ ...ace-fix-ptrace-vs-tasklist_lock-race.patch | 156 +++ .../all/rt/radix-tree-use-local-locks.patch | 166 +++ ...andom-Remove-preempt-disabled-region.patch | 49 + ...dom-avoid-preempt_disable-ed-section.patch | 75 ++ .../all/rt/random-make-it-work-on-rt.patch | 150 +++ ...nate-softirq-processing-from-rcutree.patch | 412 ++++++ .../rt/rcu-disable-rcu-fast-no-hz-on-rt.patch | 25 + ..._normal_after_boot-by-default-for-RT.patch | 30 + .../rt/rcu-make-RCU_BOOST-default-on-RT.patch | 35 + ...merge-rcu-bh-into-rcu-preempt-for-rt.patch | 348 +++++ ...l-arm-coredump-fails-for-cpu-3e-3d-4.patch | 69 + ...ease-the-nr-of-migratory-tasks-when-.patch | 155 +++ .../all/rt/rt-introduce-cpu-chill.patch | 105 ++ .../features/all/rt/rt-local-irq-lock.patch | 331 +++++ .../all/rt/rt-preempt-base-config.patch | 54 + .../features/all/rt/rt-serial-warn-fix.patch | 38 + .../rt/rtmutex-Make-lock_killable-work.patch | 45 + ...tex-Provide-rt_mutex_slowlock_locked.patch | 129 ++ ...utex-implementation-based-on-rtmutex.patch | 373 ++++++ ...lock-implementation-based-on-rtmutex.patch | 569 ++++++++ ...wsem-implementation-based-on-rtmutex.patch | 417 ++++++ ...tex-add-sleeping-lock-implementation.patch | 1188 +++++++++++++++++ ...utex-add-ww_mutex-addon-for-mutex-rt.patch | 426 ++++++ ...mutex-annotate-sleeping-lock-context.patch | 292 ++++ .../all/rt/rtmutex-avoid-include-hell.patch | 24 + ...ockdep-less-version-of-rt_mutex-s-lo.patch | 145 ++ .../all/rt/rtmutex-futex-prepare-rt.patch | 245 ++++ .../all/rt/rtmutex-lock-killable.patch | 52 + .../rt/rtmutex-trylock-is-okay-on-RT.patch | 28 + .../all/rt/rtmutex-wire-up-RT-s-locking.patch | 251 ++++ .../all/rt/rtmutex_dont_include_rcu.patch | 159 +++ ...-core-Remove-get_cpu-from-sched_fork.patch | 88 ++ .../all/rt/sched-delay-put-task.patch | 86 ++ .../sched-disable-rt-group-sched-on-rt.patch | 29 + .../all/rt/sched-disable-ttwu-queue.patch | 32 + .../all/rt/sched-limit-nr-migrate.patch | 27 + ...might-sleep-do-not-account-rcu-depth.patch | 48 + ...sable-fallback-to-preempt_disable-in.patch | 192 +++ .../all/rt/sched-mmdrop-delayed.patch | 128 ++ .../all/rt/sched-rt-mutex-wakeup.patch | 97 ++ ...Only-wake-up-idle-workers-if-not-blo.patch | 38 + .../features/all/rt/scsi-fcoe-rt-aware.patch | 106 ++ .../rt/seqlock-prevent-rt-starvation.patch | 189 +++ .../signal-revert-ptrace-preempt-magic.patch | 32 + ...t-tasks-to-cache-one-sigqueue-struct.patch | 200 +++ .../features/all/rt/skbufhead-raw-lock.patch | 163 +++ .../rt/slub-disable-SLUB_CPU_PARTIAL.patch | 48 + .../all/rt/slub-enable-irqs-for-no-wait.patch | 42 + ...oftirq-disable-softirq-stacks-for-rt.patch | 157 +++ .../all/rt/softirq-preempt-fix-3-re.patch | 169 +++ .../features/all/rt/softirq-split-locks.patch | 816 +++++++++++ ...plit-timer-softirqs-out-of-ksoftirqd.patch | 208 +++ .../all/rt/spinlock-types-separate-raw.patch | 205 +++ ...e-of-local-lock-in-multi_cpu-decompr.patch | 66 + ...place-local_irqsave-with-a-locallock.patch | 71 + ...-use-cpu_online-instead-custom-check.patch | 91 ++ ...vc_xprt_do_enqueue-use-get_cpu_light.patch | 54 + .../all/rt/sysfs-realtime-entry.patch | 48 + ...-from-going-into-infinite-spin-in-rt.patch | 295 ++++ ...rmal-Defer-thermal-wakups-to-threads.patch | 131 ++ ...id-schedule_work-with-interrupts-dis.patch | 53 + .../rt/timekeeping-split-jiffies-lock.patch | 157 +++ .../timers-prepare-for-full-preemption.patch | 167 +++ .../tpm_tis-fix-stall-after-iowrite-s.patch | 78 ++ ...0-don-t-take-the-trylock-during-oops.patch | 29 + ...ove-preemption-disabling-in-netif_rx.patch | 67 + ...o-not-disable-interrupts-in-giveback.patch | 40 + .../all/rt/wait.h-include-atomic.h.patch | 33 + ...rk-around-irqsafe-timer-optimization.patch | 133 ++ ...mple-Simple-work-queue-implemenation.patch | 232 ++++ .../rt/workqueue-distangle-from-rq-lock.patch | 282 ++++ .../rt/workqueue-prevent-deadlock-stall.patch | 200 +++ .../all/rt/workqueue-use-locallock.patch | 179 +++ .../features/all/rt/workqueue-use-rcu.patch | 354 +++++ ...ypto-reduce-preempt-disabled-regions.patch | 112 ++ ...fi-drop-task_lock-from-efi_switch_mm.patch | 49 + ...highmem-add-a-already-used-pte-check.patch | 23 + ...-let-setaffinity-unmask-threaded-EOI.patch | 106 ++ .../rt/x86-kvm-require-const-tsc-for-rt.patch | 31 + .../features/all/rt/x86-preempt-lazy.patch | 222 +++ ...ignal-delay-calling-signals-on-32bit.patch | 43 + .../rt/x86-stackprot-no-random-on-rt.patch | 46 + .../rt/x86-use-gen-rwsem-spinlocks-rt.patch | 29 + debian/patches/series-rt | 432 ++++++ 261 files changed, 32585 insertions(+), 1 deletion(-) create mode 100644 debian/patches/features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch create mode 100644 debian/patches/features/all/rt/0001-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch create mode 100644 debian/patches/features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch create mode 100644 debian/patches/features/all/rt/0001-mm-list_lru-use-list_lru_walk_one-in-list_lru_walk_n.patch create mode 100644 debian/patches/features/all/rt/0001-mm-workingset-remove-local_irq_disable-from-count_sh.patch create mode 100644 debian/patches/features/all/rt/0002-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch create mode 100644 debian/patches/features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch create mode 100644 debian/patches/features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch create mode 100644 debian/patches/features/all/rt/0002-mm-list_lru-Move-locking-from-__list_lru_walk_one-to.patch create mode 100644 debian/patches/features/all/rt/0002-mm-workingset-make-shadow_lru_isolate-use-locking-su.patch create mode 100644 debian/patches/features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch create mode 100644 debian/patches/features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch create mode 100644 debian/patches/features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch create mode 100644 debian/patches/features/all/rt/0003-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch create mode 100644 debian/patches/features/all/rt/0003-mm-list_lru-Pass-struct-list_lru_node-as-an-argument.patch create mode 100644 debian/patches/features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch create mode 100644 debian/patches/features/all/rt/0004-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch create mode 100644 debian/patches/features/all/rt/0004-mm-list_lru-Introduce-list_lru_shrink_walk_irq.patch create mode 100644 debian/patches/features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch create mode 100644 debian/patches/features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch create mode 100644 debian/patches/features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch create mode 100644 debian/patches/features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch create mode 100644 debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch create mode 100644 debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch create mode 100644 debian/patches/features/all/rt/KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch create mode 100644 debian/patches/features/all/rt/NFSv4-replace-seqcount_t-with-a-seqlock_t.patch create mode 100644 debian/patches/features/all/rt/SCSI-libsas-remove-irq-save-in-sas_ata_qc_issue.patch create mode 100644 debian/patches/features/all/rt/SCSI-qla2xxx-remove-irq-save-in-qla2x00_poll.patch create mode 100644 debian/patches/features/all/rt/add_migrate_disable.patch create mode 100644 debian/patches/features/all/rt/apparmor-use-a-locallock-instead-preempt_disable.patch create mode 100644 debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch create mode 100644 debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch create mode 100644 debian/patches/features/all/rt/arm-disable-NEON-in-kernel-mode.patch create mode 100644 debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch create mode 100644 debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch create mode 100644 debian/patches/features/all/rt/arm-include-definition-for-cpumask_t.patch create mode 100644 debian/patches/features/all/rt/arm-kprobe-replace-patch_lock-to-raw-lock.patch create mode 100644 debian/patches/features/all/rt/arm-preempt-lazy-support.patch create mode 100644 debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch create mode 100644 debian/patches/features/all/rt/arm64-KVM-compute_layout-before-altenates-are-applie.patch create mode 100644 debian/patches/features/all/rt/arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch create mode 100644 debian/patches/features/all/rt/at91_dont_enable_disable_clock.patch create mode 100644 debian/patches/features/all/rt/block-blk-mq-move-blk_queue_usage_counter_release-in.patch create mode 100644 debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch create mode 100644 debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch create mode 100644 debian/patches/features/all/rt/block-mq-use-cpu_light.patch create mode 100644 debian/patches/features/all/rt/block-use-cpu-chill.patch create mode 100644 debian/patches/features/all/rt/cgroup-tracing-Move-taking-of-spin-lock-out-of-trace.patch create mode 100644 debian/patches/features/all/rt/cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch create mode 100644 debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch create mode 100644 debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch create mode 100644 debian/patches/features/all/rt/completion-use-simple-wait-queues.patch create mode 100644 debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch create mode 100644 debian/patches/features/all/rt/connector-cn_proc-Protect-send_msg-with-a-local-lock.patch create mode 100644 debian/patches/features/all/rt/cpu-hotplug--Implement-CPU-pinning.patch create mode 100644 debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch create mode 100644 debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch create mode 100644 debian/patches/features/all/rt/cpuset-Convert-callback_lock-to-raw_spinlock_t.patch create mode 100644 debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch create mode 100644 debian/patches/features/all/rt/crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch create mode 100644 debian/patches/features/all/rt/crypto-limit-more-FPU-enabled-sections.patch create mode 100644 debian/patches/features/all/rt/crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch create mode 100644 debian/patches/features/all/rt/debugobjects-rt.patch create mode 100644 debian/patches/features/all/rt/dm-rq-remove-BUG_ON-irqs_disabled-check.patch create mode 100644 debian/patches/features/all/rt/drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch create mode 100644 debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch create mode 100644 debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch create mode 100644 debian/patches/features/all/rt/drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch create mode 100644 debian/patches/features/all/rt/drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch create mode 100644 debian/patches/features/all/rt/drmi915_Use_local_lockunlock_irq()_in_intel_pipe_update_startend().patch create mode 100644 debian/patches/features/all/rt/drmradeoni915_Use_preempt_disableenable_rt()_where_recommended.patch create mode 100644 debian/patches/features/all/rt/efi-Allow-efi-runtime.patch create mode 100644 debian/patches/features/all/rt/efi-Disable-runtime-services-on-RT.patch create mode 100644 debian/patches/features/all/rt/epoll-use-get-cpu-light.patch create mode 100644 debian/patches/features/all/rt/fs-aio-simple-simple-work.patch create mode 100644 debian/patches/features/all/rt/fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-in.patch create mode 100644 debian/patches/features/all/rt/fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch create mode 100644 debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch create mode 100644 debian/patches/features/all/rt/fs-dcache-use-swait_queue-instead-of-waitqueue.patch create mode 100644 debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch create mode 100644 debian/patches/features/all/rt/fs-nfs-turn-rmdir_sem-into-a-semaphore.patch create mode 100644 debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch create mode 100644 debian/patches/features/all/rt/fscache-initialize-cookie-hash-table-raw-spinlocks.patch create mode 100644 debian/patches/features/all/rt/ftrace-Fix-trace-header-alignment.patch create mode 100644 debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch create mode 100644 debian/patches/features/all/rt/futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch create mode 100644 debian/patches/features/all/rt/futex-requeue-pi-fix.patch create mode 100644 debian/patches/features/all/rt/futex-workaround-migrate_disable-enable-in-different.patch create mode 100644 debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch create mode 100644 debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch create mode 100644 debian/patches/features/all/rt/genirq-force-threading.patch create mode 100644 debian/patches/features/all/rt/genirq-update-irq_set_irqchip_state-documentation.patch create mode 100644 debian/patches/features/all/rt/hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch create mode 100644 debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch create mode 100644 debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch create mode 100644 debian/patches/features/all/rt/hrtimer-by-timers-by-default-into-the-softirq-context.patch create mode 100644 debian/patches/features/all/rt/hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch create mode 100644 debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch create mode 100644 debian/patches/features/all/rt/iommu-amd-drop-irqs_disabled-warn_on.patch create mode 100644 debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch create mode 100644 debian/patches/features/all/rt/irqchip-gic-v3-its-Make-its_lock-a-raw_spin_lock_t.patch create mode 100644 debian/patches/features/all/rt/irqchip-gic-v3-its-Move-ITS-pend_page-allocation-int.patch create mode 100644 debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch create mode 100644 debian/patches/features/all/rt/jump-label-rt.patch create mode 100644 debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch create mode 100644 debian/patches/features/all/rt/kconfig-preempt-rt-full.patch create mode 100644 debian/patches/features/all/rt/kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch create mode 100644 debian/patches/features/all/rt/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch create mode 100644 debian/patches/features/all/rt/kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch create mode 100644 debian/patches/features/all/rt/kgb-serial-hackaround.patch create mode 100644 debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch create mode 100644 debian/patches/features/all/rt/libata-remove-ata_sff_data_xfer_noirq.patch create mode 100644 debian/patches/features/all/rt/list_bl-fixup-bogus-lockdep-warning.patch create mode 100644 debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch create mode 100644 debian/patches/features/all/rt/locallock-provide-get-put-_locked_ptr-variants.patch create mode 100644 debian/patches/features/all/rt/localversion.patch create mode 100644 debian/patches/features/all/rt/lockdep-disable-self-test.patch create mode 100644 debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch create mode 100644 debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch create mode 100644 debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch create mode 100644 debian/patches/features/all/rt/locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch create mode 100644 debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch create mode 100644 debian/patches/features/all/rt/locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch create mode 100644 debian/patches/features/all/rt/locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch create mode 100644 debian/patches/features/all/rt/md-disable-bcache.patch create mode 100644 debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch create mode 100644 debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch create mode 100644 debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch create mode 100644 debian/patches/features/all/rt/mm-disable-sloub-rt.patch create mode 100644 debian/patches/features/all/rt/mm-enable-slub.patch create mode 100644 debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch create mode 100644 debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch create mode 100644 debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch create mode 100644 debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch create mode 100644 debian/patches/features/all/rt/mm-perform-lru_add_drain_all-remotely.patch create mode 100644 debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch create mode 100644 debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch create mode 100644 debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch create mode 100644 debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch create mode 100644 debian/patches/features/all/rt/mm_zsmalloc_copy_with_get_cpu_var_and_locking.patch create mode 100644 debian/patches/features/all/rt/mutex-no-spin-on-rt.patch create mode 100644 debian/patches/features/all/rt/net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch create mode 100644 debian/patches/features/all/rt/net-Qdisc-use-a-seqlock-instead-seqcount.patch create mode 100644 debian/patches/features/all/rt/net-add-a-lock-around-icmp_sk.patch create mode 100644 debian/patches/features/all/rt/net-add-back-the-missing-serialization-in-ip_send_un.patch create mode 100644 debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch create mode 100644 debian/patches/features/all/rt/net-core-protect-users-of-napi_alloc_cache-against-r.patch create mode 100644 debian/patches/features/all/rt/net-core-use-local_bh_disable-in-netif_rx_ni.patch create mode 100644 debian/patches/features/all/rt/net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch create mode 100644 debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch create mode 100644 debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch create mode 100644 debian/patches/features/all/rt/net-move-xmit_recursion-to-per-task-variable-on-RT.patch create mode 100644 debian/patches/features/all/rt/net-provide-a-way-to-delegate-processing-a-softirq-t.patch create mode 100644 debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch create mode 100644 debian/patches/features/all/rt/net-use-cpu-chill.patch create mode 100644 debian/patches/features/all/rt/net_disable_NET_RX_BUSY_POLL.patch create mode 100644 debian/patches/features/all/rt/ntfs-avoid-disabling-interrupts-during-kmap_atomic.patch create mode 100644 debian/patches/features/all/rt/oleg-signal-rt-fix.patch create mode 100644 debian/patches/features/all/rt/panic-disable-random-on-rt.patch create mode 100644 debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch create mode 100644 debian/patches/features/all/rt/pci-switchtec-Don-t-use-completion-s-wait-queue.patch create mode 100644 debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch create mode 100644 debian/patches/features/all/rt/peterz-percpu-rwsem-rt.patch create mode 100644 debian/patches/features/all/rt/pid.h-include-atomic.h.patch create mode 100644 debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch create mode 100644 debian/patches/features/all/rt/power-disable-highmem-on-rt.patch create mode 100644 debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch create mode 100644 debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch create mode 100644 debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch create mode 100644 debian/patches/features/all/rt/powerpc-ps3-device-init.c-adapt-to-completions-using.patch create mode 100644 debian/patches/features/all/rt/preempt-lazy-support.patch create mode 100644 debian/patches/features/all/rt/preempt-nort-rt-variants.patch create mode 100644 debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch create mode 100644 debian/patches/features/all/rt/printk-kill.patch create mode 100644 debian/patches/features/all/rt/printk-rt-aware.patch create mode 100644 debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch create mode 100644 debian/patches/features/all/rt/radix-tree-use-local-locks.patch create mode 100644 debian/patches/features/all/rt/random-Remove-preempt-disabled-region.patch create mode 100644 debian/patches/features/all/rt/random-avoid-preempt_disable-ed-section.patch create mode 100644 debian/patches/features/all/rt/random-make-it-work-on-rt.patch create mode 100644 debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch create mode 100644 debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch create mode 100644 debian/patches/features/all/rt/rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch create mode 100644 debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch create mode 100644 debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch create mode 100644 debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch create mode 100644 debian/patches/features/all/rt/rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch create mode 100644 debian/patches/features/all/rt/rt-introduce-cpu-chill.patch create mode 100644 debian/patches/features/all/rt/rt-local-irq-lock.patch create mode 100644 debian/patches/features/all/rt/rt-preempt-base-config.patch create mode 100644 debian/patches/features/all/rt/rt-serial-warn-fix.patch create mode 100644 debian/patches/features/all/rt/rtmutex-Make-lock_killable-work.patch create mode 100644 debian/patches/features/all/rt/rtmutex-Provide-rt_mutex_slowlock_locked.patch create mode 100644 debian/patches/features/all/rt/rtmutex-add-mutex-implementation-based-on-rtmutex.patch create mode 100644 debian/patches/features/all/rt/rtmutex-add-rwlock-implementation-based-on-rtmutex.patch create mode 100644 debian/patches/features/all/rt/rtmutex-add-rwsem-implementation-based-on-rtmutex.patch create mode 100644 debian/patches/features/all/rt/rtmutex-add-sleeping-lock-implementation.patch create mode 100644 debian/patches/features/all/rt/rtmutex-add-ww_mutex-addon-for-mutex-rt.patch create mode 100644 debian/patches/features/all/rt/rtmutex-annotate-sleeping-lock-context.patch create mode 100644 debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch create mode 100644 debian/patches/features/all/rt/rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch create mode 100644 debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch create mode 100644 debian/patches/features/all/rt/rtmutex-lock-killable.patch create mode 100644 debian/patches/features/all/rt/rtmutex-trylock-is-okay-on-RT.patch create mode 100644 debian/patches/features/all/rt/rtmutex-wire-up-RT-s-locking.patch create mode 100644 debian/patches/features/all/rt/rtmutex_dont_include_rcu.patch create mode 100644 debian/patches/features/all/rt/sched-core-Remove-get_cpu-from-sched_fork.patch create mode 100644 debian/patches/features/all/rt/sched-delay-put-task.patch create mode 100644 debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch create mode 100644 debian/patches/features/all/rt/sched-disable-ttwu-queue.patch create mode 100644 debian/patches/features/all/rt/sched-limit-nr-migrate.patch create mode 100644 debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch create mode 100644 debian/patches/features/all/rt/sched-migrate_disable-fallback-to-preempt_disable-in.patch create mode 100644 debian/patches/features/all/rt/sched-mmdrop-delayed.patch create mode 100644 debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch create mode 100644 debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch create mode 100644 debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch create mode 100644 debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch create mode 100644 debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch create mode 100644 debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch create mode 100644 debian/patches/features/all/rt/skbufhead-raw-lock.patch create mode 100644 debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch create mode 100644 debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch create mode 100644 debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch create mode 100644 debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch create mode 100644 debian/patches/features/all/rt/softirq-split-locks.patch create mode 100644 debian/patches/features/all/rt/softirq-split-timer-softirqs-out-of-ksoftirqd.patch create mode 100644 debian/patches/features/all/rt/spinlock-types-separate-raw.patch create mode 100644 debian/patches/features/all/rt/squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch create mode 100644 debian/patches/features/all/rt/srcu-replace-local_irqsave-with-a-locallock.patch create mode 100644 debian/patches/features/all/rt/srcu-use-cpu_online-instead-custom-check.patch create mode 100644 debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch create mode 100644 debian/patches/features/all/rt/sysfs-realtime-entry.patch create mode 100644 debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch create mode 100644 debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch create mode 100644 debian/patches/features/all/rt/time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch create mode 100644 debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch create mode 100644 debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch create mode 100644 debian/patches/features/all/rt/tpm_tis-fix-stall-after-iowrite-s.patch create mode 100644 debian/patches/features/all/rt/tty-serial-8250-don-t-take-the-trylock-during-oops.patch create mode 100644 debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch create mode 100644 debian/patches/features/all/rt/usb-do-not-disable-interrupts-in-giveback.patch create mode 100644 debian/patches/features/all/rt/wait.h-include-atomic.h.patch create mode 100644 debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch create mode 100644 debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch create mode 100644 debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch create mode 100644 debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch create mode 100644 debian/patches/features/all/rt/workqueue-use-locallock.patch create mode 100644 debian/patches/features/all/rt/workqueue-use-rcu.patch create mode 100644 debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch create mode 100644 debian/patches/features/all/rt/x86-efi-drop-task_lock-from-efi_switch_mm.patch create mode 100644 debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch create mode 100644 debian/patches/features/all/rt/x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch create mode 100644 debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch create mode 100644 debian/patches/features/all/rt/x86-preempt-lazy.patch create mode 100644 debian/patches/features/all/rt/x86-signal-delay-calling-signals-on-32bit.patch create mode 100644 debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch create mode 100644 debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch diff --git a/debian/changelog b/debian/changelog index 1a2713855..bddd0df50 100644 --- a/debian/changelog +++ b/debian/changelog @@ -2,6 +2,7 @@ linux (4.18.5-1) UNRELEASED; urgency=medium * Set ABI to 1 * [x86,arm64] Disable code signing for upload to unstable + * [rt] Update to 4.18-rc8-rt1 and re-enable -- Ben Hutchings Mon, 27 Aug 2018 14:22:41 +0100 diff --git a/debian/config/defines b/debian/config/defines index e4f46737f..52031054b 100644 --- a/debian/config/defines +++ b/debian/config/defines @@ -121,7 +121,7 @@ debug-info: true signed-code: false [featureset-rt_base] -enabled: false +enabled: true [description] part-long-up: This kernel is not suitable for SMP (multi-processor, diff --git a/debian/patches/features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch b/debian/patches/features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch new file mode 100644 index 000000000..28a4ee117 --- /dev/null +++ b/debian/patches/features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch @@ -0,0 +1,236 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:38 +0200 +Subject: [PATCH 1/6] ARM: at91: add TCB registers definitions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Add registers and bits definitions for the timer counter blocks found on +Atmel ARM SoCs. + +Tested-by: Alexander Dahl +Tested-by: Andras Szemzo +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + include/soc/at91/atmel_tcb.h | 216 +++++++++++++++++++++++++++++++++++++++++++ + 1 file changed, 216 insertions(+) + create mode 100644 include/soc/at91/atmel_tcb.h + +--- /dev/null ++++ b/include/soc/at91/atmel_tcb.h +@@ -0,0 +1,216 @@ ++// SPDX-License-Identifier: GPL-2.0 ++/* Copyright (C) 2018 Microchip */ ++ ++#ifndef __SOC_ATMEL_TCB_H ++#define __SOC_ATMEL_TCB_H ++ ++/* Channel registers */ ++#define ATMEL_TC_COFFS(c) ((c) * 0x40) ++#define ATMEL_TC_CCR(c) ATMEL_TC_COFFS(c) ++#define ATMEL_TC_CMR(c) (ATMEL_TC_COFFS(c) + 0x4) ++#define ATMEL_TC_SMMR(c) (ATMEL_TC_COFFS(c) + 0x8) ++#define ATMEL_TC_RAB(c) (ATMEL_TC_COFFS(c) + 0xc) ++#define ATMEL_TC_CV(c) (ATMEL_TC_COFFS(c) + 0x10) ++#define ATMEL_TC_RA(c) (ATMEL_TC_COFFS(c) + 0x14) ++#define ATMEL_TC_RB(c) (ATMEL_TC_COFFS(c) + 0x18) ++#define ATMEL_TC_RC(c) (ATMEL_TC_COFFS(c) + 0x1c) ++#define ATMEL_TC_SR(c) (ATMEL_TC_COFFS(c) + 0x20) ++#define ATMEL_TC_IER(c) (ATMEL_TC_COFFS(c) + 0x24) ++#define ATMEL_TC_IDR(c) (ATMEL_TC_COFFS(c) + 0x28) ++#define ATMEL_TC_IMR(c) (ATMEL_TC_COFFS(c) + 0x2c) ++#define ATMEL_TC_EMR(c) (ATMEL_TC_COFFS(c) + 0x30) ++ ++/* Block registers */ ++#define ATMEL_TC_BCR 0xc0 ++#define ATMEL_TC_BMR 0xc4 ++#define ATMEL_TC_QIER 0xc8 ++#define ATMEL_TC_QIDR 0xcc ++#define ATMEL_TC_QIMR 0xd0 ++#define ATMEL_TC_QISR 0xd4 ++#define ATMEL_TC_FMR 0xd8 ++#define ATMEL_TC_WPMR 0xe4 ++ ++/* CCR fields */ ++#define ATMEL_TC_CCR_CLKEN BIT(0) ++#define ATMEL_TC_CCR_CLKDIS BIT(1) ++#define ATMEL_TC_CCR_SWTRG BIT(2) ++ ++/* Common CMR fields */ ++#define ATMEL_TC_CMR_TCLKS_MSK GENMASK(2, 0) ++#define ATMEL_TC_CMR_TCLK(x) (x) ++#define ATMEL_TC_CMR_XC(x) ((x) + 5) ++#define ATMEL_TC_CMR_CLKI BIT(3) ++#define ATMEL_TC_CMR_BURST_MSK GENMASK(5, 4) ++#define ATMEL_TC_CMR_BURST_XC(x) (((x) + 1) << 4) ++#define ATMEL_TC_CMR_WAVE BIT(15) ++ ++/* Capture mode CMR fields */ ++#define ATMEL_TC_CMR_LDBSTOP BIT(6) ++#define ATMEL_TC_CMR_LDBDIS BIT(7) ++#define ATMEL_TC_CMR_ETRGEDG_MSK GENMASK(9, 8) ++#define ATMEL_TC_CMR_ETRGEDG_NONE (0 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_RISING (1 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_FALLING (2 << 8) ++#define ATMEL_TC_CMR_ETRGEDG_BOTH (3 << 8) ++#define ATMEL_TC_CMR_ABETRG BIT(10) ++#define ATMEL_TC_CMR_CPCTRG BIT(14) ++#define ATMEL_TC_CMR_LDRA_MSK GENMASK(17, 16) ++#define ATMEL_TC_CMR_LDRA_NONE (0 << 16) ++#define ATMEL_TC_CMR_LDRA_RISING (1 << 16) ++#define ATMEL_TC_CMR_LDRA_FALLING (2 << 16) ++#define ATMEL_TC_CMR_LDRA_BOTH (3 << 16) ++#define ATMEL_TC_CMR_LDRB_MSK GENMASK(19, 18) ++#define ATMEL_TC_CMR_LDRB_NONE (0 << 18) ++#define ATMEL_TC_CMR_LDRB_RISING (1 << 18) ++#define ATMEL_TC_CMR_LDRB_FALLING (2 << 18) ++#define ATMEL_TC_CMR_LDRB_BOTH (3 << 18) ++#define ATMEL_TC_CMR_SBSMPLR_MSK GENMASK(22, 20) ++#define ATMEL_TC_CMR_SBSMPLR(x) ((x) << 20) ++ ++/* Waveform mode CMR fields */ ++#define ATMEL_TC_CMR_CPCSTOP BIT(6) ++#define ATMEL_TC_CMR_CPCDIS BIT(7) ++#define ATMEL_TC_CMR_EEVTEDG_MSK GENMASK(9, 8) ++#define ATMEL_TC_CMR_EEVTEDG_NONE (0 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_RISING (1 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_FALLING (2 << 8) ++#define ATMEL_TC_CMR_EEVTEDG_BOTH (3 << 8) ++#define ATMEL_TC_CMR_EEVT_MSK GENMASK(11, 10) ++#define ATMEL_TC_CMR_EEVT_XC(x) (((x) + 1) << 10) ++#define ATMEL_TC_CMR_ENETRG BIT(12) ++#define ATMEL_TC_CMR_WAVESEL_MSK GENMASK(14, 13) ++#define ATMEL_TC_CMR_WAVESEL_UP (0 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPDOWN (1 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPRC (2 << 13) ++#define ATMEL_TC_CMR_WAVESEL_UPDOWNRC (3 << 13) ++#define ATMEL_TC_CMR_ACPA_MSK GENMASK(17, 16) ++#define ATMEL_TC_CMR_ACPA(a) (ATMEL_TC_CMR_ACTION_##a << 16) ++#define ATMEL_TC_CMR_ACPC_MSK GENMASK(19, 18) ++#define ATMEL_TC_CMR_ACPC(a) (ATMEL_TC_CMR_ACTION_##a << 18) ++#define ATMEL_TC_CMR_AEEVT_MSK GENMASK(21, 20) ++#define ATMEL_TC_CMR_AEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 20) ++#define ATMEL_TC_CMR_ASWTRG_MSK GENMASK(23, 22) ++#define ATMEL_TC_CMR_ASWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 22) ++#define ATMEL_TC_CMR_BCPB_MSK GENMASK(25, 24) ++#define ATMEL_TC_CMR_BCPB(a) (ATMEL_TC_CMR_ACTION_##a << 24) ++#define ATMEL_TC_CMR_BCPC_MSK GENMASK(27, 26) ++#define ATMEL_TC_CMR_BCPC(a) (ATMEL_TC_CMR_ACTION_##a << 26) ++#define ATMEL_TC_CMR_BEEVT_MSK GENMASK(29, 28) ++#define ATMEL_TC_CMR_BEEVT(a) (ATMEL_TC_CMR_ACTION_##a << 28) ++#define ATMEL_TC_CMR_BSWTRG_MSK GENMASK(31, 30) ++#define ATMEL_TC_CMR_BSWTRG(a) (ATMEL_TC_CMR_ACTION_##a << 30) ++#define ATMEL_TC_CMR_ACTION_NONE 0 ++#define ATMEL_TC_CMR_ACTION_SET 1 ++#define ATMEL_TC_CMR_ACTION_CLEAR 2 ++#define ATMEL_TC_CMR_ACTION_TOGGLE 3 ++ ++/* SMMR fields */ ++#define ATMEL_TC_SMMR_GCEN BIT(0) ++#define ATMEL_TC_SMMR_DOWN BIT(1) ++ ++/* SR/IER/IDR/IMR fields */ ++#define ATMEL_TC_COVFS BIT(0) ++#define ATMEL_TC_LOVRS BIT(1) ++#define ATMEL_TC_CPAS BIT(2) ++#define ATMEL_TC_CPBS BIT(3) ++#define ATMEL_TC_CPCS BIT(4) ++#define ATMEL_TC_LDRAS BIT(5) ++#define ATMEL_TC_LDRBS BIT(6) ++#define ATMEL_TC_ETRGS BIT(7) ++#define ATMEL_TC_CLKSTA BIT(16) ++#define ATMEL_TC_MTIOA BIT(17) ++#define ATMEL_TC_MTIOB BIT(18) ++ ++/* EMR fields */ ++#define ATMEL_TC_EMR_TRIGSRCA_MSK GENMASK(1, 0) ++#define ATMEL_TC_EMR_TRIGSRCA_TIOA 0 ++#define ATMEL_TC_EMR_TRIGSRCA_PWMX 1 ++#define ATMEL_TC_EMR_TRIGSRCB_MSK GENMASK(5, 4) ++#define ATMEL_TC_EMR_TRIGSRCB_TIOB (0 << 4) ++#define ATMEL_TC_EMR_TRIGSRCB_PWM (1 << 4) ++#define ATMEL_TC_EMR_NOCLKDIV BIT(8) ++ ++/* BCR fields */ ++#define ATMEL_TC_BCR_SYNC BIT(0) ++ ++/* BMR fields */ ++#define ATMEL_TC_BMR_TCXC_MSK(c) GENMASK(((c) * 2) + 1, (c) * 2) ++#define ATMEL_TC_BMR_TCXC(x, c) ((x) << (2 * (c))) ++#define ATMEL_TC_BMR_QDEN BIT(8) ++#define ATMEL_TC_BMR_POSEN BIT(9) ++#define ATMEL_TC_BMR_SPEEDEN BIT(10) ++#define ATMEL_TC_BMR_QDTRANS BIT(11) ++#define ATMEL_TC_BMR_EDGPHA BIT(12) ++#define ATMEL_TC_BMR_INVA BIT(13) ++#define ATMEL_TC_BMR_INVB BIT(14) ++#define ATMEL_TC_BMR_INVIDX BIT(15) ++#define ATMEL_TC_BMR_SWAP BIT(16) ++#define ATMEL_TC_BMR_IDXPHB BIT(17) ++#define ATMEL_TC_BMR_AUTOC BIT(18) ++#define ATMEL_TC_MAXFILT_MSK GENMASK(25, 20) ++#define ATMEL_TC_MAXFILT(x) (((x) - 1) << 20) ++#define ATMEL_TC_MAXCMP_MSK GENMASK(29, 26) ++#define ATMEL_TC_MAXCMP(x) ((x) << 26) ++ ++/* QEDC fields */ ++#define ATMEL_TC_QEDC_IDX BIT(0) ++#define ATMEL_TC_QEDC_DIRCHG BIT(1) ++#define ATMEL_TC_QEDC_QERR BIT(2) ++#define ATMEL_TC_QEDC_MPE BIT(3) ++#define ATMEL_TC_QEDC_DIR BIT(8) ++ ++/* FMR fields */ ++#define ATMEL_TC_FMR_ENCF(x) BIT(x) ++ ++/* WPMR fields */ ++#define ATMEL_TC_WPMR_WPKEY (0x54494d << 8) ++#define ATMEL_TC_WPMR_WPEN BIT(0) ++ ++static inline struct clk *tcb_clk_get(struct device_node *node, int channel) ++{ ++ struct clk *clk; ++ char clk_name[] = "t0_clk"; ++ ++ clk_name[1] += channel; ++ clk = of_clk_get_by_name(node->parent, clk_name); ++ if (!IS_ERR(clk)) ++ return clk; ++ ++ return of_clk_get_by_name(node->parent, "t0_clk"); ++} ++ ++static inline int tcb_irq_get(struct device_node *node, int channel) ++{ ++ int irq; ++ ++ irq = of_irq_get(node->parent, channel); ++ if (irq > 0) ++ return irq; ++ ++ return of_irq_get(node->parent, 0); ++} ++ ++static const u8 atmel_tc_divisors[5] = { 2, 8, 32, 128, 0, }; ++ ++struct atmel_tcb_info { ++ int bits; ++}; ++ ++static const struct atmel_tcb_info atmel_tcb_infos[] = { ++ { .bits = 16 }, ++ { .bits = 32 }, ++}; ++ ++static const struct of_device_id atmel_tcb_dt_ids[] = { ++ { ++ .compatible = "atmel,at91rm9200-tcb", ++ .data = &atmel_tcb_infos[0], ++ }, { ++ .compatible = "atmel,at91sam9x5-tcb", ++ .data = &atmel_tcb_infos[1], ++ }, { ++ /* sentinel */ ++ } ++}; ++ ++#endif /* __SOC_ATMEL_TCB_H */ diff --git a/debian/patches/features/all/rt/0001-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch b/debian/patches/features/all/rt/0001-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch new file mode 100644 index 000000000..dad2b88c3 --- /dev/null +++ b/debian/patches/features/all/rt/0001-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch @@ -0,0 +1,167 @@ +From: Peter Zijlstra +Date: Mon, 28 May 2018 15:24:20 +0200 +Subject: [PATCH 1/4] Split IRQ-off and zone->lock while freeing pages from PCP + list #1 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Split the IRQ-off section while accessing the PCP list from zone->lock +while freeing pages. +Introcude isolate_pcp_pages() which separates the pages from the PCP +list onto a temporary list and then free the temporary list via +free_pcppages_bulk(). + +Signed-off-by: Peter Zijlstra +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/page_alloc.c | 82 +++++++++++++++++++++++++++++++++++--------------------- + 1 file changed, 52 insertions(+), 30 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -1067,7 +1067,7 @@ static inline void prefetch_buddy(struct + } + + /* +- * Frees a number of pages from the PCP lists ++ * Frees a number of pages which have been collected from the pcp lists. + * Assumes all pages on list are in same zone, and of same order. + * count is the number of pages to free. + * +@@ -1078,14 +1078,41 @@ static inline void prefetch_buddy(struct + * pinned" detection logic. + */ + static void free_pcppages_bulk(struct zone *zone, int count, +- struct per_cpu_pages *pcp) ++ struct list_head *head) ++{ ++ bool isolated_pageblocks; ++ struct page *page, *tmp; ++ unsigned long flags; ++ ++ spin_lock_irqsave(&zone->lock, flags); ++ isolated_pageblocks = has_isolate_pageblock(zone); ++ ++ /* ++ * Use safe version since after __free_one_page(), ++ * page->lru.next will not point to original list. ++ */ ++ list_for_each_entry_safe(page, tmp, head, lru) { ++ int mt = get_pcppage_migratetype(page); ++ /* MIGRATE_ISOLATE page should not go to pcplists */ ++ VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); ++ /* Pageblock could have been isolated meanwhile */ ++ if (unlikely(isolated_pageblocks)) ++ mt = get_pageblock_migratetype(page); ++ ++ __free_one_page(page, page_to_pfn(page), zone, 0, mt); ++ trace_mm_page_pcpu_drain(page, 0, mt); ++ } ++ spin_unlock_irqrestore(&zone->lock, flags); ++} ++ ++static void isolate_pcp_pages(int count, struct per_cpu_pages *pcp, ++ struct list_head *dst) ++ + { + int migratetype = 0; + int batch_free = 0; + int prefetch_nr = 0; +- bool isolated_pageblocks; +- struct page *page, *tmp; +- LIST_HEAD(head); ++ struct page *page; + + while (count) { + struct list_head *list; +@@ -1117,7 +1144,7 @@ static void free_pcppages_bulk(struct zo + if (bulkfree_pcp_prepare(page)) + continue; + +- list_add_tail(&page->lru, &head); ++ list_add_tail(&page->lru, dst); + + /* + * We are going to put the page back to the global +@@ -1132,26 +1159,6 @@ static void free_pcppages_bulk(struct zo + prefetch_buddy(page); + } while (--count && --batch_free && !list_empty(list)); + } +- +- spin_lock(&zone->lock); +- isolated_pageblocks = has_isolate_pageblock(zone); +- +- /* +- * Use safe version since after __free_one_page(), +- * page->lru.next will not point to original list. +- */ +- list_for_each_entry_safe(page, tmp, &head, lru) { +- int mt = get_pcppage_migratetype(page); +- /* MIGRATE_ISOLATE page should not go to pcplists */ +- VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); +- /* Pageblock could have been isolated meanwhile */ +- if (unlikely(isolated_pageblocks)) +- mt = get_pageblock_migratetype(page); +- +- __free_one_page(page, page_to_pfn(page), zone, 0, mt); +- trace_mm_page_pcpu_drain(page, 0, mt); +- } +- spin_unlock(&zone->lock); + } + + static void free_one_page(struct zone *zone, +@@ -2515,13 +2522,18 @@ void drain_zone_pages(struct zone *zone, + { + unsigned long flags; + int to_drain, batch; ++ LIST_HEAD(dst); + + local_irq_save(flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) +- free_pcppages_bulk(zone, to_drain, pcp); ++ isolate_pcp_pages(to_drain, pcp, &dst); ++ + local_irq_restore(flags); ++ ++ if (to_drain > 0) ++ free_pcppages_bulk(zone, to_drain, &dst); + } + #endif + +@@ -2537,14 +2549,21 @@ static void drain_pages_zone(unsigned in + unsigned long flags; + struct per_cpu_pageset *pset; + struct per_cpu_pages *pcp; ++ LIST_HEAD(dst); ++ int count; + + local_irq_save(flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +- if (pcp->count) +- free_pcppages_bulk(zone, pcp->count, pcp); ++ count = pcp->count; ++ if (count) ++ isolate_pcp_pages(count, pcp, &dst); ++ + local_irq_restore(flags); ++ ++ if (count) ++ free_pcppages_bulk(zone, count, &dst); + } + + /* +@@ -2766,7 +2785,10 @@ static void free_unref_page_commit(struc + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- free_pcppages_bulk(zone, batch, pcp); ++ LIST_HEAD(dst); ++ ++ isolate_pcp_pages(batch, pcp, &dst); ++ free_pcppages_bulk(zone, batch, &dst); + } + } + diff --git a/debian/patches/features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch b/debian/patches/features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch new file mode 100644 index 000000000..7468afe58 --- /dev/null +++ b/debian/patches/features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch @@ -0,0 +1,103 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 7 May 2018 16:51:09 +0200 +Subject: [PATCH] bdi: use refcount_t for reference counting instead atomic_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +refcount_t type and corresponding API should be used instead of atomic_t when +the variable is used as a reference counter. This allows to avoid accidental +refcounter overflows that might lead to use-after-free situations. + +Suggested-by: Peter Zijlstra +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/backing-dev-defs.h | 3 ++- + include/linux/backing-dev.h | 4 ++-- + mm/backing-dev.c | 12 ++++++------ + 3 files changed, 10 insertions(+), 9 deletions(-) + +--- a/include/linux/backing-dev-defs.h ++++ b/include/linux/backing-dev-defs.h +@@ -12,6 +12,7 @@ + #include + #include + #include ++#include + + struct page; + struct device; +@@ -75,7 +76,7 @@ enum wb_reason { + */ + struct bdi_writeback_congested { + unsigned long state; /* WB_[a]sync_congested flags */ +- atomic_t refcnt; /* nr of attached wb's and blkg */ ++ refcount_t refcnt; /* nr of attached wb's and blkg */ + + #ifdef CONFIG_CGROUP_WRITEBACK + struct backing_dev_info *__bdi; /* the associated bdi, set to NULL +--- a/include/linux/backing-dev.h ++++ b/include/linux/backing-dev.h +@@ -404,13 +404,13 @@ static inline bool inode_cgwb_enabled(st + static inline struct bdi_writeback_congested * + wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) + { +- atomic_inc(&bdi->wb_congested->refcnt); ++ refcount_inc(&bdi->wb_congested->refcnt); + return bdi->wb_congested; + } + + static inline void wb_congested_put(struct bdi_writeback_congested *congested) + { +- if (atomic_dec_and_test(&congested->refcnt)) ++ if (refcount_dec_and_test(&congested->refcnt)) + kfree(congested); + } + +--- a/mm/backing-dev.c ++++ b/mm/backing-dev.c +@@ -438,10 +438,10 @@ wb_congested_get_create(struct backing_d + if (new_congested) { + /* !found and storage for new one already allocated, insert */ + congested = new_congested; +- new_congested = NULL; + rb_link_node(&congested->rb_node, parent, node); + rb_insert_color(&congested->rb_node, &bdi->cgwb_congested_tree); +- goto found; ++ spin_unlock_irqrestore(&cgwb_lock, flags); ++ return congested; + } + + spin_unlock_irqrestore(&cgwb_lock, flags); +@@ -451,13 +451,13 @@ wb_congested_get_create(struct backing_d + if (!new_congested) + return NULL; + +- atomic_set(&new_congested->refcnt, 0); ++ refcount_set(&new_congested->refcnt, 1); + new_congested->__bdi = bdi; + new_congested->blkcg_id = blkcg_id; + goto retry; + + found: +- atomic_inc(&congested->refcnt); ++ refcount_inc(&congested->refcnt); + spin_unlock_irqrestore(&cgwb_lock, flags); + kfree(new_congested); + return congested; +@@ -474,7 +474,7 @@ void wb_congested_put(struct bdi_writeba + unsigned long flags; + + local_irq_save(flags); +- if (!atomic_dec_and_lock(&congested->refcnt, &cgwb_lock)) { ++ if (!refcount_dec_and_lock(&congested->refcnt, &cgwb_lock)) { + local_irq_restore(flags); + return; + } +@@ -804,7 +804,7 @@ static int cgwb_bdi_init(struct backing_ + if (!bdi->wb_congested) + return -ENOMEM; + +- atomic_set(&bdi->wb_congested->refcnt, 1); ++ refcount_set(&bdi->wb_congested->refcnt, 1); + + err = wb_init(&bdi->wb, bdi, 1, GFP_KERNEL); + if (err) { diff --git a/debian/patches/features/all/rt/0001-mm-list_lru-use-list_lru_walk_one-in-list_lru_walk_n.patch b/debian/patches/features/all/rt/0001-mm-list_lru-use-list_lru_walk_one-in-list_lru_walk_n.patch new file mode 100644 index 000000000..aa43e7a62 --- /dev/null +++ b/debian/patches/features/all/rt/0001-mm-list_lru-use-list_lru_walk_one-in-list_lru_walk_n.patch @@ -0,0 +1,31 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 3 Jul 2018 12:56:19 +0200 +Subject: [PATCH 1/4] mm/list_lru: use list_lru_walk_one() in + list_lru_walk_node() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +list_lru_walk_node() invokes __list_lru_walk_one() with -1 as the +memcg_idx parameter. The same can be achieved by list_lru_walk_one() and +passing NULL as memcg argument which then gets converted into -1. This +is a preparation step when the spin_lock() function is lifted to the +caller of __list_lru_walk_one(). +Invoke list_lru_walk_one() instead __list_lru_walk_one() when possible. + +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/list_lru.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/mm/list_lru.c ++++ b/mm/list_lru.c +@@ -272,8 +272,8 @@ unsigned long list_lru_walk_node(struct + long isolated = 0; + int memcg_idx; + +- isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg, +- nr_to_walk); ++ isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, ++ nr_to_walk); + if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) { + isolated += __list_lru_walk_one(lru, nid, memcg_idx, diff --git a/debian/patches/features/all/rt/0001-mm-workingset-remove-local_irq_disable-from-count_sh.patch b/debian/patches/features/all/rt/0001-mm-workingset-remove-local_irq_disable-from-count_sh.patch new file mode 100644 index 000000000..8d9f31b91 --- /dev/null +++ b/debian/patches/features/all/rt/0001-mm-workingset-remove-local_irq_disable-from-count_sh.patch @@ -0,0 +1,46 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 22 Jun 2018 10:48:51 +0200 +Subject: [PATCH 1/3] mm: workingset: remove local_irq_disable() from + count_shadow_nodes() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In commit 0c7c1bed7e13 ("mm: make counting of list_lru_one::nr_items +lockless") the + spin_lock(&nlru->lock); + +statement was replaced with + rcu_read_lock(); + +in __list_lru_count_one(). The comment in count_shadow_nodes() says that +the local_irq_disable() is required because the lock must be acquired +with disabled interrupts and (spin_lock()) does not do so. +Since the lock is replaced with rcu_read_lock() the local_irq_disable() +is no longer needed. The code path is + list_lru_shrink_count() + -> list_lru_count_one() + -> __list_lru_count_one() + -> rcu_read_lock() + -> list_lru_from_memcg_idx() + -> rcu_read_unlock() + +Remove the local_irq_disable() statement. + +Cc: Kirill Tkhai +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/workingset.c | 3 --- + 1 file changed, 3 deletions(-) + +--- a/mm/workingset.c ++++ b/mm/workingset.c +@@ -366,10 +366,7 @@ static unsigned long count_shadow_nodes( + unsigned long nodes; + unsigned long cache; + +- /* list_lru lock nests inside the IRQ-safe i_pages lock */ +- local_irq_disable(); + nodes = list_lru_shrink_count(&shadow_nodes, sc); +- local_irq_enable(); + + /* + * Approximate a reasonable limit for the radix tree nodes diff --git a/debian/patches/features/all/rt/0002-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch b/debian/patches/features/all/rt/0002-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch new file mode 100644 index 000000000..1ae891d45 --- /dev/null +++ b/debian/patches/features/all/rt/0002-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch @@ -0,0 +1,166 @@ +From: Peter Zijlstra +Date: Mon, 28 May 2018 15:24:21 +0200 +Subject: [PATCH 2/4] Split IRQ-off and zone->lock while freeing pages from PCP + list #2 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Split the IRQ-off section while accessing the PCP list from zone->lock +while freeing pages. +Introcude isolate_pcp_pages() which separates the pages from the PCP +list onto a temporary list and then free the temporary list via +free_pcppages_bulk(). + +Signed-off-by: Peter Zijlstra +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/page_alloc.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++---------- + 1 file changed, 50 insertions(+), 10 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -1077,8 +1077,8 @@ static inline void prefetch_buddy(struct + * And clear the zone's pages_scanned counter, to hold off the "all pages are + * pinned" detection logic. + */ +-static void free_pcppages_bulk(struct zone *zone, int count, +- struct list_head *head) ++static void free_pcppages_bulk(struct zone *zone, struct list_head *head, ++ bool zone_retry) + { + bool isolated_pageblocks; + struct page *page, *tmp; +@@ -1093,12 +1093,27 @@ static void free_pcppages_bulk(struct zo + */ + list_for_each_entry_safe(page, tmp, head, lru) { + int mt = get_pcppage_migratetype(page); ++ ++ if (page_zone(page) != zone) { ++ /* ++ * free_unref_page_list() sorts pages by zone. If we end ++ * up with pages from a different NUMA nodes belonging ++ * to the same ZONE index then we need to redo with the ++ * correct ZONE pointer. Skip the page for now, redo it ++ * on the next iteration. ++ */ ++ WARN_ON_ONCE(zone_retry == false); ++ if (zone_retry) ++ continue; ++ } ++ + /* MIGRATE_ISOLATE page should not go to pcplists */ + VM_BUG_ON_PAGE(is_migrate_isolate(mt), page); + /* Pageblock could have been isolated meanwhile */ + if (unlikely(isolated_pageblocks)) + mt = get_pageblock_migratetype(page); + ++ list_del(&page->lru); + __free_one_page(page, page_to_pfn(page), zone, 0, mt); + trace_mm_page_pcpu_drain(page, 0, mt); + } +@@ -2533,7 +2548,7 @@ void drain_zone_pages(struct zone *zone, + local_irq_restore(flags); + + if (to_drain > 0) +- free_pcppages_bulk(zone, to_drain, &dst); ++ free_pcppages_bulk(zone, &dst, false); + } + #endif + +@@ -2563,7 +2578,7 @@ static void drain_pages_zone(unsigned in + local_irq_restore(flags); + + if (count) +- free_pcppages_bulk(zone, count, &dst); ++ free_pcppages_bulk(zone, &dst, false); + } + + /* +@@ -2756,7 +2771,8 @@ static bool free_unref_page_prepare(stru + return true; + } + +-static void free_unref_page_commit(struct page *page, unsigned long pfn) ++static void free_unref_page_commit(struct page *page, unsigned long pfn, ++ struct list_head *dst) + { + struct zone *zone = page_zone(page); + struct per_cpu_pages *pcp; +@@ -2785,10 +2801,8 @@ static void free_unref_page_commit(struc + pcp->count++; + if (pcp->count >= pcp->high) { + unsigned long batch = READ_ONCE(pcp->batch); +- LIST_HEAD(dst); + +- isolate_pcp_pages(batch, pcp, &dst); +- free_pcppages_bulk(zone, batch, &dst); ++ isolate_pcp_pages(batch, pcp, dst); + } + } + +@@ -2799,13 +2813,17 @@ void free_unref_page(struct page *page) + { + unsigned long flags; + unsigned long pfn = page_to_pfn(page); ++ struct zone *zone = page_zone(page); ++ LIST_HEAD(dst); + + if (!free_unref_page_prepare(page, pfn)) + return; + + local_irq_save(flags); +- free_unref_page_commit(page, pfn); ++ free_unref_page_commit(page, pfn, &dst); + local_irq_restore(flags); ++ if (!list_empty(&dst)) ++ free_pcppages_bulk(zone, &dst, false); + } + + /* +@@ -2816,6 +2834,11 @@ void free_unref_page_list(struct list_he + struct page *page, *next; + unsigned long flags, pfn; + int batch_count = 0; ++ struct list_head dsts[__MAX_NR_ZONES]; ++ int i; ++ ++ for (i = 0; i < __MAX_NR_ZONES; i++) ++ INIT_LIST_HEAD(&dsts[i]); + + /* Prepare pages for freeing */ + list_for_each_entry_safe(page, next, list, lru) { +@@ -2828,10 +2851,12 @@ void free_unref_page_list(struct list_he + local_irq_save(flags); + list_for_each_entry_safe(page, next, list, lru) { + unsigned long pfn = page_private(page); ++ enum zone_type type; + + set_page_private(page, 0); + trace_mm_page_free_batched(page); +- free_unref_page_commit(page, pfn); ++ type = page_zonenum(page); ++ free_unref_page_commit(page, pfn, &dsts[type]); + + /* + * Guard against excessive IRQ disabled times when we get +@@ -2844,6 +2869,21 @@ void free_unref_page_list(struct list_he + } + } + local_irq_restore(flags); ++ ++ for (i = 0; i < __MAX_NR_ZONES; ) { ++ struct page *page; ++ struct zone *zone; ++ ++ if (list_empty(&dsts[i])) { ++ i++; ++ continue; ++ } ++ ++ page = list_first_entry(&dsts[i], struct page, lru); ++ zone = page_zone(page); ++ ++ free_pcppages_bulk(zone, &dsts[i], true); ++ } + } + + /* diff --git a/debian/patches/features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch b/debian/patches/features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch new file mode 100644 index 000000000..22db17047 --- /dev/null +++ b/debian/patches/features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch @@ -0,0 +1,672 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:39 +0200 +Subject: [PATCH 2/6] clocksource/drivers: Add a new driver for the Atmel ARM + TC blocks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Add a driver for the Atmel Timer Counter Blocks. This driver provides a +clocksource and two clockevent devices. + +One of the clockevent device is linked to the clocksource counter and so it +will run at the same frequency. This will be used when there is only on TCB +channel available for timers. + +The other clockevent device runs on a separate TCB channel when available. + +This driver uses regmap and syscon to be able to probe early in the boot +and avoid having to switch on the TCB clocksource later. Using regmap also +means that unused TCB channels may be used by other drivers (PWM for +example). read/writel are still used to access channel specific registers +to avoid the performance impact of regmap (mainly locking). + +Tested-by: Alexander Dahl +Tested-by: Andras Szemzo +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/clocksource/Kconfig | 8 + drivers/clocksource/Makefile | 3 + drivers/clocksource/timer-atmel-tcb.c | 608 ++++++++++++++++++++++++++++++++++ + 3 files changed, 618 insertions(+), 1 deletion(-) + create mode 100644 drivers/clocksource/timer-atmel-tcb.c + +--- a/drivers/clocksource/Kconfig ++++ b/drivers/clocksource/Kconfig +@@ -403,6 +403,14 @@ config ATMEL_ST + help + Support for the Atmel ST timer. + ++config ATMEL_ARM_TCB_CLKSRC ++ bool "Microchip ARM TC Block" if COMPILE_TEST ++ select REGMAP_MMIO ++ depends on GENERIC_CLOCKEVENTS ++ help ++ This enables build of clocksource and clockevent driver for ++ the integrated Timer Counter Blocks in Microchip ARM SoCs. ++ + config CLKSRC_EXYNOS_MCT + bool "Exynos multi core timer driver" if COMPILE_TEST + depends on ARM || ARM64 +--- a/drivers/clocksource/Makefile ++++ b/drivers/clocksource/Makefile +@@ -3,7 +3,8 @@ obj-$(CONFIG_TIMER_OF) += timer-of.o + obj-$(CONFIG_TIMER_PROBE) += timer-probe.o + obj-$(CONFIG_ATMEL_PIT) += timer-atmel-pit.o + obj-$(CONFIG_ATMEL_ST) += timer-atmel-st.o +-obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o ++obj-$(CONFIG_ATMEL_TCB_CLKSRC) += tcb_clksrc.o ++obj-$(CONFIG_ATMEL_ARM_TCB_CLKSRC) += timer-atmel-tcb.o + obj-$(CONFIG_X86_PM_TIMER) += acpi_pm.o + obj-$(CONFIG_SCx200HR_TIMER) += scx200_hrt.o + obj-$(CONFIG_CS5535_CLOCK_EVENT_SRC) += cs5535-clockevt.o +--- /dev/null ++++ b/drivers/clocksource/timer-atmel-tcb.c +@@ -0,0 +1,608 @@ ++// SPDX-License-Identifier: GPL-2.0 ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++static struct atmel_tcb_clksrc { ++ struct clocksource clksrc; ++ struct clock_event_device clkevt; ++ struct regmap *regmap; ++ void __iomem *base; ++ struct clk *clk[2]; ++ char name[20]; ++ int channels[2]; ++ int bits; ++ int irq; ++ struct { ++ u32 cmr; ++ u32 imr; ++ u32 rc; ++ bool clken; ++ } cache[2]; ++ u32 bmr_cache; ++ bool registered; ++} tc = { ++ .clksrc = { ++ .rating = 200, ++ .mask = CLOCKSOURCE_MASK(32), ++ .flags = CLOCK_SOURCE_IS_CONTINUOUS, ++ }, ++ .clkevt = { ++ .features = CLOCK_EVT_FEAT_ONESHOT, ++ /* Should be lower than at91rm9200's system timer */ ++ .rating = 125, ++ }, ++}; ++ ++static struct tc_clkevt_device { ++ struct clock_event_device clkevt; ++ struct regmap *regmap; ++ void __iomem *base; ++ struct clk *slow_clk; ++ struct clk *clk; ++ char name[20]; ++ int channel; ++ int irq; ++ struct { ++ u32 cmr; ++ u32 imr; ++ u32 rc; ++ bool clken; ++ } cache; ++ bool registered; ++} tce = { ++ .clkevt = { ++ .features = CLOCK_EVT_FEAT_PERIODIC | ++ CLOCK_EVT_FEAT_ONESHOT, ++ /* ++ * Should be lower than at91rm9200's system timer ++ * but higher than tc.clkevt.rating ++ */ ++ .rating = 140, ++ }, ++}; ++ ++/* ++ * Clockevent device using its own channel ++ */ ++static int tc_clkevt2_shutdown(struct clock_event_device *d) ++{ ++ writel(0xff, tce.base + ATMEL_TC_IDR(tce.channel)); ++ writel(ATMEL_TC_CCR_CLKDIS, tce.base + ATMEL_TC_CCR(tce.channel)); ++ if (!clockevent_state_detached(d)) ++ clk_disable(tce.clk); ++ ++ return 0; ++} ++ ++/* For now, we always use the 32K clock ... this optimizes for NO_HZ, ++ * because using one of the divided clocks would usually mean the ++ * tick rate can never be less than several dozen Hz (vs 0.5 Hz). ++ * ++ * A divided clock could be good for high resolution timers, since ++ * 30.5 usec resolution can seem "low". ++ */ ++static int tc_clkevt2_set_oneshot(struct clock_event_device *d) ++{ ++ if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) ++ tc_clkevt2_shutdown(d); ++ ++ clk_enable(tce.clk); ++ ++ /* slow clock, count up to RC, then irq and stop */ ++ writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_CPCSTOP | ++ ATMEL_TC_CMR_WAVE | ATMEL_TC_CMR_WAVESEL_UPRC, ++ tce.base + ATMEL_TC_CMR(tce.channel)); ++ writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channel)); ++ ++ return 0; ++} ++ ++static int tc_clkevt2_set_periodic(struct clock_event_device *d) ++{ ++ if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) ++ tc_clkevt2_shutdown(d); ++ ++ /* By not making the gentime core emulate periodic mode on top ++ * of oneshot, we get lower overhead and improved accuracy. ++ */ ++ clk_enable(tce.clk); ++ ++ /* slow clock, count up to RC, then irq and restart */ ++ writel(ATMEL_TC_CMR_TCLK(4) | ATMEL_TC_CMR_WAVE | ++ ATMEL_TC_CMR_WAVESEL_UPRC, ++ tce.base + ATMEL_TC_CMR(tce.channel)); ++ writel((32768 + HZ / 2) / HZ, tce.base + ATMEL_TC_RC(tce.channel)); ++ ++ /* Enable clock and interrupts on RC compare */ ++ writel(ATMEL_TC_CPCS, tce.base + ATMEL_TC_IER(tce.channel)); ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tce.base + ATMEL_TC_CCR(tce.channel)); ++ ++ return 0; ++} ++ ++static int tc_clkevt2_next_event(unsigned long delta, ++ struct clock_event_device *d) ++{ ++ writel(delta, tce.base + ATMEL_TC_RC(tce.channel)); ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tce.base + ATMEL_TC_CCR(tce.channel)); ++ ++ return 0; ++} ++ ++static irqreturn_t tc_clkevt2_irq(int irq, void *handle) ++{ ++ unsigned int sr; ++ ++ sr = readl(tce.base + ATMEL_TC_SR(tce.channel)); ++ if (sr & ATMEL_TC_CPCS) { ++ tce.clkevt.event_handler(&tce.clkevt); ++ return IRQ_HANDLED; ++ } ++ ++ return IRQ_NONE; ++} ++ ++static void tc_clkevt2_suspend(struct clock_event_device *d) ++{ ++ tce.cache.cmr = readl(tce.base + ATMEL_TC_CMR(tce.channel)); ++ tce.cache.imr = readl(tce.base + ATMEL_TC_IMR(tce.channel)); ++ tce.cache.rc = readl(tce.base + ATMEL_TC_RC(tce.channel)); ++ tce.cache.clken = !!(readl(tce.base + ATMEL_TC_SR(tce.channel)) & ++ ATMEL_TC_CLKSTA); ++} ++ ++static void tc_clkevt2_resume(struct clock_event_device *d) ++{ ++ /* Restore registers for the channel, RA and RB are not used */ ++ writel(tce.cache.cmr, tc.base + ATMEL_TC_CMR(tce.channel)); ++ writel(tce.cache.rc, tc.base + ATMEL_TC_RC(tce.channel)); ++ writel(0, tc.base + ATMEL_TC_RA(tce.channel)); ++ writel(0, tc.base + ATMEL_TC_RB(tce.channel)); ++ /* Disable all the interrupts */ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tce.channel)); ++ /* Reenable interrupts that were enabled before suspending */ ++ writel(tce.cache.imr, tc.base + ATMEL_TC_IER(tce.channel)); ++ ++ /* Start the clock if it was used */ ++ if (tce.cache.clken) ++ writel(ATMEL_TC_CCR_CLKEN | ATMEL_TC_CCR_SWTRG, ++ tc.base + ATMEL_TC_CCR(tce.channel)); ++} ++ ++static int __init tc_clkevt_register(struct device_node *node, ++ struct regmap *regmap, void __iomem *base, ++ int channel, int irq, int bits) ++{ ++ int ret; ++ ++ tce.regmap = regmap; ++ tce.base = base; ++ tce.channel = channel; ++ tce.irq = irq; ++ ++ tce.slow_clk = of_clk_get_by_name(node->parent, "slow_clk"); ++ if (IS_ERR(tce.slow_clk)) ++ return PTR_ERR(tce.slow_clk); ++ ++ ret = clk_prepare_enable(tce.slow_clk); ++ if (ret) ++ return ret; ++ ++ tce.clk = tcb_clk_get(node, tce.channel); ++ if (IS_ERR(tce.clk)) { ++ ret = PTR_ERR(tce.clk); ++ goto err_slow; ++ } ++ ++ snprintf(tce.name, sizeof(tce.name), "%s:%d", ++ kbasename(node->parent->full_name), channel); ++ tce.clkevt.cpumask = cpumask_of(0); ++ tce.clkevt.name = tce.name; ++ tce.clkevt.set_next_event = tc_clkevt2_next_event, ++ tce.clkevt.set_state_shutdown = tc_clkevt2_shutdown, ++ tce.clkevt.set_state_periodic = tc_clkevt2_set_periodic, ++ tce.clkevt.set_state_oneshot = tc_clkevt2_set_oneshot, ++ tce.clkevt.suspend = tc_clkevt2_suspend, ++ tce.clkevt.resume = tc_clkevt2_resume, ++ ++ /* try to enable clk to avoid future errors in mode change */ ++ ret = clk_prepare_enable(tce.clk); ++ if (ret) ++ goto err_slow; ++ clk_disable(tce.clk); ++ ++ clockevents_config_and_register(&tce.clkevt, 32768, 1, BIT(bits) - 1); ++ ++ ret = request_irq(tce.irq, tc_clkevt2_irq, IRQF_TIMER | IRQF_SHARED, ++ tce.clkevt.name, &tce); ++ if (ret) ++ goto err_clk; ++ ++ tce.registered = true; ++ ++ return 0; ++ ++err_clk: ++ clk_unprepare(tce.clk); ++err_slow: ++ clk_disable_unprepare(tce.slow_clk); ++ ++ return ret; ++} ++ ++/* ++ * Clocksource and clockevent using the same channel(s) ++ */ ++static u64 tc_get_cycles(struct clocksource *cs) ++{ ++ u32 lower, upper; ++ ++ do { ++ upper = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1])); ++ lower = readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ } while (upper != readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[1]))); ++ ++ return (upper << 16) | lower; ++} ++ ++static u64 tc_get_cycles32(struct clocksource *cs) ++{ ++ return readl_relaxed(tc.base + ATMEL_TC_CV(tc.channels[0])); ++} ++ ++static u64 notrace tc_sched_clock_read(void) ++{ ++ return tc_get_cycles(&tc.clksrc); ++} ++ ++static u64 notrace tc_sched_clock_read32(void) ++{ ++ return tc_get_cycles32(&tc.clksrc); ++} ++ ++static int tcb_clkevt_next_event(unsigned long delta, ++ struct clock_event_device *d) ++{ ++ u32 old, next, cur; ++ ++ ++ old = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ next = old + delta; ++ writel(next, tc.base + ATMEL_TC_RC(tc.channels[0])); ++ cur = readl(tc.base + ATMEL_TC_CV(tc.channels[0])); ++ ++ /* check whether the delta elapsed while setting the register */ ++ if ((next < old && cur < old && cur > next) || ++ (next > old && (cur < old || cur > next))) { ++ /* ++ * Clear the CPCS bit in the status register to avoid ++ * generating a spurious interrupt next time a valid ++ * timer event is configured. ++ */ ++ old = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); ++ return -ETIME; ++ } ++ ++ writel(ATMEL_TC_CPCS, tc.base + ATMEL_TC_IER(tc.channels[0])); ++ ++ return 0; ++} ++ ++static irqreturn_t tc_clkevt_irq(int irq, void *handle) ++{ ++ unsigned int sr; ++ ++ sr = readl(tc.base + ATMEL_TC_SR(tc.channels[0])); ++ if (sr & ATMEL_TC_CPCS) { ++ tc.clkevt.event_handler(&tc.clkevt); ++ return IRQ_HANDLED; ++ } ++ ++ return IRQ_NONE; ++} ++ ++static int tcb_clkevt_oneshot(struct clock_event_device *dev) ++{ ++ if (clockevent_state_oneshot(dev)) ++ return 0; ++ ++ /* ++ * Because both clockevent devices may share the same IRQ, we don't want ++ * the less likely one to stay requested ++ */ ++ return request_irq(tc.irq, tc_clkevt_irq, IRQF_TIMER | IRQF_SHARED, ++ tc.name, &tc); ++} ++ ++static int tcb_clkevt_shutdown(struct clock_event_device *dev) ++{ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[0])); ++ if (tc.bits == 16) ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[1])); ++ ++ if (!clockevent_state_detached(dev)) ++ free_irq(tc.irq, &tc); ++ ++ return 0; ++} ++ ++static void __init tcb_setup_dual_chan(struct atmel_tcb_clksrc *tc, ++ int mck_divisor_idx) ++{ ++ /* first channel: waveform mode, input mclk/8, clock TIOA on overflow */ ++ writel(mck_divisor_idx /* likely divide-by-8 */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP /* free-run */ ++ | ATMEL_TC_CMR_ACPA(SET) /* TIOA rises at 0 */ ++ | ATMEL_TC_CMR_ACPC(CLEAR), /* (duty cycle 50%) */ ++ tc->base + ATMEL_TC_CMR(tc->channels[0])); ++ writel(0x0000, tc->base + ATMEL_TC_RA(tc->channels[0])); ++ writel(0x8000, tc->base + ATMEL_TC_RC(tc->channels[0])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); ++ ++ /* second channel: waveform mode, input TIOA */ ++ writel(ATMEL_TC_CMR_XC(tc->channels[1]) /* input: TIOA */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ ++ tc->base + ATMEL_TC_CMR(tc->channels[1])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[1])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[1])); ++ ++ /* chain both channel, we assume the previous channel */ ++ regmap_write(tc->regmap, ATMEL_TC_BMR, ++ ATMEL_TC_BMR_TCXC(1 + tc->channels[1], tc->channels[1])); ++ /* then reset all the timers */ ++ regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static void __init tcb_setup_single_chan(struct atmel_tcb_clksrc *tc, ++ int mck_divisor_idx) ++{ ++ /* channel 0: waveform mode, input mclk/8 */ ++ writel(mck_divisor_idx /* likely divide-by-8 */ ++ | ATMEL_TC_CMR_WAVE ++ | ATMEL_TC_CMR_WAVESEL_UP, /* free-run */ ++ tc->base + ATMEL_TC_CMR(tc->channels[0])); ++ writel(0xff, tc->base + ATMEL_TC_IDR(tc->channels[0])); /* no irqs */ ++ writel(ATMEL_TC_CCR_CLKEN, tc->base + ATMEL_TC_CCR(tc->channels[0])); ++ ++ /* then reset all the timers */ ++ regmap_write(tc->regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static void tc_clksrc_suspend(struct clocksource *cs) ++{ ++ int i; ++ ++ for (i = 0; i < 1 + (tc.bits == 16); i++) { ++ tc.cache[i].cmr = readl(tc.base + ATMEL_TC_CMR(tc.channels[i])); ++ tc.cache[i].imr = readl(tc.base + ATMEL_TC_IMR(tc.channels[i])); ++ tc.cache[i].rc = readl(tc.base + ATMEL_TC_RC(tc.channels[i])); ++ tc.cache[i].clken = !!(readl(tc.base + ++ ATMEL_TC_SR(tc.channels[i])) & ++ ATMEL_TC_CLKSTA); ++ } ++ ++ if (tc.bits == 16) ++ regmap_read(tc.regmap, ATMEL_TC_BMR, &tc.bmr_cache); ++} ++ ++static void tc_clksrc_resume(struct clocksource *cs) ++{ ++ int i; ++ ++ for (i = 0; i < 1 + (tc.bits == 16); i++) { ++ /* Restore registers for the channel, RA and RB are not used */ ++ writel(tc.cache[i].cmr, tc.base + ATMEL_TC_CMR(tc.channels[i])); ++ writel(tc.cache[i].rc, tc.base + ATMEL_TC_RC(tc.channels[i])); ++ writel(0, tc.base + ATMEL_TC_RA(tc.channels[i])); ++ writel(0, tc.base + ATMEL_TC_RB(tc.channels[i])); ++ /* Disable all the interrupts */ ++ writel(0xff, tc.base + ATMEL_TC_IDR(tc.channels[i])); ++ /* Reenable interrupts that were enabled before suspending */ ++ writel(tc.cache[i].imr, tc.base + ATMEL_TC_IER(tc.channels[i])); ++ ++ /* Start the clock if it was used */ ++ if (tc.cache[i].clken) ++ writel(ATMEL_TC_CCR_CLKEN, tc.base + ++ ATMEL_TC_CCR(tc.channels[i])); ++ } ++ ++ /* in case of dual channel, chain channels */ ++ if (tc.bits == 16) ++ regmap_write(tc.regmap, ATMEL_TC_BMR, tc.bmr_cache); ++ /* Finally, trigger all the channels*/ ++ regmap_write(tc.regmap, ATMEL_TC_BCR, ATMEL_TC_BCR_SYNC); ++} ++ ++static int __init tcb_clksrc_register(struct device_node *node, ++ struct regmap *regmap, void __iomem *base, ++ int channel, int channel1, int irq, ++ int bits) ++{ ++ u32 rate, divided_rate = 0; ++ int best_divisor_idx = -1; ++ int i, err = -1; ++ u64 (*tc_sched_clock)(void); ++ ++ tc.regmap = regmap; ++ tc.base = base; ++ tc.channels[0] = channel; ++ tc.channels[1] = channel1; ++ tc.irq = irq; ++ tc.bits = bits; ++ ++ tc.clk[0] = tcb_clk_get(node, tc.channels[0]); ++ if (IS_ERR(tc.clk[0])) ++ return PTR_ERR(tc.clk[0]); ++ err = clk_prepare_enable(tc.clk[0]); ++ if (err) { ++ pr_debug("can't enable T0 clk\n"); ++ goto err_clk; ++ } ++ ++ /* How fast will we be counting? Pick something over 5 MHz. */ ++ rate = (u32)clk_get_rate(tc.clk[0]); ++ for (i = 0; i < 5; i++) { ++ unsigned int divisor = atmel_tc_divisors[i]; ++ unsigned int tmp; ++ ++ if (!divisor) ++ continue; ++ ++ tmp = rate / divisor; ++ pr_debug("TC: %u / %-3u [%d] --> %u\n", rate, divisor, i, tmp); ++ if (best_divisor_idx > 0) { ++ if (tmp < 5 * 1000 * 1000) ++ continue; ++ } ++ divided_rate = tmp; ++ best_divisor_idx = i; ++ } ++ ++ if (tc.bits == 32) { ++ tc.clksrc.read = tc_get_cycles32; ++ tcb_setup_single_chan(&tc, best_divisor_idx); ++ tc_sched_clock = tc_sched_clock_read32; ++ snprintf(tc.name, sizeof(tc.name), "%s:%d", ++ kbasename(node->parent->full_name), tc.channels[0]); ++ } else { ++ tc.clk[1] = tcb_clk_get(node, tc.channels[1]); ++ if (IS_ERR(tc.clk[1])) ++ goto err_disable_t0; ++ ++ err = clk_prepare_enable(tc.clk[1]); ++ if (err) { ++ pr_debug("can't enable T1 clk\n"); ++ goto err_clk1; ++ } ++ tc.clksrc.read = tc_get_cycles, ++ tcb_setup_dual_chan(&tc, best_divisor_idx); ++ tc_sched_clock = tc_sched_clock_read; ++ snprintf(tc.name, sizeof(tc.name), "%s:%d,%d", ++ kbasename(node->parent->full_name), tc.channels[0], ++ tc.channels[1]); ++ } ++ ++ pr_debug("%s at %d.%03d MHz\n", tc.name, ++ divided_rate / 1000000, ++ ((divided_rate + 500000) % 1000000) / 1000); ++ ++ tc.clksrc.name = tc.name; ++ tc.clksrc.suspend = tc_clksrc_suspend; ++ tc.clksrc.resume = tc_clksrc_resume; ++ ++ err = clocksource_register_hz(&tc.clksrc, divided_rate); ++ if (err) ++ goto err_disable_t1; ++ ++ sched_clock_register(tc_sched_clock, 32, divided_rate); ++ ++ tc.registered = true; ++ ++ /* Set up and register clockevents */ ++ tc.clkevt.name = tc.name; ++ tc.clkevt.cpumask = cpumask_of(0); ++ tc.clkevt.set_next_event = tcb_clkevt_next_event; ++ tc.clkevt.set_state_oneshot = tcb_clkevt_oneshot; ++ tc.clkevt.set_state_shutdown = tcb_clkevt_shutdown; ++ clockevents_config_and_register(&tc.clkevt, divided_rate, 1, ++ BIT(tc.bits) - 1); ++ ++ return 0; ++ ++err_disable_t1: ++ if (tc.bits == 16) ++ clk_disable_unprepare(tc.clk[1]); ++ ++err_clk1: ++ if (tc.bits == 16) ++ clk_put(tc.clk[1]); ++ ++err_disable_t0: ++ clk_disable_unprepare(tc.clk[0]); ++ ++err_clk: ++ clk_put(tc.clk[0]); ++ ++ pr_err("%s: unable to register clocksource/clockevent\n", ++ tc.clksrc.name); ++ ++ return err; ++} ++ ++static int __init tcb_clksrc_init(struct device_node *node) ++{ ++ const struct of_device_id *match; ++ const struct atmel_tcb_info *tcb_info; ++ struct regmap *regmap; ++ void __iomem *tcb_base; ++ u32 channel; ++ int bits, irq, err, chan1 = -1; ++ ++ if (tc.registered && tce.registered) ++ return -ENODEV; ++ ++ /* ++ * The regmap has to be used to access registers that are shared ++ * between channels on the same TCB but we keep direct IO access for ++ * the counters to avoid the impact on performance ++ */ ++ regmap = syscon_node_to_regmap(node->parent); ++ if (IS_ERR(regmap)) ++ return PTR_ERR(regmap); ++ ++ tcb_base = of_iomap(node->parent, 0); ++ if (!tcb_base) { ++ pr_err("%s +%d %s\n", __FILE__, __LINE__, __func__); ++ return -ENXIO; ++ } ++ ++ match = of_match_node(atmel_tcb_dt_ids, node->parent); ++ tcb_info = match->data; ++ bits = tcb_info->bits; ++ ++ err = of_property_read_u32_index(node, "reg", 0, &channel); ++ if (err) ++ return err; ++ ++ irq = tcb_irq_get(node, channel); ++ if (irq < 0) ++ return irq; ++ ++ if (tc.registered) ++ return tc_clkevt_register(node, regmap, tcb_base, channel, irq, ++ bits); ++ ++ if (bits == 16) { ++ of_property_read_u32_index(node, "reg", 1, &chan1); ++ if (chan1 == -1) { ++ if (tce.registered) { ++ pr_err("%s: clocksource needs two channels\n", ++ node->parent->full_name); ++ return -EINVAL; ++ } else { ++ return tc_clkevt_register(node, regmap, ++ tcb_base, channel, ++ irq, bits); ++ } ++ } ++ } ++ ++ return tcb_clksrc_register(node, regmap, tcb_base, channel, chan1, irq, ++ bits); ++} ++CLOCKSOURCE_OF_DECLARE(atmel_tcb_clksrc, "atmel,tcb-timer", ++ tcb_clksrc_init); diff --git a/debian/patches/features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch b/debian/patches/features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch new file mode 100644 index 000000000..af6de3baa --- /dev/null +++ b/debian/patches/features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch @@ -0,0 +1,37 @@ +From: Anna-Maria Gleixner +Date: Fri, 4 May 2018 17:45:32 +0200 +Subject: [PATCH 2/3] drivers/md/raid5: Use irqsave variant of + atomic_dec_and_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The irqsave variant of atomic_dec_and_lock handles irqsave/restore when +taking/releasing the spin lock. With this variant the call of +local_irq_save is no longer required. + +Signed-off-by: Anna-Maria Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/md/raid5.c | 5 ++--- + 1 file changed, 2 insertions(+), 3 deletions(-) + +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -409,16 +409,15 @@ void raid5_release_stripe(struct stripe_ + md_wakeup_thread(conf->mddev->thread); + return; + slow_path: +- local_irq_save(flags); + /* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */ +- if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) { ++ if (atomic_dec_and_lock_irqsave(&sh->count, &conf->device_lock, flags)) { + INIT_LIST_HEAD(&list); + hash = sh->hash_lock_index; + do_release_stripe(conf, sh, &list); + spin_unlock(&conf->device_lock); + release_inactive_stripe_list(conf, &list, hash); ++ local_irq_restore(flags); + } +- local_irq_restore(flags); + } + + static inline void remove_hash(struct stripe_head *sh) diff --git a/debian/patches/features/all/rt/0002-mm-list_lru-Move-locking-from-__list_lru_walk_one-to.patch b/debian/patches/features/all/rt/0002-mm-list_lru-Move-locking-from-__list_lru_walk_one-to.patch new file mode 100644 index 000000000..a88d5550a --- /dev/null +++ b/debian/patches/features/all/rt/0002-mm-list_lru-Move-locking-from-__list_lru_walk_one-to.patch @@ -0,0 +1,65 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 3 Jul 2018 13:06:07 +0200 +Subject: [PATCH 2/4] mm/list_lru: Move locking from __list_lru_walk_one() to + its caller +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Move the locking inside __list_lru_walk_one() to its caller. This is a +preparation step in order to introduce list_lru_walk_one_irq() which +does spin_lock_irq() instead of spin_lock() for the locking. + +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/list_lru.c | 18 +++++++++++++----- + 1 file changed, 13 insertions(+), 5 deletions(-) + +--- a/mm/list_lru.c ++++ b/mm/list_lru.c +@@ -204,7 +204,6 @@ static unsigned long + struct list_head *item, *n; + unsigned long isolated = 0; + +- spin_lock(&nlru->lock); + l = list_lru_from_memcg_idx(nlru, memcg_idx); + restart: + list_for_each_safe(item, n, &l->list) { +@@ -250,8 +249,6 @@ static unsigned long + BUG(); + } + } +- +- spin_unlock(&nlru->lock); + return isolated; + } + +@@ -260,8 +257,14 @@ list_lru_walk_one(struct list_lru *lru, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) + { +- return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), +- isolate, cb_arg, nr_to_walk); ++ struct list_lru_node *nlru = &lru->node[nid]; ++ unsigned long ret; ++ ++ spin_lock(&nlru->lock); ++ ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), ++ isolate, cb_arg, nr_to_walk); ++ spin_unlock(&nlru->lock); ++ return ret; + } + EXPORT_SYMBOL_GPL(list_lru_walk_one); + +@@ -276,8 +279,13 @@ unsigned long list_lru_walk_node(struct + nr_to_walk); + if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) { ++ struct list_lru_node *nlru = &lru->node[nid]; ++ ++ spin_lock(&nlru->lock); + isolated += __list_lru_walk_one(lru, nid, memcg_idx, + isolate, cb_arg, nr_to_walk); ++ spin_unlock(&nlru->lock); ++ + if (*nr_to_walk <= 0) + break; + } diff --git a/debian/patches/features/all/rt/0002-mm-workingset-make-shadow_lru_isolate-use-locking-su.patch b/debian/patches/features/all/rt/0002-mm-workingset-make-shadow_lru_isolate-use-locking-su.patch new file mode 100644 index 000000000..1cb6988f8 --- /dev/null +++ b/debian/patches/features/all/rt/0002-mm-workingset-make-shadow_lru_isolate-use-locking-su.patch @@ -0,0 +1,45 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 22 Jun 2018 11:43:35 +0200 +Subject: [PATCH 2/3] mm: workingset: make shadow_lru_isolate() use locking + suffix +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +shadow_lru_isolate() disables interrupts and acquires a lock. It could +use spin_lock_irq() instead. It also uses local_irq_enable() while it +could use spin_unlock_irq()/xa_unlock_irq(). + +Use proper suffix for lock/unlock in order to enable/disable interrupts +during release/acquire of a lock. + +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/workingset.c | 8 +++----- + 1 file changed, 3 insertions(+), 5 deletions(-) + +--- a/mm/workingset.c ++++ b/mm/workingset.c +@@ -431,7 +431,7 @@ static enum lru_status shadow_lru_isolat + + /* Coming from the list, invert the lock order */ + if (!xa_trylock(&mapping->i_pages)) { +- spin_unlock(lru_lock); ++ spin_unlock_irq(lru_lock); + ret = LRU_RETRY; + goto out; + } +@@ -469,13 +469,11 @@ static enum lru_status shadow_lru_isolat + workingset_lookup_update(mapping)); + + out_invalid: +- xa_unlock(&mapping->i_pages); ++ xa_unlock_irq(&mapping->i_pages); + ret = LRU_REMOVED_RETRY; + out: +- local_irq_enable(); + cond_resched(); +- local_irq_disable(); +- spin_lock(lru_lock); ++ spin_lock_irq(lru_lock); + return ret; + } + diff --git a/debian/patches/features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch b/debian/patches/features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch new file mode 100644 index 000000000..e0ba8f218 --- /dev/null +++ b/debian/patches/features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch @@ -0,0 +1,83 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 7 May 2018 17:09:42 +0200 +Subject: [PATCH] userns: use refcount_t for reference counting instead + atomic_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +refcount_t type and corresponding API should be used instead of atomic_t when +the variable is used as a reference counter. This allows to avoid accidental +refcounter overflows that might lead to use-after-free situations. + +Suggested-by: Peter Zijlstra +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/sched/user.h | 5 +++-- + kernel/user.c | 8 ++++---- + 2 files changed, 7 insertions(+), 6 deletions(-) + +--- a/include/linux/sched/user.h ++++ b/include/linux/sched/user.h +@@ -4,6 +4,7 @@ + + #include + #include ++#include + #include + + struct key; +@@ -12,7 +13,7 @@ struct key; + * Some day this will be a full-fledged user tracking system.. + */ + struct user_struct { +- atomic_t __count; /* reference count */ ++ refcount_t __count; /* reference count */ + atomic_t processes; /* How many processes does this user have? */ + atomic_t sigpending; /* How many pending signals does this user have? */ + #ifdef CONFIG_FANOTIFY +@@ -59,7 +60,7 @@ extern struct user_struct root_user; + extern struct user_struct * alloc_uid(kuid_t); + static inline struct user_struct *get_uid(struct user_struct *u) + { +- atomic_inc(&u->__count); ++ refcount_inc(&u->__count); + return u; + } + extern void free_uid(struct user_struct *); +--- a/kernel/user.c ++++ b/kernel/user.c +@@ -96,7 +96,7 @@ static DEFINE_SPINLOCK(uidhash_lock); + + /* root_user.__count is 1, for init task cred */ + struct user_struct root_user = { +- .__count = ATOMIC_INIT(1), ++ .__count = REFCOUNT_INIT(1), + .processes = ATOMIC_INIT(1), + .sigpending = ATOMIC_INIT(0), + .locked_shm = 0, +@@ -123,7 +123,7 @@ static struct user_struct *uid_hash_find + + hlist_for_each_entry(user, hashent, uidhash_node) { + if (uid_eq(user->uid, uid)) { +- atomic_inc(&user->__count); ++ refcount_inc(&user->__count); + return user; + } + } +@@ -170,7 +170,7 @@ void free_uid(struct user_struct *up) + return; + + local_irq_save(flags); +- if (atomic_dec_and_lock(&up->__count, &uidhash_lock)) ++ if (refcount_dec_and_lock(&up->__count, &uidhash_lock)) + free_user(up, flags); + else + local_irq_restore(flags); +@@ -191,7 +191,7 @@ struct user_struct *alloc_uid(kuid_t uid + goto out_unlock; + + new->uid = uid; +- atomic_set(&new->__count, 1); ++ refcount_set(&new->__count, 1); + ratelimit_state_init(&new->ratelimit, HZ, 100); + ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); + diff --git a/debian/patches/features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch b/debian/patches/features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch new file mode 100644 index 000000000..11c298515 --- /dev/null +++ b/debian/patches/features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch @@ -0,0 +1,30 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:40 +0200 +Subject: [PATCH 3/6] clocksource/drivers: atmel-pit: make option silent +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +To conform with the other option, make the ATMEL_PIT option silent so it +can be selected from the platform + +Tested-by: Alexander Dahl +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/clocksource/Kconfig | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/drivers/clocksource/Kconfig ++++ b/drivers/clocksource/Kconfig +@@ -392,8 +392,11 @@ config ARMV7M_SYSTICK + This options enables support for the ARMv7M system timer unit + + config ATMEL_PIT ++ bool "Microchip ARM Periodic Interval Timer (PIT)" if COMPILE_TEST + select TIMER_OF if OF +- def_bool SOC_AT91SAM9 || SOC_SAMA5 ++ help ++ This enables build of clocksource and clockevent driver for ++ the integrated PIT in Microchip ARM SoCs. + + config ATMEL_ST + bool "Atmel ST timer support" if COMPILE_TEST diff --git a/debian/patches/features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch b/debian/patches/features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch new file mode 100644 index 000000000..ce33e0d34 --- /dev/null +++ b/debian/patches/features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch @@ -0,0 +1,31 @@ +From: Anna-Maria Gleixner +Date: Fri, 4 May 2018 17:45:33 +0200 +Subject: [PATCH 3/3] drivers/md/raid5: Do not disable irq on + release_inactive_stripe_list() call +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There is no need to invoke release_inactive_stripe_list() with interrupts +disabled. All call sites, except raid5_release_stripe(), unlock +->device_lock and enable interrupts before invoking the function. + +Make it consistent. + +Signed-off-by: Anna-Maria Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/md/raid5.c | 3 +-- + 1 file changed, 1 insertion(+), 2 deletions(-) + +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -414,9 +414,8 @@ void raid5_release_stripe(struct stripe_ + INIT_LIST_HEAD(&list); + hash = sh->hash_lock_index; + do_release_stripe(conf, sh, &list); +- spin_unlock(&conf->device_lock); ++ spin_unlock_irqrestore(&conf->device_lock, flags); + release_inactive_stripe_list(conf, &list, hash); +- local_irq_restore(flags); + } + } + diff --git a/debian/patches/features/all/rt/0003-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch b/debian/patches/features/all/rt/0003-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch new file mode 100644 index 000000000..44530354b --- /dev/null +++ b/debian/patches/features/all/rt/0003-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch @@ -0,0 +1,609 @@ +From: Thomas Gleixner +Date: Mon, 28 May 2018 15:24:22 +0200 +Subject: [PATCH 3/4] mm/SLxB: change list_lock to raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The list_lock is used with used with IRQs off on RT. Make it a raw_spinlock_t +otherwise the interrupts won't be disabled on -RT. The locking rules remain +the same on !RT. +This patch changes it for SLAB and SLUB since both share the same header +file for struct kmem_cache_node defintion. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/slab.c | 94 +++++++++++++++++++++++++++++++------------------------------- + mm/slab.h | 2 - + mm/slub.c | 50 ++++++++++++++++---------------- + 3 files changed, 73 insertions(+), 73 deletions(-) + +--- a/mm/slab.c ++++ b/mm/slab.c +@@ -233,7 +233,7 @@ static void kmem_cache_node_init(struct + parent->shared = NULL; + parent->alien = NULL; + parent->colour_next = 0; +- spin_lock_init(&parent->list_lock); ++ raw_spin_lock_init(&parent->list_lock); + parent->free_objects = 0; + parent->free_touched = 0; + } +@@ -600,9 +600,9 @@ static noinline void cache_free_pfmemall + page_node = page_to_nid(page); + n = get_node(cachep, page_node); + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -728,7 +728,7 @@ static void __drain_alien_cache(struct k + struct kmem_cache_node *n = get_node(cachep, node); + + if (ac->avail) { +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + /* + * Stuff objects into the remote nodes shared array first. + * That way we could avoid the overhead of putting the objects +@@ -739,7 +739,7 @@ static void __drain_alien_cache(struct k + + free_block(cachep, ac->entry, ac->avail, node, list); + ac->avail = 0; +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + } + } + +@@ -812,9 +812,9 @@ static int __cache_free_alien(struct kme + slabs_destroy(cachep, &list); + } else { + n = get_node(cachep, page_node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, &objp, 1, page_node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + } + return 1; +@@ -855,10 +855,10 @@ static int init_cache_node(struct kmem_c + */ + n = get_node(cachep, node); + if (n) { +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + n->free_limit = (1 + nr_cpus_node(node)) * cachep->batchcount + + cachep->num; +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + return 0; + } +@@ -937,7 +937,7 @@ static int setup_kmem_cache_node(struct + goto fail; + + n = get_node(cachep, node); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + if (n->shared && force_change) { + free_block(cachep, n->shared->entry, + n->shared->avail, node, &list); +@@ -955,7 +955,7 @@ static int setup_kmem_cache_node(struct + new_alien = NULL; + } + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + + /* +@@ -994,7 +994,7 @@ static void cpuup_canceled(long cpu) + if (!n) + continue; + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + /* Free limit for this kmem_cache_node */ + n->free_limit -= cachep->batchcount; +@@ -1007,7 +1007,7 @@ static void cpuup_canceled(long cpu) + } + + if (!cpumask_empty(mask)) { +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + goto free_slab; + } + +@@ -1021,7 +1021,7 @@ static void cpuup_canceled(long cpu) + alien = n->alien; + n->alien = NULL; + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + kfree(shared); + if (alien) { +@@ -1205,7 +1205,7 @@ static void __init init_list(struct kmem + /* + * Do not assume that spinlocks can be initialized via memcpy: + */ +- spin_lock_init(&ptr->list_lock); ++ raw_spin_lock_init(&ptr->list_lock); + + MAKE_ALL_LISTS(cachep, ptr, nodeid); + cachep->node[nodeid] = ptr; +@@ -1376,11 +1376,11 @@ slab_out_of_memory(struct kmem_cache *ca + for_each_kmem_cache_node(cachep, node, n) { + unsigned long total_slabs, free_slabs, free_objs; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + total_slabs = n->total_slabs; + free_slabs = n->free_slabs; + free_objs = n->free_objects; +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + pr_warn(" node %d: slabs: %ld/%ld, objs: %ld/%ld\n", + node, total_slabs - free_slabs, total_slabs, +@@ -2173,7 +2173,7 @@ static void check_spinlock_acquired(stru + { + #ifdef CONFIG_SMP + check_irq_off(); +- assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); ++ assert_raw_spin_locked(&get_node(cachep, numa_mem_id())->list_lock); + #endif + } + +@@ -2181,7 +2181,7 @@ static void check_spinlock_acquired_node + { + #ifdef CONFIG_SMP + check_irq_off(); +- assert_spin_locked(&get_node(cachep, node)->list_lock); ++ assert_raw_spin_locked(&get_node(cachep, node)->list_lock); + #endif + } + +@@ -2221,9 +2221,9 @@ static void do_drain(void *arg) + check_irq_off(); + ac = cpu_cache_get(cachep); + n = get_node(cachep, node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + ac->avail = 0; + } +@@ -2241,9 +2241,9 @@ static void drain_cpu_caches(struct kmem + drain_alien_cache(cachep, n->alien); + + for_each_kmem_cache_node(cachep, node, n) { +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, n->shared, node, true, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -2265,10 +2265,10 @@ static int drain_freelist(struct kmem_ca + nr_freed = 0; + while (nr_freed < tofree && !list_empty(&n->slabs_free)) { + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + p = n->slabs_free.prev; + if (p == &n->slabs_free) { +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + goto out; + } + +@@ -2281,7 +2281,7 @@ static int drain_freelist(struct kmem_ca + * to the cache. + */ + n->free_objects -= cache->num; +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slab_destroy(cache, page); + nr_freed++; + } +@@ -2729,7 +2729,7 @@ static void cache_grow_end(struct kmem_c + INIT_LIST_HEAD(&page->lru); + n = get_node(cachep, page_to_nid(page)); + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + n->total_slabs++; + if (!page->active) { + list_add_tail(&page->lru, &(n->slabs_free)); +@@ -2739,7 +2739,7 @@ static void cache_grow_end(struct kmem_c + + STATS_INC_GROWN(cachep); + n->free_objects += cachep->num - page->active; +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + fixup_objfreelist_debug(cachep, &list); + } +@@ -2907,7 +2907,7 @@ static struct page *get_first_slab(struc + { + struct page *page; + +- assert_spin_locked(&n->list_lock); ++ assert_raw_spin_locked(&n->list_lock); + page = list_first_entry_or_null(&n->slabs_partial, struct page, lru); + if (!page) { + n->free_touched = 1; +@@ -2933,10 +2933,10 @@ static noinline void *cache_alloc_pfmema + if (!gfp_pfmemalloc_allowed(flags)) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + page = get_first_slab(n, true); + if (!page) { +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return NULL; + } + +@@ -2945,7 +2945,7 @@ static noinline void *cache_alloc_pfmema + + fixup_slab_list(cachep, n, page, &list); + +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + + return obj; +@@ -3004,7 +3004,7 @@ static void *cache_alloc_refill(struct k + if (!n->free_objects && (!shared || !shared->avail)) + goto direct_grow; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + shared = READ_ONCE(n->shared); + + /* See if we can refill from the shared array */ +@@ -3028,7 +3028,7 @@ static void *cache_alloc_refill(struct k + must_grow: + n->free_objects -= ac->avail; + alloc_done: +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + + direct_grow: +@@ -3253,7 +3253,7 @@ static void *____cache_alloc_node(struct + BUG_ON(!n); + + check_irq_off(); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + page = get_first_slab(n, false); + if (!page) + goto must_grow; +@@ -3271,12 +3271,12 @@ static void *____cache_alloc_node(struct + + fixup_slab_list(cachep, n, page, &list); + +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + fixup_objfreelist_debug(cachep, &list); + return obj; + + must_grow: +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + page = cache_grow_begin(cachep, gfp_exact_node(flags), nodeid); + if (page) { + /* This slab isn't counted yet so don't update free_objects */ +@@ -3452,7 +3452,7 @@ static void cache_flusharray(struct kmem + + check_irq_off(); + n = get_node(cachep, node); +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + if (n->shared) { + struct array_cache *shared_array = n->shared; + int max = shared_array->limit - shared_array->avail; +@@ -3481,7 +3481,7 @@ static void cache_flusharray(struct kmem + STATS_SET_FREEABLE(cachep, i); + } + #endif +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + slabs_destroy(cachep, &list); + ac->avail -= batchcount; + memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail); +@@ -3887,9 +3887,9 @@ static int __do_tune_cpucache(struct kme + + node = cpu_to_mem(cpu); + n = get_node(cachep, node); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + free_block(cachep, ac->entry, ac->avail, node, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + slabs_destroy(cachep, &list); + } + free_percpu(prev); +@@ -4014,9 +4014,9 @@ static void drain_array(struct kmem_cach + return; + } + +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + drain_array_locked(cachep, ac, node, false, &list); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + slabs_destroy(cachep, &list); + } +@@ -4100,7 +4100,7 @@ void get_slabinfo(struct kmem_cache *cac + + for_each_kmem_cache_node(cachep, node, n) { + check_irq_on(); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + total_slabs += n->total_slabs; + free_slabs += n->free_slabs; +@@ -4109,7 +4109,7 @@ void get_slabinfo(struct kmem_cache *cac + if (n->shared) + shared_avail += n->shared->avail; + +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + } + num_objs = total_slabs * cachep->num; + active_slabs = total_slabs - free_slabs; +@@ -4324,13 +4324,13 @@ static int leaks_show(struct seq_file *m + for_each_kmem_cache_node(cachep, node, n) { + + check_irq_on(); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + + list_for_each_entry(page, &n->slabs_full, lru) + handle_slab(x, cachep, page); + list_for_each_entry(page, &n->slabs_partial, lru) + handle_slab(x, cachep, page); +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + } + } while (!is_store_user_clean(cachep)); + +--- a/mm/slab.h ++++ b/mm/slab.h +@@ -453,7 +453,7 @@ static inline void slab_post_alloc_hook( + * The slab lists for all objects. + */ + struct kmem_cache_node { +- spinlock_t list_lock; ++ raw_spinlock_t list_lock; + + #ifdef CONFIG_SLAB + struct list_head slabs_partial; /* partial list first, better asm code */ +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1169,7 +1169,7 @@ static noinline int free_debug_processin + unsigned long uninitialized_var(flags); + int ret = 0; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + slab_lock(page); + + if (s->flags & SLAB_CONSISTENCY_CHECKS) { +@@ -1204,7 +1204,7 @@ static noinline int free_debug_processin + bulk_cnt, cnt); + + slab_unlock(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + if (!ret) + slab_fix(s, "Object at 0x%p not freed", object); + return ret; +@@ -1804,7 +1804,7 @@ static void *get_partial_node(struct kme + if (!n || !n->nr_partial) + return NULL; + +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + list_for_each_entry_safe(page, page2, &n->partial, lru) { + void *t; + +@@ -1829,7 +1829,7 @@ static void *get_partial_node(struct kme + break; + + } +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + return object; + } + +@@ -2075,7 +2075,7 @@ static void deactivate_slab(struct kmem_ + * that acquire_slab() will see a slab page that + * is frozen + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } else { + m = M_FULL; +@@ -2086,7 +2086,7 @@ static void deactivate_slab(struct kmem_ + * slabs from diagnostic functions will not see + * any frozen slabs. + */ +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + } + +@@ -2121,7 +2121,7 @@ static void deactivate_slab(struct kmem_ + goto redo; + + if (lock) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + if (m == M_FREE) { + stat(s, DEACTIVATE_EMPTY); +@@ -2156,10 +2156,10 @@ static void unfreeze_partials(struct kme + n2 = get_node(s, page_to_nid(page)); + if (n != n2) { + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + n = n2; +- spin_lock(&n->list_lock); ++ raw_spin_lock(&n->list_lock); + } + + do { +@@ -2188,7 +2188,7 @@ static void unfreeze_partials(struct kme + } + + if (n) +- spin_unlock(&n->list_lock); ++ raw_spin_unlock(&n->list_lock); + + while (discard_page) { + page = discard_page; +@@ -2357,10 +2357,10 @@ static unsigned long count_partial(struc + unsigned long x = 0; + struct page *page; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + x += get_count(page); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return x; + } + #endif /* CONFIG_SLUB_DEBUG || CONFIG_SYSFS */ +@@ -2795,7 +2795,7 @@ static void __slab_free(struct kmem_cach + + do { + if (unlikely(n)) { +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + n = NULL; + } + prior = page->freelist; +@@ -2827,7 +2827,7 @@ static void __slab_free(struct kmem_cach + * Otherwise the list_lock will synchronize with + * other processors updating the list of slabs. + */ +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + } + } +@@ -2869,7 +2869,7 @@ static void __slab_free(struct kmem_cach + add_partial(n, page, DEACTIVATE_TO_TAIL); + stat(s, FREE_ADD_PARTIAL); + } +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return; + + slab_empty: +@@ -2884,7 +2884,7 @@ static void __slab_free(struct kmem_cach + remove_full(s, n, page); + } + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + stat(s, FREE_SLAB); + discard_slab(s, page); + } +@@ -3271,7 +3271,7 @@ static void + init_kmem_cache_node(struct kmem_cache_node *n) + { + n->nr_partial = 0; +- spin_lock_init(&n->list_lock); ++ raw_spin_lock_init(&n->list_lock); + INIT_LIST_HEAD(&n->partial); + #ifdef CONFIG_SLUB_DEBUG + atomic_long_set(&n->nr_slabs, 0); +@@ -3655,7 +3655,7 @@ static void free_partial(struct kmem_cac + struct page *page, *h; + + BUG_ON(irqs_disabled()); +- spin_lock_irq(&n->list_lock); ++ raw_spin_lock_irq(&n->list_lock); + list_for_each_entry_safe(page, h, &n->partial, lru) { + if (!page->inuse) { + remove_partial(n, page); +@@ -3665,7 +3665,7 @@ static void free_partial(struct kmem_cac + "Objects remaining in %s on __kmem_cache_shutdown()"); + } + } +- spin_unlock_irq(&n->list_lock); ++ raw_spin_unlock_irq(&n->list_lock); + + list_for_each_entry_safe(page, h, &discard, lru) + discard_slab(s, page); +@@ -3938,7 +3938,7 @@ int __kmem_cache_shrink(struct kmem_cach + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + /* + * Build lists of slabs to discard or promote. +@@ -3969,7 +3969,7 @@ int __kmem_cache_shrink(struct kmem_cach + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); + +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + + /* Release empty slabs */ + list_for_each_entry_safe(page, t, &discard, lru) +@@ -4383,7 +4383,7 @@ static int validate_slab_node(struct kme + struct page *page; + unsigned long flags; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + + list_for_each_entry(page, &n->partial, lru) { + validate_slab_slab(s, page, map); +@@ -4405,7 +4405,7 @@ static int validate_slab_node(struct kme + s->name, count, atomic_long_read(&n->nr_slabs)); + + out: +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + return count; + } + +@@ -4595,12 +4595,12 @@ static int list_locations(struct kmem_ca + if (!atomic_long_read(&n->nr_slabs)) + continue; + +- spin_lock_irqsave(&n->list_lock, flags); ++ raw_spin_lock_irqsave(&n->list_lock, flags); + list_for_each_entry(page, &n->partial, lru) + process_slab(&t, s, page, alloc, map); + list_for_each_entry(page, &n->full, lru) + process_slab(&t, s, page, alloc, map); +- spin_unlock_irqrestore(&n->list_lock, flags); ++ raw_spin_unlock_irqrestore(&n->list_lock, flags); + } + + for (i = 0; i < t.count; i++) { diff --git a/debian/patches/features/all/rt/0003-mm-list_lru-Pass-struct-list_lru_node-as-an-argument.patch b/debian/patches/features/all/rt/0003-mm-list_lru-Pass-struct-list_lru_node-as-an-argument.patch new file mode 100644 index 000000000..031d4b5c7 --- /dev/null +++ b/debian/patches/features/all/rt/0003-mm-list_lru-Pass-struct-list_lru_node-as-an-argument.patch @@ -0,0 +1,56 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 3 Jul 2018 13:08:56 +0200 +Subject: [PATCH 3/4] mm/list_lru: Pass struct list_lru_node as an argument + __list_lru_walk_one() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +__list_lru_walk_one() is invoked with struct list_lru *lru, int nid as +the first two argument. Those two are only used to retrieve struct +list_lru_node. Since this is already done by the caller of the function +for the locking, we can pass struct list_lru_node directly and avoid the +dance around it. + +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/list_lru.c | 12 ++++++------ + 1 file changed, 6 insertions(+), 6 deletions(-) + +--- a/mm/list_lru.c ++++ b/mm/list_lru.c +@@ -194,12 +194,11 @@ unsigned long list_lru_count_node(struct + EXPORT_SYMBOL_GPL(list_lru_count_node); + + static unsigned long +-__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, ++__list_lru_walk_one(struct list_lru_node *nlru, int memcg_idx, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) + { + +- struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; + struct list_head *item, *n; + unsigned long isolated = 0; +@@ -261,8 +260,8 @@ list_lru_walk_one(struct list_lru *lru, + unsigned long ret; + + spin_lock(&nlru->lock); +- ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), +- isolate, cb_arg, nr_to_walk); ++ ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, ++ nr_to_walk); + spin_unlock(&nlru->lock); + return ret; + } +@@ -282,8 +281,9 @@ unsigned long list_lru_walk_node(struct + struct list_lru_node *nlru = &lru->node[nid]; + + spin_lock(&nlru->lock); +- isolated += __list_lru_walk_one(lru, nid, memcg_idx, +- isolate, cb_arg, nr_to_walk); ++ isolated += __list_lru_walk_one(nlru, memcg_idx, ++ isolate, cb_arg, ++ nr_to_walk); + spin_unlock(&nlru->lock); + + if (*nr_to_walk <= 0) diff --git a/debian/patches/features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch b/debian/patches/features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch new file mode 100644 index 000000000..257d5d0d9 --- /dev/null +++ b/debian/patches/features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch @@ -0,0 +1,49 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:41 +0200 +Subject: [PATCH 4/6] ARM: at91: Implement clocksource selection +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Allow selecting and unselecting the PIT clocksource driver so it doesn't +have to be compile when unused. + +Tested-by: Alexander Dahl +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mach-at91/Kconfig | 25 +++++++++++++++++++++++++ + 1 file changed, 25 insertions(+) + +--- a/arch/arm/mach-at91/Kconfig ++++ b/arch/arm/mach-at91/Kconfig +@@ -106,6 +106,31 @@ config SOC_AT91SAM9 + AT91SAM9X35 + AT91SAM9XE + ++comment "Clocksource driver selection" ++ ++config ATMEL_CLOCKSOURCE_PIT ++ bool "Periodic Interval Timer (PIT) support" ++ depends on SOC_AT91SAM9 || SOC_SAMA5 ++ default SOC_AT91SAM9 || SOC_SAMA5 ++ select ATMEL_PIT ++ help ++ Select this to get a clocksource based on the Atmel Periodic Interval ++ Timer. It has a relatively low resolution and the TC Block clocksource ++ should be preferred. ++ ++config ATMEL_CLOCKSOURCE_TCB ++ bool "Timer Counter Blocks (TCB) support" ++ depends on SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 || COMPILE_TEST ++ default SOC_AT91RM9200 || SOC_AT91SAM9 || SOC_SAMA5 ++ depends on !ATMEL_TCLIB ++ select ATMEL_ARM_TCB_CLKSRC ++ help ++ Select this to get a high precision clocksource based on a ++ TC block with a 5+ MHz base clock rate. ++ On platforms with 16-bit counters, two timer channels are combined ++ to make a single 32-bit timer. ++ It can also be used as a clock event device supporting oneshot mode. ++ + config HAVE_AT91_UTMI + bool + diff --git a/debian/patches/features/all/rt/0004-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch b/debian/patches/features/all/rt/0004-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch new file mode 100644 index 000000000..d364ae8ec --- /dev/null +++ b/debian/patches/features/all/rt/0004-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch @@ -0,0 +1,217 @@ +From: Thomas Gleixner +Date: Thu, 21 Jun 2018 17:29:19 +0200 +Subject: [PATCH 4/4] mm/SLUB: delay giving back empty slubs to IRQ enabled + regions +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +__free_slab() is invoked with disabled interrupts which increases the +irq-off time while __free_pages() is doing the work. +Allow __free_slab() to be invoked with enabled interrupts and move +everything from interrupts-off invocations to a temporary per-CPU list +so it can be processed later. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/slub.c | 74 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++----- + 1 file changed, 69 insertions(+), 5 deletions(-) + +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1332,6 +1332,12 @@ static inline void dec_slabs_node(struct + + #endif /* CONFIG_SLUB_DEBUG */ + ++struct slub_free_list { ++ raw_spinlock_t lock; ++ struct list_head list; ++}; ++static DEFINE_PER_CPU(struct slub_free_list, slub_free_list); ++ + /* + * Hooks for other subsystems that check memory allocations. In a typical + * production configuration these hooks all should produce no code at all. +@@ -1686,6 +1692,16 @@ static void __free_slab(struct kmem_cach + __free_pages(page, order); + } + ++static void free_delayed(struct list_head *h) ++{ ++ while (!list_empty(h)) { ++ struct page *page = list_first_entry(h, struct page, lru); ++ ++ list_del(&page->lru); ++ __free_slab(page->slab_cache, page); ++ } ++} ++ + static void rcu_free_slab(struct rcu_head *h) + { + struct page *page = container_of(h, struct page, rcu_head); +@@ -1697,6 +1713,12 @@ static void free_slab(struct kmem_cache + { + if (unlikely(s->flags & SLAB_TYPESAFE_BY_RCU)) { + call_rcu(&page->rcu_head, rcu_free_slab); ++ } else if (irqs_disabled()) { ++ struct slub_free_list *f = this_cpu_ptr(&slub_free_list); ++ ++ raw_spin_lock(&f->lock); ++ list_add(&page->lru, &f->list); ++ raw_spin_unlock(&f->lock); + } else + __free_slab(s, page); + } +@@ -2225,14 +2247,21 @@ static void put_cpu_partial(struct kmem_ + pobjects = oldpage->pobjects; + pages = oldpage->pages; + if (drain && pobjects > s->cpu_partial) { ++ struct slub_free_list *f; + unsigned long flags; ++ LIST_HEAD(tofree); + /* + * partial array is full. Move the existing + * set to the per node partial list. + */ + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock(&f->lock); + local_irq_restore(flags); ++ free_delayed(&tofree); + oldpage = NULL; + pobjects = 0; + pages = 0; +@@ -2302,7 +2331,22 @@ static bool has_cpu_slab(int cpu, void * + + static void flush_all(struct kmem_cache *s) + { ++ LIST_HEAD(tofree); ++ int cpu; ++ + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); ++ for_each_online_cpu(cpu) { ++ struct slub_free_list *f; ++ ++ if (!has_cpu_slab(cpu, s)) ++ continue; ++ ++ f = &per_cpu(slub_free_list, cpu); ++ raw_spin_lock_irq(&f->lock); ++ list_splice_init(&f->list, &tofree); ++ raw_spin_unlock_irq(&f->lock); ++ free_delayed(&tofree); ++ } + } + + /* +@@ -2500,8 +2544,10 @@ static inline void *get_freelist(struct + * already disabled (which is the case for bulk allocation). + */ + static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +- unsigned long addr, struct kmem_cache_cpu *c) ++ unsigned long addr, struct kmem_cache_cpu *c, ++ struct list_head *to_free) + { ++ struct slub_free_list *f; + void *freelist; + struct page *page; + +@@ -2557,6 +2603,13 @@ static void *___slab_alloc(struct kmem_c + VM_BUG_ON(!c->page->frozen); + c->freelist = get_freepointer(s, freelist); + c->tid = next_tid(c->tid); ++ ++out: ++ f = this_cpu_ptr(&slub_free_list); ++ raw_spin_lock(&f->lock); ++ list_splice_init(&f->list, to_free); ++ raw_spin_unlock(&f->lock); ++ + return freelist; + + new_slab: +@@ -2572,7 +2625,7 @@ static void *___slab_alloc(struct kmem_c + + if (unlikely(!freelist)) { + slab_out_of_memory(s, gfpflags, node); +- return NULL; ++ goto out; + } + + page = c->page; +@@ -2585,7 +2638,7 @@ static void *___slab_alloc(struct kmem_c + goto new_slab; /* Slab failed checks. Next slab needed */ + + deactivate_slab(s, page, get_freepointer(s, freelist), c); +- return freelist; ++ goto out; + } + + /* +@@ -2597,6 +2650,7 @@ static void *__slab_alloc(struct kmem_ca + { + void *p; + unsigned long flags; ++ LIST_HEAD(tofree); + + local_irq_save(flags); + #ifdef CONFIG_PREEMPT +@@ -2608,8 +2662,9 @@ static void *__slab_alloc(struct kmem_ca + c = this_cpu_ptr(s->cpu_slab); + #endif + +- p = ___slab_alloc(s, gfpflags, node, addr, c); ++ p = ___slab_alloc(s, gfpflags, node, addr, c, &tofree); + local_irq_restore(flags); ++ free_delayed(&tofree); + return p; + } + +@@ -3087,6 +3142,7 @@ int kmem_cache_alloc_bulk(struct kmem_ca + void **p) + { + struct kmem_cache_cpu *c; ++ LIST_HEAD(to_free); + int i; + + /* memcg and kmem_cache debug support */ +@@ -3110,7 +3166,7 @@ int kmem_cache_alloc_bulk(struct kmem_ca + * of re-populating per CPU c->freelist + */ + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, +- _RET_IP_, c); ++ _RET_IP_, c, &to_free); + if (unlikely(!p[i])) + goto error; + +@@ -3122,6 +3178,7 @@ int kmem_cache_alloc_bulk(struct kmem_ca + } + c->tid = next_tid(c->tid); + local_irq_enable(); ++ free_delayed(&to_free); + + /* Clear memory outside IRQ disabled fastpath loop */ + if (unlikely(flags & __GFP_ZERO)) { +@@ -3136,6 +3193,7 @@ int kmem_cache_alloc_bulk(struct kmem_ca + return i; + error: + local_irq_enable(); ++ free_delayed(&to_free); + slab_post_alloc_hook(s, flags, i, p); + __kmem_cache_free_bulk(s, i, p); + return 0; +@@ -4182,6 +4240,12 @@ void __init kmem_cache_init(void) + { + static __initdata struct kmem_cache boot_kmem_cache, + boot_kmem_cache_node; ++ int cpu; ++ ++ for_each_possible_cpu(cpu) { ++ raw_spin_lock_init(&per_cpu(slub_free_list, cpu).lock); ++ INIT_LIST_HEAD(&per_cpu(slub_free_list, cpu).list); ++ } + + if (debug_guardpage_minorder()) + slub_max_order = 0; diff --git a/debian/patches/features/all/rt/0004-mm-list_lru-Introduce-list_lru_shrink_walk_irq.patch b/debian/patches/features/all/rt/0004-mm-list_lru-Introduce-list_lru_shrink_walk_irq.patch new file mode 100644 index 000000000..36770659d --- /dev/null +++ b/debian/patches/features/all/rt/0004-mm-list_lru-Introduce-list_lru_shrink_walk_irq.patch @@ -0,0 +1,107 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 3 Jul 2018 13:17:27 +0200 +Subject: [PATCH 4/4] mm/list_lru: Introduce list_lru_shrink_walk_irq() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Provide list_lru_shrink_walk_irq() and let it behave like +list_lru_walk_one() except that it locks the spinlock with +spin_lock_irq(). This is used by scan_shadow_nodes() because its lock +nests within the i_pages lock which is acquired with IRQ. +This change allows to use proper locking promitives instead hand crafted +lock_irq_disable() plus spin_lock(). +There is no EXPORT_SYMBOL provided because the current user is in-KERNEL +only. + +Add list_lru_shrink_walk_irq() which acquires the spinlock with the +proper locking primitives. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/list_lru.h | 25 +++++++++++++++++++++++++ + mm/list_lru.c | 15 +++++++++++++++ + mm/workingset.c | 8 ++------ + 3 files changed, 42 insertions(+), 6 deletions(-) + +--- a/include/linux/list_lru.h ++++ b/include/linux/list_lru.h +@@ -162,6 +162,23 @@ unsigned long list_lru_walk_one(struct l + int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); ++/** ++ * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items. ++ * @lru: the lru pointer. ++ * @nid: the node id to scan from. ++ * @memcg: the cgroup to scan from. ++ * @isolate: callback function that is resposible for deciding what to do with ++ * the item currently being scanned ++ * @cb_arg: opaque type that will be passed to @isolate ++ * @nr_to_walk: how many items to scan. ++ * ++ * Same as @list_lru_walk_one except that the spinlock is acquired with ++ * spin_lock_irq(). ++ */ ++unsigned long list_lru_walk_one_irq(struct list_lru *lru, ++ int nid, struct mem_cgroup *memcg, ++ list_lru_walk_cb isolate, void *cb_arg, ++ unsigned long *nr_to_walk); + unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk); +@@ -175,6 +192,14 @@ list_lru_shrink_walk(struct list_lru *lr + } + + static inline unsigned long ++list_lru_shrink_walk_irq(struct list_lru *lru, struct shrink_control *sc, ++ list_lru_walk_cb isolate, void *cb_arg) ++{ ++ return list_lru_walk_one_irq(lru, sc->nid, sc->memcg, isolate, cb_arg, ++ &sc->nr_to_scan); ++} ++ ++static inline unsigned long + list_lru_walk(struct list_lru *lru, list_lru_walk_cb isolate, + void *cb_arg, unsigned long nr_to_walk) + { +--- a/mm/list_lru.c ++++ b/mm/list_lru.c +@@ -267,6 +267,21 @@ list_lru_walk_one(struct list_lru *lru, + } + EXPORT_SYMBOL_GPL(list_lru_walk_one); + ++unsigned long ++list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, ++ list_lru_walk_cb isolate, void *cb_arg, ++ unsigned long *nr_to_walk) ++{ ++ struct list_lru_node *nlru = &lru->node[nid]; ++ unsigned long ret; ++ ++ spin_lock_irq(&nlru->lock); ++ ret = __list_lru_walk_one(nlru, memcg_cache_id(memcg), isolate, cb_arg, ++ nr_to_walk); ++ spin_unlock_irq(&nlru->lock); ++ return ret; ++} ++ + unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +--- a/mm/workingset.c ++++ b/mm/workingset.c +@@ -480,13 +480,9 @@ static enum lru_status shadow_lru_isolat + static unsigned long scan_shadow_nodes(struct shrinker *shrinker, + struct shrink_control *sc) + { +- unsigned long ret; +- + /* list_lru lock nests inside the IRQ-safe i_pages lock */ +- local_irq_disable(); +- ret = list_lru_shrink_walk(&shadow_nodes, sc, shadow_lru_isolate, NULL); +- local_irq_enable(); +- return ret; ++ return list_lru_shrink_walk_irq(&shadow_nodes, sc, shadow_lru_isolate, ++ NULL); + } + + static struct shrinker workingset_shadow_shrinker = { diff --git a/debian/patches/features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch b/debian/patches/features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch new file mode 100644 index 000000000..7767228c1 --- /dev/null +++ b/debian/patches/features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch @@ -0,0 +1,35 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:42 +0200 +Subject: [PATCH 5/6] ARM: configs: at91: use new TCB timer driver +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Unselecting ATMEL_TCLIB switches the TCB timer driver from tcb_clksrc to +timer-atmel-tcb. + +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/configs/at91_dt_defconfig | 1 - + arch/arm/configs/sama5_defconfig | 1 - + 2 files changed, 2 deletions(-) + +--- a/arch/arm/configs/at91_dt_defconfig ++++ b/arch/arm/configs/at91_dt_defconfig +@@ -64,7 +64,6 @@ CONFIG_BLK_DEV_LOOP=y + CONFIG_BLK_DEV_RAM=y + CONFIG_BLK_DEV_RAM_COUNT=4 + CONFIG_BLK_DEV_RAM_SIZE=8192 +-CONFIG_ATMEL_TCLIB=y + CONFIG_ATMEL_SSC=y + CONFIG_SCSI=y + CONFIG_BLK_DEV_SD=y +--- a/arch/arm/configs/sama5_defconfig ++++ b/arch/arm/configs/sama5_defconfig +@@ -75,7 +75,6 @@ CONFIG_BLK_DEV_LOOP=y + CONFIG_BLK_DEV_RAM=y + CONFIG_BLK_DEV_RAM_COUNT=4 + CONFIG_BLK_DEV_RAM_SIZE=8192 +-CONFIG_ATMEL_TCLIB=y + CONFIG_ATMEL_SSC=y + CONFIG_EEPROM_AT24=y + CONFIG_SCSI=y diff --git a/debian/patches/features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch b/debian/patches/features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch new file mode 100644 index 000000000..e398430b4 --- /dev/null +++ b/debian/patches/features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch @@ -0,0 +1,31 @@ +From: Anna-Maria Gleixner +Date: Wed, 4 Apr 2018 11:43:56 +0200 +Subject: [PATCH] bdi: Use irqsave variant of refcount_dec_and_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The irqsave variant of refcount_dec_and_lock handles irqsave/restore when +taking/releasing the spin lock. With this variant the call of +local_irq_save/restore is no longer required. + +Signed-off-by: Anna-Maria Gleixner +[bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g ] +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/backing-dev.c | 5 +---- + 1 file changed, 1 insertion(+), 4 deletions(-) + +--- a/mm/backing-dev.c ++++ b/mm/backing-dev.c +@@ -473,11 +473,8 @@ void wb_congested_put(struct bdi_writeba + { + unsigned long flags; + +- local_irq_save(flags); +- if (!refcount_dec_and_lock(&congested->refcnt, &cgwb_lock)) { +- local_irq_restore(flags); ++ if (!refcount_dec_and_lock_irqsave(&congested->refcnt, &cgwb_lock, &flags)) + return; +- } + + /* bdi might already have been destroyed leaving @congested unlinked */ + if (congested->__bdi) { diff --git a/debian/patches/features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch b/debian/patches/features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch new file mode 100644 index 000000000..80873e583 --- /dev/null +++ b/debian/patches/features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch @@ -0,0 +1,36 @@ +From: Alexandre Belloni +Date: Wed, 18 Apr 2018 12:51:43 +0200 +Subject: [PATCH 6/6] ARM: configs: at91: unselect PIT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The PIT is not required anymore to successfully boot and may actually harm +in case preempt-rt is used because the PIT interrupt is shared. +Disable it so the TCB clocksource is used. + +Signed-off-by: Alexandre Belloni +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/configs/at91_dt_defconfig | 1 + + arch/arm/configs/sama5_defconfig | 1 + + 2 files changed, 2 insertions(+) + +--- a/arch/arm/configs/at91_dt_defconfig ++++ b/arch/arm/configs/at91_dt_defconfig +@@ -19,6 +19,7 @@ CONFIG_ARCH_MULTI_V5=y + CONFIG_ARCH_AT91=y + CONFIG_SOC_AT91RM9200=y + CONFIG_SOC_AT91SAM9=y ++# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set + CONFIG_AEABI=y + CONFIG_UACCESS_WITH_MEMCPY=y + CONFIG_ZBOOT_ROM_TEXT=0x0 +--- a/arch/arm/configs/sama5_defconfig ++++ b/arch/arm/configs/sama5_defconfig +@@ -20,6 +20,7 @@ CONFIG_ARCH_AT91=y + CONFIG_SOC_SAMA5D2=y + CONFIG_SOC_SAMA5D3=y + CONFIG_SOC_SAMA5D4=y ++# CONFIG_ATMEL_CLOCKSOURCE_PIT is not set + CONFIG_AEABI=y + CONFIG_UACCESS_WITH_MEMCPY=y + CONFIG_ZBOOT_ROM_TEXT=0x0 diff --git a/debian/patches/features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch b/debian/patches/features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch new file mode 100644 index 000000000..d093616f7 --- /dev/null +++ b/debian/patches/features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch @@ -0,0 +1,31 @@ +From: Anna-Maria Gleixner +Date: Wed, 4 Apr 2018 11:43:57 +0200 +Subject: [PATCH] userns: Use irqsave variant of refcount_dec_and_lock() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The irqsave variant of refcount_dec_and_lock handles irqsave/restore when +taking/releasing the spin lock. With this variant the call of +local_irq_save/restore is no longer required. + +Signed-off-by: Anna-Maria Gleixner +[bigeasy: s@atomic_dec_and_lock@refcount_dec_and_lock@g ] +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/user.c | 5 +---- + 1 file changed, 1 insertion(+), 4 deletions(-) + +--- a/kernel/user.c ++++ b/kernel/user.c +@@ -169,11 +169,8 @@ void free_uid(struct user_struct *up) + if (!up) + return; + +- local_irq_save(flags); +- if (refcount_dec_and_lock(&up->__count, &uidhash_lock)) ++ if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) + free_user(up, flags); +- else +- local_irq_restore(flags); + } + + struct user_struct *alloc_uid(kuid_t uid) diff --git a/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch b/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch new file mode 100644 index 000000000..74b3767ed --- /dev/null +++ b/debian/patches/features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch @@ -0,0 +1,86 @@ +From: "Yadi.hu" +Date: Wed, 10 Dec 2014 10:32:09 +0800 +Subject: ARM: enable irq in translation/section permission fault handlers +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Probably happens on all ARM, with +CONFIG_PREEMPT_RT_FULL +CONFIG_DEBUG_ATOMIC_SLEEP + +This simple program.... + +int main() { + *((char*)0xc0001000) = 0; +}; + +[ 512.742724] BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +[ 512.743000] in_atomic(): 0, irqs_disabled(): 128, pid: 994, name: a +[ 512.743217] INFO: lockdep is turned off. +[ 512.743360] irq event stamp: 0 +[ 512.743482] hardirqs last enabled at (0): [< (null)>] (null) +[ 512.743714] hardirqs last disabled at (0): [] copy_process+0x3b0/0x11c0 +[ 512.744013] softirqs last enabled at (0): [] copy_process+0x3b0/0x11c0 +[ 512.744303] softirqs last disabled at (0): [< (null)>] (null) +[ 512.744631] [] (unwind_backtrace+0x0/0x104) +[ 512.745001] [] (dump_stack+0x20/0x24) +[ 512.745355] [] (__might_sleep+0x1dc/0x1e0) +[ 512.745717] [] (rt_spin_lock+0x34/0x6c) +[ 512.746073] [] (do_force_sig_info+0x34/0xf0) +[ 512.746457] [] (force_sig_info+0x18/0x1c) +[ 512.746829] [] (__do_user_fault+0x9c/0xd8) +[ 512.747185] [] (do_bad_area+0x7c/0x94) +[ 512.747536] [] (do_sect_fault+0x40/0x48) +[ 512.747898] [] (do_DataAbort+0x40/0xa0) +[ 512.748181] Exception stack(0xecaa1fb0 to 0xecaa1ff8) + +Oxc0000000 belongs to kernel address space, user task can not be +allowed to access it. For above condition, correct result is that +test case should receive a “segment fault” and exits but not stacks. + +the root cause is commit 02fe2845d6a8 ("avoid enabling interrupts in +prefetch/data abort handlers"),it deletes irq enable block in Data +abort assemble code and move them into page/breakpiont/alignment fault +handlers instead. But author does not enable irq in translation/section +permission fault handlers. ARM disables irq when it enters exception/ +interrupt mode, if kernel doesn't enable irq, it would be still disabled +during translation/section permission fault. + +We see the above splat because do_force_sig_info is still called with +IRQs off, and that code eventually does a: + + spin_lock_irqsave(&t->sighand->siglock, flags); + +As this is architecture independent code, and we've not seen any other +need for other arch to have the siglock converted to raw lock, we can +conclude that we should enable irq for ARM translation/section +permission exception. + + +Signed-off-by: Yadi.hu +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mm/fault.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +--- a/arch/arm/mm/fault.c ++++ b/arch/arm/mm/fault.c +@@ -438,6 +438,9 @@ do_translation_fault(unsigned long addr, + if (addr < TASK_SIZE) + return do_page_fault(addr, fsr, regs); + ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + if (user_mode(regs)) + goto bad_area; + +@@ -505,6 +508,9 @@ do_translation_fault(unsigned long addr, + static int + do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs) + { ++ if (interrupts_enabled(regs)) ++ local_irq_enable(); ++ + do_bad_area(addr, fsr, regs); + return 0; + } diff --git a/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch b/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch new file mode 100644 index 000000000..7bbc99b1e --- /dev/null +++ b/debian/patches/features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch @@ -0,0 +1,77 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 21 Mar 2013 19:01:05 +0100 +Subject: printk: Drop the logbuf_lock more often +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The lock is hold with irgs off. The latency drops 500us+ on my arm bugs +with a "full" buffer after executing "dmesg" on the shell. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/printk/printk.c | 27 +++++++++++++++++++++++++++ + 1 file changed, 27 insertions(+) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1411,6 +1411,8 @@ static int syslog_print_all(char __user + { + char *text; + int len = 0; ++ int attempts = 0; ++ int num_msg; + + text = kmalloc(LOG_LINE_MAX + PREFIX_MAX, GFP_KERNEL); + if (!text) +@@ -1422,6 +1424,14 @@ static int syslog_print_all(char __user + u64 seq; + u32 idx; + ++try_again: ++ attempts++; ++ if (attempts > 10) { ++ len = -EBUSY; ++ goto out; ++ } ++ num_msg = 0; ++ + /* + * Find first record that fits, including all following records, + * into the user-provided buffer for this dump. +@@ -1434,6 +1444,14 @@ static int syslog_print_all(char __user + len += msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ logbuf_unlock_irq(); ++ logbuf_lock_irq(); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* move first record forward until length fits into the buffer */ +@@ -1445,6 +1463,14 @@ static int syslog_print_all(char __user + len -= msg_print_text(msg, true, NULL, 0); + idx = log_next(idx); + seq++; ++ num_msg++; ++ if (num_msg > 5) { ++ num_msg = 0; ++ logbuf_unlock_irq(); ++ logbuf_lock_irq(); ++ if (clear_seq < log_first_seq) ++ goto try_again; ++ } + } + + /* last message fitting into this dump */ +@@ -1483,6 +1509,7 @@ static int syslog_print_all(char __user + clear_seq = log_next_seq; + clear_idx = log_next_idx; + } ++out: + logbuf_unlock_irq(); + + kfree(text); diff --git a/debian/patches/features/all/rt/KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch b/debian/patches/features/all/rt/KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch new file mode 100644 index 000000000..aceeac933 --- /dev/null +++ b/debian/patches/features/all/rt/KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch @@ -0,0 +1,52 @@ +From: Josh Cartwright +Date: Thu, 11 Feb 2016 11:54:01 -0600 +Subject: KVM: arm/arm64: downgrade preempt_disable()d region to migrate_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +kvm_arch_vcpu_ioctl_run() disables the use of preemption when updating +the vgic and timer states to prevent the calling task from migrating to +another CPU. It does so to prevent the task from writing to the +incorrect per-CPU GIC distributor registers. + +On -rt kernels, it's possible to maintain the same guarantee with the +use of migrate_{disable,enable}(), with the added benefit that the +migrate-disabled region is preemptible. Update +kvm_arch_vcpu_ioctl_run() to do so. + +Cc: Christoffer Dall +Reported-by: Manish Jaggi +Signed-off-by: Josh Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + virt/kvm/arm/arm.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/virt/kvm/arm/arm.c ++++ b/virt/kvm/arm/arm.c +@@ -694,7 +694,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v + * involves poking the GIC, which must be done in a + * non-preemptible context. + */ +- preempt_disable(); ++ migrate_disable(); + + kvm_pmu_flush_hwstate(vcpu); + +@@ -743,7 +743,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v + kvm_timer_sync_hwstate(vcpu); + kvm_vgic_sync_hwstate(vcpu); + local_irq_enable(); +- preempt_enable(); ++ migrate_enable(); + continue; + } + +@@ -821,7 +821,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_v + /* Exit types that need handling before we can be preempted */ + handle_exit_early(vcpu, run, ret); + +- preempt_enable(); ++ migrate_enable(); + + ret = handle_exit(vcpu, run, ret); + } diff --git a/debian/patches/features/all/rt/NFSv4-replace-seqcount_t-with-a-seqlock_t.patch b/debian/patches/features/all/rt/NFSv4-replace-seqcount_t-with-a-seqlock_t.patch new file mode 100644 index 000000000..b8ce03d88 --- /dev/null +++ b/debian/patches/features/all/rt/NFSv4-replace-seqcount_t-with-a-seqlock_t.patch @@ -0,0 +1,128 @@ +Date: Fri, 28 Oct 2016 23:05:11 +0200 +From: Sebastian Andrzej Siewior +To: Trond Myklebust +Cc: Anna Schumaker , + linux-nfs@vger.kernel.org, linux-kernel@vger.kernel.org, + tglx@linutronix.de +Subject: NFSv4: replace seqcount_t with a seqlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The raw_write_seqcount_begin() in nfs4_reclaim_open_state() bugs me +because it maps to preempt_disable() in -RT which I can't have at this +point. So I took a look at the code. +It the lockdep part was removed in commit abbec2da13f0 ("NFS: Use +raw_write_seqcount_begin/end int nfs4_reclaim_open_state") because +lockdep complained. The whole seqcount thing was introduced in commit +c137afabe330 ("NFSv4: Allow the state manager to mark an open_owner as +being recovered"). +The recovery threads runs only once. +write_seqlock() does not work on !RT because it disables preemption and it the +writer side is preemptible (has to remain so despite the fact that it will +block readers). + +Reported-by: kernel test robot +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/nfs/delegation.c | 4 ++-- + fs/nfs/nfs4_fs.h | 2 +- + fs/nfs/nfs4proc.c | 4 ++-- + fs/nfs/nfs4state.c | 22 ++++++++++++++++------ + 4 files changed, 21 insertions(+), 11 deletions(-) + +--- a/fs/nfs/delegation.c ++++ b/fs/nfs/delegation.c +@@ -152,11 +152,11 @@ static int nfs_delegation_claim_opens(st + sp = state->owner; + /* Block nfs4_proc_unlck */ + mutex_lock(&sp->so_delegreturn_mutex); +- seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); ++ seq = read_seqbegin(&sp->so_reclaim_seqlock); + err = nfs4_open_delegation_recall(ctx, state, stateid, type); + if (!err) + err = nfs_delegation_claim_locks(ctx, state, stateid); +- if (!err && read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) ++ if (!err && read_seqretry(&sp->so_reclaim_seqlock, seq)) + err = -EAGAIN; + mutex_unlock(&sp->so_delegreturn_mutex); + put_nfs_open_context(ctx); +--- a/fs/nfs/nfs4_fs.h ++++ b/fs/nfs/nfs4_fs.h +@@ -112,7 +112,7 @@ struct nfs4_state_owner { + unsigned long so_flags; + struct list_head so_states; + struct nfs_seqid_counter so_seqid; +- seqcount_t so_reclaim_seqcount; ++ seqlock_t so_reclaim_seqlock; + struct mutex so_delegreturn_mutex; + }; + +--- a/fs/nfs/nfs4proc.c ++++ b/fs/nfs/nfs4proc.c +@@ -2811,7 +2811,7 @@ static int _nfs4_open_and_get_state(stru + unsigned int seq; + int ret; + +- seq = raw_seqcount_begin(&sp->so_reclaim_seqcount); ++ seq = raw_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); + + ret = _nfs4_proc_open(opendata, ctx); + if (ret != 0) +@@ -2849,7 +2849,7 @@ static int _nfs4_open_and_get_state(stru + + if (d_inode(dentry) == state->inode) { + nfs_inode_attach_open_context(ctx); +- if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq)) ++ if (read_seqretry(&sp->so_reclaim_seqlock, seq)) + nfs4_schedule_stateid_recovery(server, state); + else + pnfs_parse_lgopen(state->inode, opendata->lgp, ctx); +--- a/fs/nfs/nfs4state.c ++++ b/fs/nfs/nfs4state.c +@@ -511,7 +511,7 @@ nfs4_alloc_state_owner(struct nfs_server + nfs4_init_seqid_counter(&sp->so_seqid); + atomic_set(&sp->so_count, 1); + INIT_LIST_HEAD(&sp->so_lru); +- seqcount_init(&sp->so_reclaim_seqcount); ++ seqlock_init(&sp->so_reclaim_seqlock); + mutex_init(&sp->so_delegreturn_mutex); + return sp; + } +@@ -1560,8 +1560,12 @@ static int nfs4_reclaim_open_state(struc + * recovering after a network partition or a reboot from a + * server that doesn't support a grace period. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_seqlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_begin(&sp->so_reclaim_seqlock.seqcount); ++#endif + spin_lock(&sp->so_lock); +- raw_write_seqcount_begin(&sp->so_reclaim_seqcount); + restart: + list_for_each_entry(state, &sp->so_states, open_states) { + if (!test_and_clear_bit(ops->state_flag_bit, &state->flags)) +@@ -1630,14 +1634,20 @@ static int nfs4_reclaim_open_state(struc + spin_lock(&sp->so_lock); + goto restart; + } +- raw_write_seqcount_end(&sp->so_reclaim_seqcount); + spin_unlock(&sp->so_lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_sequnlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); ++#endif + return 0; + out_err: + nfs4_put_open_state(state); +- spin_lock(&sp->so_lock); +- raw_write_seqcount_end(&sp->so_reclaim_seqcount); +- spin_unlock(&sp->so_lock); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ write_sequnlock(&sp->so_reclaim_seqlock); ++#else ++ write_seqcount_end(&sp->so_reclaim_seqlock.seqcount); ++#endif + return status; + } + diff --git a/debian/patches/features/all/rt/SCSI-libsas-remove-irq-save-in-sas_ata_qc_issue.patch b/debian/patches/features/all/rt/SCSI-libsas-remove-irq-save-in-sas_ata_qc_issue.patch new file mode 100644 index 000000000..ec87fe042 --- /dev/null +++ b/debian/patches/features/all/rt/SCSI-libsas-remove-irq-save-in-sas_ata_qc_issue.patch @@ -0,0 +1,49 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 12 Apr 2018 09:16:22 +0200 +Subject: [PATCH] [SCSI] libsas: remove irq save in sas_ata_qc_issue() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +[ upstream commit 2da11d4262639dc0e2fabc6a70886db57af25c43 ] + +Since commit 312d3e56119a ("[SCSI] libsas: remove ata_port.lock +management duties from lldds") the sas_ata_qc_issue() function unlocks +the ata_port.lock and disables interrupts before doing so. +That lock is always taken with disabled interrupts so at this point, the +interrupts are already disabled. There is no need to disable the +interrupts before the unlock operation because they are already +disabled. +Restoring the interrupt state later does not change anything because +they were disabled and remain disabled. Therefore remove the operations +which do not change the behaviour. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/scsi/libsas/sas_ata.c | 3 --- + 1 file changed, 3 deletions(-) + +--- a/drivers/scsi/libsas/sas_ata.c ++++ b/drivers/scsi/libsas/sas_ata.c +@@ -176,7 +176,6 @@ static void sas_ata_task_done(struct sas + + static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc) + { +- unsigned long flags; + struct sas_task *task; + struct scatterlist *sg; + int ret = AC_ERR_SYSTEM; +@@ -190,7 +189,6 @@ static unsigned int sas_ata_qc_issue(str + /* TODO: audit callers to ensure they are ready for qc_issue to + * unconditionally re-enable interrupts + */ +- local_irq_save(flags); + spin_unlock(ap->lock); + + /* If the device fell off, no sense in issuing commands */ +@@ -252,7 +250,6 @@ static unsigned int sas_ata_qc_issue(str + + out: + spin_lock(ap->lock); +- local_irq_restore(flags); + return ret; + } + diff --git a/debian/patches/features/all/rt/SCSI-qla2xxx-remove-irq-save-in-qla2x00_poll.patch b/debian/patches/features/all/rt/SCSI-qla2xxx-remove-irq-save-in-qla2x00_poll.patch new file mode 100644 index 000000000..e250abcdf --- /dev/null +++ b/debian/patches/features/all/rt/SCSI-qla2xxx-remove-irq-save-in-qla2x00_poll.patch @@ -0,0 +1,42 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 12 Apr 2018 09:55:25 +0200 +Subject: [PATCH] [SCSI] qla2xxx: remove irq save in qla2x00_poll() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +[ upstream commit b3a8aa90c46095cbad454eb068bfb5a8eb56d4e3 ] + +In commit d2ba5675d899 ("[SCSI] qla2xxx: Disable local-interrupts while +polling for RISC status.") added a local_irq_disable() before invoking +the ->intr_handler callback. The function, which was used in this +callback, did not disable interrupts while acquiring the spin_lock so a +deadlock was possible and this change was one possible solution. + +The function in question was qla2300_intr_handler() and is using +spin_lock_irqsave() since commit 43fac4d97a1a ("[SCSI] qla2xxx: Resolve +a performance issue in interrupt"). +I checked all other ->intr_handler callbacks and all of them use the +irqsave variant so it is safe to remove the local_irq_save() block now. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/scsi/qla2xxx/qla_inline.h | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +--- a/drivers/scsi/qla2xxx/qla_inline.h ++++ b/drivers/scsi/qla2xxx/qla_inline.h +@@ -58,14 +58,12 @@ qla2x00_debounce_register(volatile uint1 + static inline void + qla2x00_poll(struct rsp_que *rsp) + { +- unsigned long flags; + struct qla_hw_data *ha = rsp->hw; +- local_irq_save(flags); ++ + if (IS_P3P_TYPE(ha)) + qla82xx_poll(0, rsp); + else + ha->isp_ops->intr_handler(0, rsp); +- local_irq_restore(flags); + } + + static inline uint8_t * diff --git a/debian/patches/features/all/rt/add_migrate_disable.patch b/debian/patches/features/all/rt/add_migrate_disable.patch new file mode 100644 index 000000000..968e22cdf --- /dev/null +++ b/debian/patches/features/all/rt/add_migrate_disable.patch @@ -0,0 +1,252 @@ +From: Sebastian Andrzej Siewior +Date: Sat, 27 May 2017 19:02:06 +0200 +Subject: kernel/sched/core: add migrate_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +--- + include/linux/preempt.h | 23 ++++++++ + include/linux/sched.h | 7 ++ + include/linux/smp.h | 3 + + kernel/sched/core.c | 130 +++++++++++++++++++++++++++++++++++++++++++++++- + kernel/sched/debug.c | 4 + + 5 files changed, 165 insertions(+), 2 deletions(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -185,6 +185,22 @@ do { \ + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + ++#ifdef CONFIG_SMP ++ ++extern void migrate_disable(void); ++extern void migrate_enable(void); ++ ++int __migrate_disabled(struct task_struct *p); ++ ++#else ++#define migrate_disable() barrier() ++#define migrate_enable() barrier() ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} ++#endif ++ + #ifdef CONFIG_PREEMPT + #define preempt_enable() \ + do { \ +@@ -253,6 +269,13 @@ do { \ + #define preempt_enable_notrace() barrier() + #define preemptible() 0 + ++#define migrate_disable() barrier() ++#define migrate_enable() barrier() ++ ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} + #endif /* CONFIG_PREEMPT_COUNT */ + + #ifdef MODULE +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -662,6 +662,13 @@ struct task_struct { + int nr_cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ int migrate_disable; ++ int migrate_disable_update; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif + + #ifdef CONFIG_PREEMPT_RCU + int rcu_read_lock_nesting; +--- a/include/linux/smp.h ++++ b/include/linux/smp.h +@@ -202,6 +202,9 @@ static inline int get_boot_cpu_id(void) + #define get_cpu() ({ preempt_disable(); smp_processor_id(); }) + #define put_cpu() preempt_enable() + ++#define get_cpu_light() ({ migrate_disable(); smp_processor_id(); }) ++#define put_cpu_light() migrate_enable() ++ + /* + * Callback to arch code if there's nosmp or maxcpus=0 on the + * boot command line: +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1030,7 +1030,15 @@ void set_cpus_allowed_common(struct task + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +-void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++int __migrate_disabled(struct task_struct *p) ++{ ++ return p->migrate_disable; ++} ++#endif ++ ++static void __do_set_cpus_allowed_tail(struct task_struct *p, ++ const struct cpumask *new_mask) + { + struct rq *rq = task_rq(p); + bool queued, running; +@@ -1059,6 +1067,20 @@ void do_set_cpus_allowed(struct task_str + set_curr_task(rq, p); + } + ++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) ++{ ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ if (__migrate_disabled(p)) { ++ lockdep_assert_held(&p->pi_lock); ++ ++ cpumask_copy(&p->cpus_mask, new_mask); ++ p->migrate_disable_update = 1; ++ return; ++ } ++#endif ++ __do_set_cpus_allowed_tail(p, new_mask); ++} ++ + /* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on +@@ -1117,9 +1139,16 @@ static int __set_cpus_allowed_ptr(struct + } + + /* Can the task run on the task's current CPU? If so, we're done */ +- if (cpumask_test_cpu(task_cpu(p), new_mask)) ++ if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ if (__migrate_disabled(p)) { ++ p->migrate_disable_update = 1; ++ goto out; ++ } ++#endif ++ + dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask); + if (task_running(rq, p) || p->state == TASK_WAKING) { + struct migration_arg arg = { p, dest_cpu }; +@@ -7082,3 +7111,100 @@ const u32 sched_prio_to_wmult[40] = { + }; + + #undef CREATE_TRACE_POINTS ++ ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ if (p->migrate_disable) { ++ p->migrate_disable++; ++ return; ++ } ++ ++ preempt_disable(); ++ p->migrate_disable = 1; ++ ++ p->cpus_ptr = cpumask_of(smp_processor_id()); ++ p->nr_cpus_allowed = 1; ++ ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ WARN_ON_ONCE(p->migrate_disable_atomic); ++#endif ++ ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ if (p->migrate_disable > 1) { ++ p->migrate_disable--; ++ return; ++ } ++ ++ preempt_disable(); ++ ++ p->cpus_ptr = &p->cpus_mask; ++ p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); ++ p->migrate_disable = 0; ++ ++ if (p->migrate_disable_update) { ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ rq = task_rq_lock(p, &rf); ++ update_rq_clock(rq); ++ ++ __do_set_cpus_allowed_tail(p, &p->cpus_mask); ++ task_rq_unlock(rq, p, &rf); ++ ++ p->migrate_disable_update = 0; ++ ++ WARN_ON(smp_processor_id() != task_cpu(p)); ++ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { ++ const struct cpumask *cpu_valid_mask = cpu_active_mask; ++ struct migration_arg arg; ++ unsigned int dest_cpu; ++ ++ if (p->flags & PF_KTHREAD) { ++ /* ++ * Kernel threads are allowed on online && !active CPUs ++ */ ++ cpu_valid_mask = cpu_online_mask; ++ } ++ dest_cpu = cpumask_any_and(cpu_valid_mask, &p->cpus_mask); ++ arg.task = p; ++ arg.dest_cpu = dest_cpu; ++ ++ preempt_enable(); ++ stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); ++ tlb_migrate_finish(p->mm); ++ return; ++ } ++ } ++ preempt_enable(); ++} ++EXPORT_SYMBOL(migrate_enable); ++#endif +--- a/kernel/sched/debug.c ++++ b/kernel/sched/debug.c +@@ -979,6 +979,10 @@ void proc_sched_show_task(struct task_st + P(dl.runtime); + P(dl.deadline); + } ++#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++ P(migrate_disable); ++#endif ++ P(nr_cpus_allowed); + #undef PN_SCHEDSTAT + #undef PN + #undef __PN diff --git a/debian/patches/features/all/rt/apparmor-use-a-locallock-instead-preempt_disable.patch b/debian/patches/features/all/rt/apparmor-use-a-locallock-instead-preempt_disable.patch new file mode 100644 index 000000000..7d88c68d6 --- /dev/null +++ b/debian/patches/features/all/rt/apparmor-use-a-locallock-instead-preempt_disable.patch @@ -0,0 +1,77 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 11 Oct 2017 17:43:49 +0200 +Subject: apparmor: use a locallock instead preempt_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +get_buffers() disables preemption which acts as a lock for the per-CPU +variable. Since we can't disable preemption here on RT, a local_lock is +lock is used in order to remain on the same CPU and not to have more +than one user within the critical section. + +Signed-off-by: Sebastian Andrzej Siewior +--- + security/apparmor/include/path.h | 19 ++++++++++++++++--- + security/apparmor/lsm.c | 2 +- + 2 files changed, 17 insertions(+), 4 deletions(-) + +--- a/security/apparmor/include/path.h ++++ b/security/apparmor/include/path.h +@@ -40,8 +40,10 @@ struct aa_buffers { + + #include + #include ++#include + + DECLARE_PER_CPU(struct aa_buffers, aa_buffers); ++DECLARE_LOCAL_IRQ_LOCK(aa_buffers_lock); + + #define ASSIGN(FN, A, X, N) ((X) = FN(A, N)) + #define EVAL1(FN, A, X) ASSIGN(FN, A, X, 0) /*X = FN(0)*/ +@@ -51,7 +53,17 @@ DECLARE_PER_CPU(struct aa_buffers, aa_bu + + #define for_each_cpu_buffer(I) for ((I) = 0; (I) < MAX_PATH_BUFFERS; (I)++) + +-#ifdef CONFIG_DEBUG_PREEMPT ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void AA_BUG_PREEMPT_ENABLED(const char *s) ++{ ++ struct local_irq_lock *lv; ++ ++ lv = this_cpu_ptr(&aa_buffers_lock); ++ WARN_ONCE(lv->owner != current, ++ "__get_buffer without aa_buffers_lock\n"); ++} ++ ++#elif defined(CONFIG_DEBUG_PREEMPT) + #define AA_BUG_PREEMPT_ENABLED(X) AA_BUG(preempt_count() <= 0, X) + #else + #define AA_BUG_PREEMPT_ENABLED(X) /* nop */ +@@ -67,14 +79,15 @@ DECLARE_PER_CPU(struct aa_buffers, aa_bu + + #define get_buffers(X...) \ + do { \ +- struct aa_buffers *__cpu_var = get_cpu_ptr(&aa_buffers); \ ++ struct aa_buffers *__cpu_var; \ ++ __cpu_var = get_locked_ptr(aa_buffers_lock, &aa_buffers); \ + __get_buffers(__cpu_var, X); \ + } while (0) + + #define put_buffers(X, Y...) \ + do { \ + __put_buffers(X, Y); \ +- put_cpu_ptr(&aa_buffers); \ ++ put_locked_ptr(aa_buffers_lock, &aa_buffers); \ + } while (0) + + #endif /* __AA_PATH_H */ +--- a/security/apparmor/lsm.c ++++ b/security/apparmor/lsm.c +@@ -45,7 +45,7 @@ + int apparmor_initialized; + + DEFINE_PER_CPU(struct aa_buffers, aa_buffers); +- ++DEFINE_LOCAL_IRQ_LOCK(aa_buffers_lock); + + /* + * LSM hook functions diff --git a/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch b/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch new file mode 100644 index 000000000..ec8bf2803 --- /dev/null +++ b/debian/patches/features/all/rt/arch-arm64-Add-lazy-preempt-support.patch @@ -0,0 +1,119 @@ +From: Anders Roxell +Date: Thu, 14 May 2015 17:52:17 +0200 +Subject: arch/arm64: Add lazy preempt support +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +arm64 is missing support for PREEMPT_RT. The main feature which is +lacking is support for lazy preemption. The arch-specific entry code, +thread information structure definitions, and associated data tables +have to be extended to provide this support. Then the Kconfig file has +to be extended to indicate the support is available, and also to +indicate that support for full RT preemption is now available. + +Signed-off-by: Anders Roxell +--- + arch/arm64/Kconfig | 1 + + arch/arm64/include/asm/thread_info.h | 6 +++++- + arch/arm64/kernel/asm-offsets.c | 1 + + arch/arm64/kernel/entry.S | 12 +++++++++--- + arch/arm64/kernel/signal.c | 2 +- + 5 files changed, 17 insertions(+), 5 deletions(-) + +--- a/arch/arm64/Kconfig ++++ b/arch/arm64/Kconfig +@@ -125,6 +125,7 @@ config ARM64 + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RCU_TABLE_FREE + select HAVE_STACKPROTECTOR +--- a/arch/arm64/include/asm/thread_info.h ++++ b/arch/arm64/include/asm/thread_info.h +@@ -43,6 +43,7 @@ struct thread_info { + u64 ttbr0; /* saved TTBR0_EL1 */ + #endif + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + }; + + #define thread_saved_pc(tsk) \ +@@ -76,6 +77,7 @@ void arch_release_task_struct(struct tas + #define TIF_FOREIGN_FPSTATE 3 /* CPU's FP state is not current's */ + #define TIF_UPROBE 4 /* uprobe breakpoint or singlestep */ + #define TIF_FSCHECK 5 /* Check FS is USER_DS on return */ ++#define TIF_NEED_RESCHED_LAZY 6 + #define TIF_NOHZ 7 + #define TIF_SYSCALL_TRACE 8 + #define TIF_SYSCALL_AUDIT 9 +@@ -94,6 +96,7 @@ void arch_release_task_struct(struct tas + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) + #define _TIF_FOREIGN_FPSTATE (1 << TIF_FOREIGN_FPSTATE) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_NOHZ (1 << TIF_NOHZ) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -106,8 +109,9 @@ void arch_release_task_struct(struct tas + + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ + _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \ +- _TIF_UPROBE | _TIF_FSCHECK) ++ _TIF_UPROBE | _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) + #define _TIF_SYSCALL_WORK (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \ + _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \ + _TIF_NOHZ) +--- a/arch/arm64/kernel/asm-offsets.c ++++ b/arch/arm64/kernel/asm-offsets.c +@@ -41,6 +41,7 @@ int main(void) + BLANK(); + DEFINE(TSK_TI_FLAGS, offsetof(struct task_struct, thread_info.flags)); + DEFINE(TSK_TI_PREEMPT, offsetof(struct task_struct, thread_info.preempt_count)); ++ DEFINE(TSK_TI_PREEMPT_LAZY, offsetof(struct task_struct, thread_info.preempt_lazy_count)); + DEFINE(TSK_TI_ADDR_LIMIT, offsetof(struct task_struct, thread_info.addr_limit)); + #ifdef CONFIG_ARM64_SW_TTBR0_PAN + DEFINE(TSK_TI_TTBR0, offsetof(struct task_struct, thread_info.ttbr0)); +--- a/arch/arm64/kernel/entry.S ++++ b/arch/arm64/kernel/entry.S +@@ -633,11 +633,16 @@ ENDPROC(el1_sync) + + #ifdef CONFIG_PREEMPT + ldr w24, [tsk, #TSK_TI_PREEMPT] // get preempt count +- cbnz w24, 1f // preempt count != 0 ++ cbnz w24, 2f // preempt count != 0 + ldr x0, [tsk, #TSK_TI_FLAGS] // get flags +- tbz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? +- bl el1_preempt ++ tbnz x0, #TIF_NEED_RESCHED, 1f // needs rescheduling? ++ ++ ldr w24, [tsk, #TSK_TI_PREEMPT_LAZY] // get preempt lazy count ++ cbnz w24, 2f // preempt lazy count != 0 ++ tbz x0, #TIF_NEED_RESCHED_LAZY, 2f // needs rescheduling? + 1: ++ bl el1_preempt ++2: + #endif + #ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_on +@@ -651,6 +656,7 @@ ENDPROC(el1_irq) + 1: bl preempt_schedule_irq // irq en/disable is done inside + ldr x0, [tsk, #TSK_TI_FLAGS] // get new tasks TI_FLAGS + tbnz x0, #TIF_NEED_RESCHED, 1b // needs rescheduling? ++ tbnz x0, #TIF_NEED_RESCHED_LAZY, 1b // needs rescheduling? + ret x24 + #endif + +--- a/arch/arm64/kernel/signal.c ++++ b/arch/arm64/kernel/signal.c +@@ -923,7 +923,7 @@ asmlinkage void do_notify_resume(struct + /* Check valid user FS if needed */ + addr_limit_user_check(); + +- if (thread_flags & _TIF_NEED_RESCHED) { ++ if (thread_flags & _TIF_NEED_RESCHED_MASK) { + /* Unmask Debug and SError for the next task */ + local_daif_restore(DAIF_PROCCTX_NOIRQ); + diff --git a/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch b/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch new file mode 100644 index 000000000..f0604f072 --- /dev/null +++ b/debian/patches/features/all/rt/arm-convert-boot-lock-to-raw.patch @@ -0,0 +1,412 @@ +From: Frank Rowand +Date: Mon, 19 Sep 2011 14:51:14 -0700 +Subject: arm: Convert arm boot_lock to raw +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The arm boot_lock is used by the secondary processor startup code. The locking +task is the idle thread, which has idle->sched_class == &idle_sched_class. +idle_sched_class->enqueue_task == NULL, so if the idle task blocks on the +lock, the attempt to wake it when the lock becomes available will fail: + +try_to_wake_up() + ... + activate_task() + enqueue_task() + p->sched_class->enqueue_task(rq, p, flags) + +Fix by converting boot_lock to a raw spin lock. + +Signed-off-by: Frank Rowand +Link: http://lkml.kernel.org/r/4E77B952.3010606@am.sony.com +Signed-off-by: Thomas Gleixner +Tested-by: Tony Lindgren +Acked-by: Krzysztof Kozlowski +Tested-by: Krzysztof Kozlowski [Exynos5422 Linaro PM-QA] +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mach-exynos/platsmp.c | 12 ++++++------ + arch/arm/mach-hisi/platmcpm.c | 22 +++++++++++----------- + arch/arm/mach-omap2/omap-smp.c | 10 +++++----- + arch/arm/mach-prima2/platsmp.c | 10 +++++----- + arch/arm/mach-qcom/platsmp.c | 10 +++++----- + arch/arm/mach-spear/platsmp.c | 10 +++++----- + arch/arm/mach-sti/platsmp.c | 10 +++++----- + arch/arm/plat-versatile/platsmp.c | 10 +++++----- + 8 files changed, 47 insertions(+), 47 deletions(-) + +--- a/arch/arm/mach-exynos/platsmp.c ++++ b/arch/arm/mach-exynos/platsmp.c +@@ -239,7 +239,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void exynos_secondary_init(unsigned int cpu) + { +@@ -252,8 +252,8 @@ static void exynos_secondary_init(unsign + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int exynos_set_boot_addr(u32 core_id, unsigned long boot_addr) +@@ -317,7 +317,7 @@ static int exynos_boot_secondary(unsigne + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -344,7 +344,7 @@ static int exynos_boot_secondary(unsigne + + if (timeout == 0) { + printk(KERN_ERR "cpu1 power enable failed"); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return -ETIMEDOUT; + } + } +@@ -390,7 +390,7 @@ static int exynos_boot_secondary(unsigne + * calibrations, then wait for it to finish + */ + fail: +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? ret : 0; + } +--- a/arch/arm/mach-hisi/platmcpm.c ++++ b/arch/arm/mach-hisi/platmcpm.c +@@ -61,7 +61,7 @@ + + static void __iomem *sysctrl, *fabric; + static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER]; +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + static u32 fabric_phys_addr; + /* + * [0]: bootwrapper physical address +@@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned + if (cluster >= HIP04_MAX_CLUSTERS || cpu >= HIP04_MAX_CPUS_PER_CLUSTER) + return -EINVAL; + +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + + if (hip04_cpu_table[cluster][cpu]) + goto out; +@@ -147,7 +147,7 @@ static int hip04_boot_secondary(unsigned + + out: + hip04_cpu_table[cluster][cpu]++; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + + return 0; + } +@@ -162,11 +162,11 @@ static void hip04_cpu_die(unsigned int l + cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + hip04_cpu_table[cluster][cpu]--; + if (hip04_cpu_table[cluster][cpu] == 1) { + /* A power_up request went ahead of us. */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + return; + } else if (hip04_cpu_table[cluster][cpu] > 1) { + pr_err("Cluster %d CPU%d boots multiple times\n", cluster, cpu); +@@ -174,7 +174,7 @@ static void hip04_cpu_die(unsigned int l + } + + last_man = hip04_cluster_is_down(cluster); +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + if (last_man) { + /* Since it's Cortex A15, disable L2 prefetching. */ + asm volatile( +@@ -203,7 +203,7 @@ static int hip04_cpu_kill(unsigned int l + cpu >= HIP04_MAX_CPUS_PER_CLUSTER); + + count = TIMEOUT_MSEC / POLL_MSEC; +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + for (tries = 0; tries < count; tries++) { + if (hip04_cpu_table[cluster][cpu]) + goto err; +@@ -211,10 +211,10 @@ static int hip04_cpu_kill(unsigned int l + data = readl_relaxed(sysctrl + SC_CPU_RESET_STATUS(cluster)); + if (data & CORE_WFI_STATUS(cpu)) + break; +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + /* Wait for clean L2 when the whole cluster is down. */ + msleep(POLL_MSEC); +- spin_lock_irq(&boot_lock); ++ raw_spin_lock_irq(&boot_lock); + } + if (tries >= count) + goto err; +@@ -231,10 +231,10 @@ static int hip04_cpu_kill(unsigned int l + goto err; + if (hip04_cluster_is_down(cluster)) + hip04_set_snoop_filter(cluster, 0); +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 1; + err: +- spin_unlock_irq(&boot_lock); ++ raw_spin_unlock_irq(&boot_lock); + return 0; + } + #endif +--- a/arch/arm/mach-omap2/omap-smp.c ++++ b/arch/arm/mach-omap2/omap-smp.c +@@ -69,7 +69,7 @@ static const struct omap_smp_config omap + .startup_addr = omap5_secondary_startup, + }; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void __iomem *omap4_get_scu_base(void) + { +@@ -177,8 +177,8 @@ static void omap4_secondary_init(unsigne + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -191,7 +191,7 @@ static int omap4_boot_secondary(unsigned + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Update the AuxCoreBoot0 with boot state for secondary core. +@@ -270,7 +270,7 @@ static int omap4_boot_secondary(unsigned + * Now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return 0; + } +--- a/arch/arm/mach-prima2/platsmp.c ++++ b/arch/arm/mach-prima2/platsmp.c +@@ -22,7 +22,7 @@ + + static void __iomem *clk_base; + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sirfsoc_secondary_init(unsigned int cpu) + { +@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsig + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static const struct of_device_id clk_ids[] = { +@@ -75,7 +75,7 @@ static int sirfsoc_boot_secondary(unsign + /* make sure write buffer is drained */ + mb(); + +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -107,7 +107,7 @@ static int sirfsoc_boot_secondary(unsign + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/mach-qcom/platsmp.c ++++ b/arch/arm/mach-qcom/platsmp.c +@@ -46,7 +46,7 @@ + + extern void secondary_startup_arm(void); + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + #ifdef CONFIG_HOTPLUG_CPU + static void qcom_cpu_die(unsigned int cpu) +@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int scss_release_secondary(unsigned int cpu) +@@ -284,7 +284,7 @@ static int qcom_boot_secondary(unsigned + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * Send the secondary CPU a soft interrupt, thereby causing +@@ -297,7 +297,7 @@ static int qcom_boot_secondary(unsigned + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return ret; + } +--- a/arch/arm/mach-spear/platsmp.c ++++ b/arch/arm/mach-spear/platsmp.c +@@ -32,7 +32,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void __iomem *scu_base = IOMEM(VA_SCU_BASE); + +@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(uns + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int spear13xx_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -59,7 +59,7 @@ static int spear13xx_boot_secondary(unsi + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -84,7 +84,7 @@ static int spear13xx_boot_secondary(unsi + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/mach-sti/platsmp.c ++++ b/arch/arm/mach-sti/platsmp.c +@@ -35,7 +35,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + static void sti_secondary_init(unsigned int cpu) + { +@@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + static int sti_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -60,7 +60,7 @@ static int sti_boot_secondary(unsigned i + * set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * The secondary processor is waiting to be released from +@@ -91,7 +91,7 @@ static int sti_boot_secondary(unsigned i + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } +--- a/arch/arm/plat-versatile/platsmp.c ++++ b/arch/arm/plat-versatile/platsmp.c +@@ -32,7 +32,7 @@ static void write_pen_release(int val) + sync_cache_w(&pen_release); + } + +-static DEFINE_SPINLOCK(boot_lock); ++static DEFINE_RAW_SPINLOCK(boot_lock); + + void versatile_secondary_init(unsigned int cpu) + { +@@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned i + /* + * Synchronise with the boot thread. + */ +- spin_lock(&boot_lock); +- spin_unlock(&boot_lock); ++ raw_spin_lock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + } + + int versatile_boot_secondary(unsigned int cpu, struct task_struct *idle) +@@ -57,7 +57,7 @@ int versatile_boot_secondary(unsigned in + * Set synchronisation state between this boot processor + * and the secondary one + */ +- spin_lock(&boot_lock); ++ raw_spin_lock(&boot_lock); + + /* + * This is really belt and braces; we hold unintended secondary +@@ -87,7 +87,7 @@ int versatile_boot_secondary(unsigned in + * now the secondary core is starting up let it run its + * calibrations, then wait for it to finish + */ +- spin_unlock(&boot_lock); ++ raw_spin_unlock(&boot_lock); + + return pen_release != -1 ? -ENOSYS : 0; + } diff --git a/debian/patches/features/all/rt/arm-disable-NEON-in-kernel-mode.patch b/debian/patches/features/all/rt/arm-disable-NEON-in-kernel-mode.patch new file mode 100644 index 000000000..dc10880e8 --- /dev/null +++ b/debian/patches/features/all/rt/arm-disable-NEON-in-kernel-mode.patch @@ -0,0 +1,165 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 1 Dec 2017 10:42:03 +0100 +Subject: [PATCH] arm*: disable NEON in kernel mode +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +NEON in kernel mode is used by the crypto algorithms and raid6 code. +While the raid6 code looks okay, the crypto algorithms do not: NEON +is enabled on first invocation and may allocate/free/map memory before +the NEON mode is disabled again. +This needs to be changed until it can be enabled. +On ARM NEON in kernel mode can be simply disabled. on ARM64 it needs to +stay on due to possible EFI callbacks so here I disable each algorithm. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/Kconfig | 2 +- + arch/arm64/crypto/Kconfig | 30 +++++++++++++++--------------- + arch/arm64/crypto/crc32-ce-glue.c | 3 ++- + 3 files changed, 18 insertions(+), 17 deletions(-) + +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -2169,7 +2169,7 @@ config NEON + + config KERNEL_MODE_NEON + bool "Support for NEON in kernel mode" +- depends on NEON && AEABI ++ depends on NEON && AEABI && !PREEMPT_RT_BASE + help + Say Y to include support for NEON in kernel mode. + +--- a/arch/arm64/crypto/Kconfig ++++ b/arch/arm64/crypto/Kconfig +@@ -19,43 +19,43 @@ config CRYPTO_SHA512_ARM64 + + config CRYPTO_SHA1_ARM64_CE + tristate "SHA-1 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA1 + + config CRYPTO_SHA2_ARM64_CE + tristate "SHA-224/SHA-256 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA256_ARM64 + + config CRYPTO_SHA512_ARM64_CE + tristate "SHA-384/SHA-512 digest algorithm (ARMv8 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA512_ARM64 + + config CRYPTO_SHA3_ARM64 + tristate "SHA3 digest algorithm (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SHA3 + + config CRYPTO_SM3_ARM64_CE + tristate "SM3 digest algorithm (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_SM3 + + config CRYPTO_SM4_ARM64_CE + tristate "SM4 symmetric cipher (ARMv8.2 Crypto Extensions)" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_SM4 + + config CRYPTO_GHASH_ARM64_CE + tristate "GHASH/AES-GCM using ARMv8 Crypto Extensions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_HASH + select CRYPTO_GF128MUL + select CRYPTO_AES +@@ -63,7 +63,7 @@ config CRYPTO_GHASH_ARM64_CE + + config CRYPTO_CRCT10DIF_ARM64_CE + tristate "CRCT10DIF digest algorithm using PMULL instructions" +- depends on KERNEL_MODE_NEON && CRC_T10DIF ++ depends on KERNEL_MODE_NEON && CRC_T10DIF && !PREEMPT_RT_BASE + select CRYPTO_HASH + + config CRYPTO_CRC32_ARM64_CE +@@ -77,13 +77,13 @@ config CRYPTO_AES_ARM64 + + config CRYPTO_AES_ARM64_CE + tristate "AES core cipher using ARMv8 Crypto Extensions" +- depends on ARM64 && KERNEL_MODE_NEON ++ depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_AES_ARM64 + + config CRYPTO_AES_ARM64_CE_CCM + tristate "AES in CCM mode using ARMv8 Crypto Extensions" +- depends on ARM64 && KERNEL_MODE_NEON ++ depends on ARM64 && KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_ALGAPI + select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 +@@ -91,7 +91,7 @@ config CRYPTO_AES_ARM64_CE_CCM + + config CRYPTO_AES_ARM64_CE_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using ARMv8 Crypto Extensions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64_CE + select CRYPTO_AES_ARM64 +@@ -99,7 +99,7 @@ config CRYPTO_AES_ARM64_CE_BLK + + config CRYPTO_AES_ARM64_NEON_BLK + tristate "AES in ECB/CBC/CTR/XTS modes using NEON instructions" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64 + select CRYPTO_AES +@@ -107,13 +107,13 @@ config CRYPTO_AES_ARM64_NEON_BLK + + config CRYPTO_CHACHA20_NEON + tristate "NEON accelerated ChaCha20 symmetric cipher" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_CHACHA20 + + config CRYPTO_AES_ARM64_BS + tristate "AES in ECB/CBC/CTR/XTS modes using bit-sliced NEON algorithm" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_AES_ARM64_NEON_BLK + select CRYPTO_AES_ARM64 +@@ -121,7 +121,7 @@ config CRYPTO_AES_ARM64_BS + + config CRYPTO_SPECK_NEON + tristate "NEON accelerated Speck cipher algorithms" +- depends on KERNEL_MODE_NEON ++ depends on KERNEL_MODE_NEON && !PREEMPT_RT_BASE + select CRYPTO_BLKCIPHER + select CRYPTO_SPECK + +--- a/arch/arm64/crypto/crc32-ce-glue.c ++++ b/arch/arm64/crypto/crc32-ce-glue.c +@@ -208,7 +208,8 @@ static struct shash_alg crc32_pmull_algs + + static int __init crc32_pmull_mod_init(void) + { +- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) { ++ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && ++ !IS_ENABLED(CONFIG_PREEMPT_RT_BASE) && (elf_hwcap & HWCAP_PMULL)) { + crc32_pmull_algs[0].update = crc32_pmull_update; + crc32_pmull_algs[1].update = crc32c_pmull_update; + diff --git a/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch b/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch new file mode 100644 index 000000000..066867b3b --- /dev/null +++ b/debian/patches/features/all/rt/arm-enable-highmem-for-rt.patch @@ -0,0 +1,174 @@ +Subject: arm: Enable highmem for rt +From: Thomas Gleixner +Date: Wed, 13 Feb 2013 11:03:11 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +fixup highmem for ARM. + +Signed-off-by: Thomas Gleixner +--- + arch/arm/include/asm/switch_to.h | 8 +++++ + arch/arm/mm/highmem.c | 56 +++++++++++++++++++++++++++++++++------ + include/linux/highmem.h | 1 + 3 files changed, 57 insertions(+), 8 deletions(-) + +--- a/arch/arm/include/asm/switch_to.h ++++ b/arch/arm/include/asm/switch_to.h +@@ -4,6 +4,13 @@ + + #include + ++#if defined CONFIG_PREEMPT_RT_FULL && defined CONFIG_HIGHMEM ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p); ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + /* + * For v7 SMP cores running a preemptible kernel we may be pre-empted + * during a TLB maintenance operation, so execute an inner-shareable dsb +@@ -26,6 +33,7 @@ extern struct task_struct *__switch_to(s + #define switch_to(prev,next,last) \ + do { \ + __complete_pending_tlbi(); \ ++ switch_kmaps(prev, next); \ + last = __switch_to(prev,task_thread_info(prev), task_thread_info(next)); \ + } while (0) + +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsig + return *ptep; + } + ++static unsigned int fixmap_idx(int type) ++{ ++ return FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++} ++ + void *kmap(struct page *page) + { + might_sleep(); +@@ -54,12 +59,13 @@ EXPORT_SYMBOL(kunmap); + + void *kmap_atomic(struct page *page) + { ++ pte_t pte = mk_pte(page, kmap_prot); + unsigned int idx; + unsigned long vaddr; + void *kmap; + int type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); +@@ -79,7 +85,7 @@ void *kmap_atomic(struct page *page) + + type = kmap_atomic_idx_push(); + +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + /* +@@ -93,7 +99,10 @@ void *kmap_atomic(struct page *page) + * in place, so the contained TLB flush ensures the TLB is updated + * with the new mapping. + */ +- set_fixmap_pte(idx, mk_pte(page, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } +@@ -106,10 +115,13 @@ void __kunmap_atomic(void *kvaddr) + + if (kvaddr >= (void *)FIXADDR_START) { + type = kmap_atomic_idx(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + + if (cache_is_vivt()) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); + #else +@@ -122,28 +134,56 @@ void __kunmap_atomic(void *kvaddr) + kunmap_high(pte_page(pkmap_page_table[PKMAP_NR(vaddr)])); + } + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + + void *kmap_atomic_pfn(unsigned long pfn) + { ++ pte_t pte = pfn_pte(pfn, kmap_prot); + unsigned long vaddr; + int idx, type; + struct page *page = pfn_to_page(pfn); + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + if (!PageHighMem(page)) + return page_address(page); + + type = kmap_atomic_idx_push(); +- idx = FIX_KMAP_BEGIN + type + KM_TYPE_NR * smp_processor_id(); ++ idx = fixmap_idx(type); + vaddr = __fix_to_virt(idx); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(!pte_none(get_fixmap_pte(vaddr))); + #endif +- set_fixmap_pte(idx, pfn_pte(pfn, kmap_prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_fixmap_pte(idx, pte); + + return (void *)vaddr; + } ++#if defined CONFIG_PREEMPT_RT_FULL ++void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ set_fixmap_pte(idx, __pte(0)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = fixmap_idx(i); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_fixmap_pte(idx, next_p->kmap_pte[i]); ++ } ++} ++#endif +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -8,6 +8,7 @@ + #include + #include + #include ++#include + + #include + diff --git a/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch b/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch new file mode 100644 index 000000000..d32a4dc88 --- /dev/null +++ b/debian/patches/features/all/rt/arm-highmem-flush-tlb-on-unmap.patch @@ -0,0 +1,28 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 11 Mar 2013 21:37:27 +0100 +Subject: arm/highmem: Flush tlb on unmap +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The tlb should be flushed on unmap and thus make the mapping entry +invalid. This is only done in the non-debug case which does not look +right. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/mm/highmem.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/arm/mm/highmem.c ++++ b/arch/arm/mm/highmem.c +@@ -112,10 +112,10 @@ void __kunmap_atomic(void *kvaddr) + __cpuc_flush_dcache_area((void *)vaddr, PAGE_SIZE); + #ifdef CONFIG_DEBUG_HIGHMEM + BUG_ON(vaddr != __fix_to_virt(idx)); +- set_fixmap_pte(idx, __pte(0)); + #else + (void) idx; /* to kill a warning */ + #endif ++ set_fixmap_pte(idx, __pte(0)); + kmap_atomic_idx_pop(); + } else if (vaddr >= PKMAP_ADDR(0) && vaddr < PKMAP_ADDR(LAST_PKMAP)) { + /* this address was obtained through kmap_high_get() */ diff --git a/debian/patches/features/all/rt/arm-include-definition-for-cpumask_t.patch b/debian/patches/features/all/rt/arm-include-definition-for-cpumask_t.patch new file mode 100644 index 000000000..1a7a05e9f --- /dev/null +++ b/debian/patches/features/all/rt/arm-include-definition-for-cpumask_t.patch @@ -0,0 +1,25 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 22 Dec 2016 17:28:33 +0100 +Subject: [PATCH] arm: include definition for cpumask_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This definition gets pulled in by other files. With the (later) split of +RCU and spinlock.h it won't compile anymore. +The split is done in ("rbtree: don't include the rcu header"). + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/include/asm/irq.h | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/arch/arm/include/asm/irq.h ++++ b/arch/arm/include/asm/irq.h +@@ -23,6 +23,8 @@ + #endif + + #ifndef __ASSEMBLY__ ++#include ++ + struct irqaction; + struct pt_regs; + extern void migrate_irqs(void); diff --git a/debian/patches/features/all/rt/arm-kprobe-replace-patch_lock-to-raw-lock.patch b/debian/patches/features/all/rt/arm-kprobe-replace-patch_lock-to-raw-lock.patch new file mode 100644 index 000000000..b732003d0 --- /dev/null +++ b/debian/patches/features/all/rt/arm-kprobe-replace-patch_lock-to-raw-lock.patch @@ -0,0 +1,70 @@ +From: Yang Shi +Date: Thu, 10 Nov 2016 16:17:55 -0800 +Subject: [PATCH] arm: kprobe: replace patch_lock to raw lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When running kprobe on -rt kernel, the below bug is caught: + +BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 +in_atomic(): 1, irqs_disabled(): 128, pid: 14, name: migration/0 +INFO: lockdep is turned off. +irq event stamp: 238 +hardirqs last enabled at (237): [<80b5aecc>] _raw_spin_unlock_irqrestore+0x88/0x90 +hardirqs last disabled at (238): [<80b56d88>] __schedule+0xec/0x94c +softirqs last enabled at (0): [<80225584>] copy_process.part.5+0x30c/0x1994 +softirqs last disabled at (0): [< (null)>] (null) +Preemption disabled at:[<802f2b98>] cpu_stopper_thread+0xc0/0x140 + +CPU: 0 PID: 14 Comm: migration/0 Tainted: G O 4.8.3-rt2 #1 +Hardware name: Freescale LS1021A +[<80212e7c>] (unwind_backtrace) from [<8020cd2c>] (show_stack+0x20/0x24) +[<8020cd2c>] (show_stack) from [<80689e14>] (dump_stack+0xa0/0xcc) +[<80689e14>] (dump_stack) from [<8025a43c>] (___might_sleep+0x1b8/0x2a4) +[<8025a43c>] (___might_sleep) from [<80b5b324>] (rt_spin_lock+0x34/0x74) +[<80b5b324>] (rt_spin_lock) from [<80b5c31c>] (__patch_text_real+0x70/0xe8) +[<80b5c31c>] (__patch_text_real) from [<80b5c3ac>] (patch_text_stop_machine+0x18/0x20) +[<80b5c3ac>] (patch_text_stop_machine) from [<802f2920>] (multi_cpu_stop+0xfc/0x134) +[<802f2920>] (multi_cpu_stop) from [<802f2ba0>] (cpu_stopper_thread+0xc8/0x140) +[<802f2ba0>] (cpu_stopper_thread) from [<802563a4>] (smpboot_thread_fn+0x1a4/0x354) +[<802563a4>] (smpboot_thread_fn) from [<80251d38>] (kthread+0x104/0x11c) +[<80251d38>] (kthread) from [<80207f70>] (ret_from_fork+0x14/0x24) + +Since patch_text_stop_machine() is called in stop_machine() which disables IRQ, +sleepable lock should be not used in this atomic context, so replace patch_lock +to raw lock. + +Signed-off-by: Yang Shi +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/kernel/patch.c | 6 +++--- + 1 file changed, 3 insertions(+), 3 deletions(-) + +--- a/arch/arm/kernel/patch.c ++++ b/arch/arm/kernel/patch.c +@@ -16,7 +16,7 @@ struct patch { + unsigned int insn; + }; + +-static DEFINE_SPINLOCK(patch_lock); ++static DEFINE_RAW_SPINLOCK(patch_lock); + + static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) + __acquires(&patch_lock) +@@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *a + return addr; + + if (flags) +- spin_lock_irqsave(&patch_lock, *flags); ++ raw_spin_lock_irqsave(&patch_lock, *flags); + else + __acquire(&patch_lock); + +@@ -48,7 +48,7 @@ static void __kprobes patch_unmap(int fi + clear_fixmap(fixmap); + + if (flags) +- spin_unlock_irqrestore(&patch_lock, *flags); ++ raw_spin_unlock_irqrestore(&patch_lock, *flags); + else + __release(&patch_lock); + } diff --git a/debian/patches/features/all/rt/arm-preempt-lazy-support.patch b/debian/patches/features/all/rt/arm-preempt-lazy-support.patch new file mode 100644 index 000000000..881136bda --- /dev/null +++ b/debian/patches/features/all/rt/arm-preempt-lazy-support.patch @@ -0,0 +1,152 @@ +Subject: arm: Add support for lazy preemption +From: Thomas Gleixner +Date: Wed, 31 Oct 2012 12:04:11 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Implement the arm pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/arm/Kconfig | 1 + + arch/arm/include/asm/thread_info.h | 8 ++++++-- + arch/arm/kernel/asm-offsets.c | 1 + + arch/arm/kernel/entry-armv.S | 19 ++++++++++++++++--- + arch/arm/kernel/entry-common.S | 9 +++++++-- + arch/arm/kernel/signal.c | 3 ++- + 6 files changed, 33 insertions(+), 8 deletions(-) + +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -89,6 +89,7 @@ config ARM + select HAVE_PERF_EVENTS + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if (SMP && ARM_LPAE) + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RSEQ +--- a/arch/arm/include/asm/thread_info.h ++++ b/arch/arm/include/asm/thread_info.h +@@ -49,6 +49,7 @@ struct cpu_context_save { + struct thread_info { + unsigned long flags; /* low level flags */ + int preempt_count; /* 0 => preemptable, <0 => bug */ ++ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */ + mm_segment_t addr_limit; /* address limit */ + struct task_struct *task; /* main task structure */ + __u32 cpu; /* cpu */ +@@ -139,7 +140,8 @@ extern int vfp_restore_user_hwstate(stru + #define TIF_SYSCALL_TRACE 4 /* syscall trace active */ + #define TIF_SYSCALL_AUDIT 5 /* syscall auditing active */ + #define TIF_SYSCALL_TRACEPOINT 6 /* syscall tracepoint instrumentation */ +-#define TIF_SECCOMP 7 /* seccomp syscall filtering active */ ++#define TIF_SECCOMP 8 /* seccomp syscall filtering active */ ++#define TIF_NEED_RESCHED_LAZY 7 + + #define TIF_NOHZ 12 /* in adaptive nohz mode */ + #define TIF_USING_IWMMXT 17 +@@ -149,6 +151,7 @@ extern int vfp_restore_user_hwstate(stru + #define _TIF_SIGPENDING (1 << TIF_SIGPENDING) + #define _TIF_NEED_RESCHED (1 << TIF_NEED_RESCHED) + #define _TIF_NOTIFY_RESUME (1 << TIF_NOTIFY_RESUME) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) +@@ -164,7 +167,8 @@ extern int vfp_restore_user_hwstate(stru + * Change these and you break ASM code in entry-common.S + */ + #define _TIF_WORK_MASK (_TIF_NEED_RESCHED | _TIF_SIGPENDING | \ +- _TIF_NOTIFY_RESUME | _TIF_UPROBE) ++ _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ ++ _TIF_NEED_RESCHED_LAZY) + + #endif /* __KERNEL__ */ + #endif /* __ASM_ARM_THREAD_INFO_H */ +--- a/arch/arm/kernel/asm-offsets.c ++++ b/arch/arm/kernel/asm-offsets.c +@@ -67,6 +67,7 @@ int main(void) + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); ++ DEFINE(TI_PREEMPT_LAZY, offsetof(struct thread_info, preempt_lazy_count)); + DEFINE(TI_ADDR_LIMIT, offsetof(struct thread_info, addr_limit)); + DEFINE(TI_TASK, offsetof(struct thread_info, task)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); +--- a/arch/arm/kernel/entry-armv.S ++++ b/arch/arm/kernel/entry-armv.S +@@ -216,11 +216,18 @@ ENDPROC(__dabt_svc) + + #ifdef CONFIG_PREEMPT + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count +- ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 ++ bne 1f @ return from exeption ++ ldr r0, [tsk, #TI_FLAGS] @ get flags ++ tst r0, #_TIF_NEED_RESCHED @ if NEED_RESCHED is set ++ blne svc_preempt @ preempt! ++ ++ ldr r8, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r8, #0 @ if preempt lazy count != 0 + movne r0, #0 @ force flags to 0 +- tst r0, #_TIF_NEED_RESCHED ++ tst r0, #_TIF_NEED_RESCHED_LAZY + blne svc_preempt ++1: + #endif + + svc_exit r5, irq = 1 @ return from exception +@@ -235,8 +242,14 @@ ENDPROC(__irq_svc) + 1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED ++ bne 1b ++ tst r0, #_TIF_NEED_RESCHED_LAZY + reteq r8 @ go again +- b 1b ++ ldr r0, [tsk, #TI_PREEMPT_LAZY] @ get preempt lazy count ++ teq r0, #0 @ if preempt lazy count != 0 ++ beq 1b ++ ret r8 @ go again ++ + #endif + + __und_fault: +--- a/arch/arm/kernel/entry-common.S ++++ b/arch/arm/kernel/entry-common.S +@@ -56,7 +56,9 @@ saved_pc .req lr + cmp r2, #TASK_SIZE + blne addr_limit_check_failed + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne fast_work_pending ++ tst r1, #_TIF_SECCOMP + bne fast_work_pending + + +@@ -93,8 +95,11 @@ ENDPROC(ret_fast_syscall) + cmp r2, #TASK_SIZE + blne addr_limit_check_failed + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing +- tst r1, #_TIF_SYSCALL_WORK | _TIF_WORK_MASK ++ tst r1, #((_TIF_SYSCALL_WORK | _TIF_WORK_MASK) & ~_TIF_SECCOMP) ++ bne do_slower_path ++ tst r1, #_TIF_SECCOMP + beq no_work_pending ++do_slower_path: + UNWIND(.fnend ) + ENDPROC(ret_fast_syscall) + +--- a/arch/arm/kernel/signal.c ++++ b/arch/arm/kernel/signal.c +@@ -644,7 +644,8 @@ do_work_pending(struct pt_regs *regs, un + */ + trace_hardirqs_off(); + do { +- if (likely(thread_flags & _TIF_NEED_RESCHED)) { ++ if (likely(thread_flags & (_TIF_NEED_RESCHED | ++ _TIF_NEED_RESCHED_LAZY))) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) diff --git a/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch b/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch new file mode 100644 index 000000000..732e5b01c --- /dev/null +++ b/debian/patches/features/all/rt/arm-unwind-use_raw_lock.patch @@ -0,0 +1,84 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 20 Sep 2013 14:31:54 +0200 +Subject: arm/unwind: use a raw_spin_lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Mostly unwind is done with irqs enabled however SLUB may call it with +irqs disabled while creating a new SLUB cache. + +I had system freeze while loading a module which called +kmem_cache_create() on init. That means SLUB's __slab_alloc() disabled +interrupts and then + +->new_slab_objects() + ->new_slab() + ->setup_object() + ->setup_object_debug() + ->init_tracking() + ->set_track() + ->save_stack_trace() + ->save_stack_trace_tsk() + ->walk_stackframe() + ->unwind_frame() + ->unwind_find_idx() + =>spin_lock_irqsave(&unwind_lock); + + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/kernel/unwind.c | 14 +++++++------- + 1 file changed, 7 insertions(+), 7 deletions(-) + +--- a/arch/arm/kernel/unwind.c ++++ b/arch/arm/kernel/unwind.c +@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_u + static const struct unwind_idx *__origin_unwind_idx; + extern const struct unwind_idx __stop_unwind_idx[]; + +-static DEFINE_SPINLOCK(unwind_lock); ++static DEFINE_RAW_SPINLOCK(unwind_lock); + static LIST_HEAD(unwind_tables); + + /* Convert a prel31 symbol to an absolute address */ +@@ -201,7 +201,7 @@ static const struct unwind_idx *unwind_f + /* module unwind tables */ + struct unwind_table *table; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_for_each_entry(table, &unwind_tables, list) { + if (addr >= table->begin_addr && + addr < table->end_addr) { +@@ -213,7 +213,7 @@ static const struct unwind_idx *unwind_f + break; + } + } +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); +@@ -529,9 +529,9 @@ struct unwind_table *unwind_table_add(un + tab->begin_addr = text_addr; + tab->end_addr = text_addr + text_size; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_add_tail(&tab->list, &unwind_tables); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + return tab; + } +@@ -543,9 +543,9 @@ void unwind_table_del(struct unwind_tabl + if (!tab) + return; + +- spin_lock_irqsave(&unwind_lock, flags); ++ raw_spin_lock_irqsave(&unwind_lock, flags); + list_del(&tab->list); +- spin_unlock_irqrestore(&unwind_lock, flags); ++ raw_spin_unlock_irqrestore(&unwind_lock, flags); + + kfree(tab); + } diff --git a/debian/patches/features/all/rt/arm64-KVM-compute_layout-before-altenates-are-applie.patch b/debian/patches/features/all/rt/arm64-KVM-compute_layout-before-altenates-are-applie.patch new file mode 100644 index 000000000..f436a4a0a --- /dev/null +++ b/debian/patches/features/all/rt/arm64-KVM-compute_layout-before-altenates-are-applie.patch @@ -0,0 +1,72 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 26 Jul 2018 09:13:42 +0200 +Subject: [PATCH] arm64: KVM: compute_layout before altenates are applied +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +compute_layout() is invoked as part of an alternative fixup under +stop_machine() and needs a sleeping lock as part of get_random_long(). + +Invoke compute_layout() before the alternatives are applied. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm64/include/asm/alternative.h | 6 ++++++ + arch/arm64/kernel/alternative.c | 1 + + arch/arm64/kvm/va_layout.c | 7 +------ + 3 files changed, 8 insertions(+), 6 deletions(-) + +--- a/arch/arm64/include/asm/alternative.h ++++ b/arch/arm64/include/asm/alternative.h +@@ -35,6 +35,12 @@ void apply_alternatives_module(void *sta + static inline void apply_alternatives_module(void *start, size_t length) { } + #endif + ++#ifdef CONFIG_KVM_ARM_HOST ++void kvm_compute_layout(void); ++#else ++static inline void kvm_compute_layout(void) { } ++#endif ++ + #define ALTINSTR_ENTRY(feature,cb) \ + " .word 661b - .\n" /* label */ \ + " .if " __stringify(cb) " == 0\n" \ +--- a/arch/arm64/kernel/alternative.c ++++ b/arch/arm64/kernel/alternative.c +@@ -224,6 +224,7 @@ static int __apply_alternatives_multi_st + void __init apply_alternatives_all(void) + { + /* better not try code patching on a live SMP system */ ++ kvm_compute_layout(); + stop_machine(__apply_alternatives_multi_stop, NULL, cpu_online_mask); + } + +--- a/arch/arm64/kvm/va_layout.c ++++ b/arch/arm64/kvm/va_layout.c +@@ -33,7 +33,7 @@ static u8 tag_lsb; + static u64 tag_val; + static u64 va_mask; + +-static void compute_layout(void) ++__init void kvm_compute_layout(void) + { + phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start); + u64 hyp_va_msb; +@@ -121,8 +121,6 @@ void __init kvm_update_va_mask(struct al + + BUG_ON(nr_inst != 5); + +- if (!has_vhe() && !va_mask) +- compute_layout(); + + for (i = 0; i < nr_inst; i++) { + u32 rd, rn, insn, oinsn; +@@ -167,9 +165,6 @@ void kvm_patch_vector_branch(struct alt_ + return; + } + +- if (!va_mask) +- compute_layout(); +- + /* + * Compute HYP VA by using the same computation as kern_hyp_va() + */ diff --git a/debian/patches/features/all/rt/arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch b/debian/patches/features/all/rt/arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch new file mode 100644 index 000000000..8483fca11 --- /dev/null +++ b/debian/patches/features/all/rt/arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch @@ -0,0 +1,165 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 25 Jul 2018 14:02:38 +0200 +Subject: [PATCH] arm64: fpsimd: use preemp_disable in addition to + local_bh_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In v4.16-RT I noticed a number of warnings from task_fpsimd_load(). The +code disables BH and expects that it is not preemptible. On -RT the +task remains preemptible but remains the same CPU. This may corrupt the +content of the SIMD registers if the task is preempted during +saving/restoring those registers. + +Add preempt_disable()/enable() to enfore the required semantic on -RT. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm64/kernel/fpsimd.c | 31 +++++++++++++++++++++++++++++-- + 1 file changed, 29 insertions(+), 2 deletions(-) + +--- a/arch/arm64/kernel/fpsimd.c ++++ b/arch/arm64/kernel/fpsimd.c +@@ -159,6 +159,16 @@ static void sve_free(struct task_struct + __sve_free(task); + } + ++static void *sve_free_atomic(struct task_struct *task) ++{ ++ void *sve_state = task->thread.sve_state; ++ ++ WARN_ON(test_tsk_thread_flag(task, TIF_SVE)); ++ ++ task->thread.sve_state = NULL; ++ return sve_state; ++} ++ + static void change_cpacr(u64 val, u64 mask) + { + u64 cpacr = read_sysreg(CPACR_EL1); +@@ -566,6 +576,7 @@ int sve_set_vector_length(struct task_st + * non-SVE thread. + */ + if (task == current) { ++ preempt_disable(); + local_bh_disable(); + + fpsimd_save(); +@@ -576,8 +587,10 @@ int sve_set_vector_length(struct task_st + if (test_and_clear_tsk_thread_flag(task, TIF_SVE)) + sve_to_fpsimd(task); + +- if (task == current) ++ if (task == current) { + local_bh_enable(); ++ preempt_enable(); ++ } + + /* + * Force reallocation of task SVE state to the correct size +@@ -832,6 +845,7 @@ asmlinkage void do_sve_acc(unsigned int + + sve_alloc(current); + ++ preempt_disable(); + local_bh_disable(); + + fpsimd_save(); +@@ -845,6 +859,7 @@ asmlinkage void do_sve_acc(unsigned int + WARN_ON(1); /* SVE access shouldn't have trapped */ + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -911,10 +926,12 @@ void fpsimd_thread_switch(struct task_st + void fpsimd_flush_thread(void) + { + int vl, supported_vl; ++ void *mem = NULL; + + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + + memset(¤t->thread.uw.fpsimd_state, 0, +@@ -923,7 +940,7 @@ void fpsimd_flush_thread(void) + + if (system_supports_sve()) { + clear_thread_flag(TIF_SVE); +- sve_free(current); ++ mem = sve_free_atomic(current); + + /* + * Reset the task vector length as required. +@@ -959,6 +976,8 @@ void fpsimd_flush_thread(void) + set_thread_flag(TIF_FOREIGN_FPSTATE); + + local_bh_enable(); ++ preempt_enable(); ++ kfree(mem); + } + + /* +@@ -970,9 +989,11 @@ void fpsimd_preserve_current_state(void) + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + fpsimd_save(); + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1030,6 +1051,7 @@ void fpsimd_restore_current_state(void) + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + + if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) { +@@ -1038,6 +1060,7 @@ void fpsimd_restore_current_state(void) + } + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1050,6 +1073,7 @@ void fpsimd_update_current_state(struct + if (!system_supports_fpsimd()) + return; + ++ preempt_disable(); + local_bh_disable(); + + current->thread.uw.fpsimd_state = *state; +@@ -1062,6 +1086,7 @@ void fpsimd_update_current_state(struct + clear_thread_flag(TIF_FOREIGN_FPSTATE); + + local_bh_enable(); ++ preempt_enable(); + } + + /* +@@ -1107,6 +1132,7 @@ void kernel_neon_begin(void) + + BUG_ON(!may_use_simd()); + ++ preempt_disable(); + local_bh_disable(); + + __this_cpu_write(kernel_neon_busy, true); +@@ -1120,6 +1146,7 @@ void kernel_neon_begin(void) + preempt_disable(); + + local_bh_enable(); ++ preempt_enable(); + } + EXPORT_SYMBOL(kernel_neon_begin); + diff --git a/debian/patches/features/all/rt/at91_dont_enable_disable_clock.patch b/debian/patches/features/all/rt/at91_dont_enable_disable_clock.patch new file mode 100644 index 000000000..8b44990f2 --- /dev/null +++ b/debian/patches/features/all/rt/at91_dont_enable_disable_clock.patch @@ -0,0 +1,92 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 09 Mar 2016 10:51:06 +0100 +Subject: arm: at91: do not disable/enable clocks in a row +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Currently the driver will disable the clock and enable it one line later +if it is switching from periodic mode into one shot. +This can be avoided and causes a needless warning on -RT. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/clocksource/tcb_clksrc.c | 33 +++++++++++++++++++++++++++++---- + 1 file changed, 29 insertions(+), 4 deletions(-) + +--- a/drivers/clocksource/tcb_clksrc.c ++++ b/drivers/clocksource/tcb_clksrc.c +@@ -126,6 +126,7 @@ static struct clocksource clksrc = { + struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; ++ bool clk_enabled; + void __iomem *regs; + }; + +@@ -143,6 +144,24 @@ static struct tc_clkevt_device *to_tc_cl + */ + static u32 timer_clock; + ++static void tc_clk_disable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ clk_disable(tcd->clk); ++ tcd->clk_enabled = false; ++} ++ ++static void tc_clk_enable(struct clock_event_device *d) ++{ ++ struct tc_clkevt_device *tcd = to_tc_clkevt(d); ++ ++ if (tcd->clk_enabled) ++ return; ++ clk_enable(tcd->clk); ++ tcd->clk_enabled = true; ++} ++ + static int tc_shutdown(struct clock_event_device *d) + { + struct tc_clkevt_device *tcd = to_tc_clkevt(d); +@@ -150,8 +169,14 @@ static int tc_shutdown(struct clock_even + + writel(0xff, regs + ATMEL_TC_REG(2, IDR)); + writel(ATMEL_TC_CLKDIS, regs + ATMEL_TC_REG(2, CCR)); ++ return 0; ++} ++ ++static int tc_shutdown_clk_off(struct clock_event_device *d) ++{ ++ tc_shutdown(d); + if (!clockevent_state_detached(d)) +- clk_disable(tcd->clk); ++ tc_clk_disable(d); + + return 0; + } +@@ -164,7 +189,7 @@ static int tc_set_oneshot(struct clock_e + if (clockevent_state_oneshot(d) || clockevent_state_periodic(d)) + tc_shutdown(d); + +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + + /* slow clock, count up to RC, then irq and stop */ + writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | +@@ -186,7 +211,7 @@ static int tc_set_periodic(struct clock_ + /* By not making the gentime core emulate periodic mode on top + * of oneshot, we get lower overhead and improved accuracy. + */ +- clk_enable(tcd->clk); ++ tc_clk_enable(d); + + /* slow clock, count up to RC, then irq and restart */ + writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, +@@ -220,7 +245,7 @@ static struct tc_clkevt_device clkevt = + /* Should be lower than at91rm9200's system timer */ + .rating = 125, + .set_next_event = tc_next_event, +- .set_state_shutdown = tc_shutdown, ++ .set_state_shutdown = tc_shutdown_clk_off, + .set_state_periodic = tc_set_periodic, + .set_state_oneshot = tc_set_oneshot, + }, diff --git a/debian/patches/features/all/rt/block-blk-mq-move-blk_queue_usage_counter_release-in.patch b/debian/patches/features/all/rt/block-blk-mq-move-blk_queue_usage_counter_release-in.patch new file mode 100644 index 000000000..89e6adb75 --- /dev/null +++ b/debian/patches/features/all/rt/block-blk-mq-move-blk_queue_usage_counter_release-in.patch @@ -0,0 +1,112 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 13 Mar 2018 13:49:16 +0100 +Subject: [PATCH] block: blk-mq: move blk_queue_usage_counter_release() + into process context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +| in_atomic(): 1, irqs_disabled(): 0, pid: 255, name: kworker/u257:6 +| 5 locks held by kworker/u257:6/255: +| #0: ("events_unbound"){.+.+.+}, at: [] process_one_work+0x171/0x5e0 +| #1: ((&entry->work)){+.+.+.}, at: [] process_one_work+0x171/0x5e0 +| #2: (&shost->scan_mutex){+.+.+.}, at: [] __scsi_add_device+0xa3/0x130 [scsi_mod] +| #3: (&set->tag_list_lock){+.+...}, at: [] blk_mq_init_queue+0x96a/0xa50 +| #4: (rcu_read_lock_sched){......}, at: [] percpu_ref_kill_and_confirm+0x1d/0x120 +| Preemption disabled at:[] blk_mq_freeze_queue_start+0x56/0x70 +| +| CPU: 2 PID: 255 Comm: kworker/u257:6 Not tainted 3.18.7-rt0+ #1 +| Workqueue: events_unbound async_run_entry_fn +| 0000000000000003 ffff8800bc29f998 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff8800bc29f9b8 ffffffff8109aa16 ffff8800bc29fa28 +| ffff8800bc5d1bc8 ffff8800bc29f9e8 ffffffff815b8dd4 ffff880000000000 +| Call Trace: +| [] dump_stack+0x4f/0x7c +| [] __might_sleep+0x116/0x190 +| [] rt_spin_lock+0x24/0x60 +| [] __wake_up+0x29/0x60 +| [] blk_mq_usage_counter_release+0x1e/0x20 +| [] percpu_ref_kill_and_confirm+0x106/0x120 +| [] blk_mq_freeze_queue_start+0x56/0x70 +| [] blk_mq_update_tag_set_depth+0x40/0xd0 +| [] blk_mq_init_queue+0x98c/0xa50 +| [] scsi_mq_alloc_queue+0x20/0x60 [scsi_mod] +| [] scsi_alloc_sdev+0x2f5/0x370 [scsi_mod] +| [] scsi_probe_and_add_lun+0x9e4/0xdd0 [scsi_mod] +| [] __scsi_add_device+0x126/0x130 [scsi_mod] +| [] ata_scsi_scan_host+0xaf/0x200 [libata] +| [] async_port_probe+0x46/0x60 [libata] +| [] async_run_entry_fn+0x3b/0xf0 +| [] process_one_work+0x201/0x5e0 + +percpu_ref_kill_and_confirm() invokes blk_mq_usage_counter_release() in +a rcu-sched region. swait based wake queue can't be used due to +wake_up_all() usage and disabled interrupts in !RT configs (as reported +by Corey Minyard). +The wq_has_sleeper() check has been suggested by Peter Zijlstra. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-core.c | 14 +++++++++++++- + include/linux/blkdev.h | 2 ++ + 2 files changed, 15 insertions(+), 1 deletion(-) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -959,12 +959,21 @@ void blk_queue_exit(struct request_queue + percpu_ref_put(&q->q_usage_counter); + } + ++static void blk_queue_usage_counter_release_swork(struct swork_event *sev) ++{ ++ struct request_queue *q = ++ container_of(sev, struct request_queue, mq_pcpu_wake); ++ ++ wake_up_all(&q->mq_freeze_wq); ++} ++ + static void blk_queue_usage_counter_release(struct percpu_ref *ref) + { + struct request_queue *q = + container_of(ref, struct request_queue, q_usage_counter); + +- wake_up_all(&q->mq_freeze_wq); ++ if (wq_has_sleeper(&q->mq_freeze_wq)) ++ swork_queue(&q->mq_pcpu_wake); + } + + static void blk_rq_timed_out_timer(struct timer_list *t) +@@ -1058,6 +1067,7 @@ struct request_queue *blk_alloc_queue_no + queue_flag_set_unlocked(QUEUE_FLAG_BYPASS, q); + + init_waitqueue_head(&q->mq_freeze_wq); ++ INIT_SWORK(&q->mq_pcpu_wake, blk_queue_usage_counter_release_swork); + + /* + * Init percpu_ref in atomic mode so that it's faster to shutdown. +@@ -3939,6 +3949,8 @@ int __init blk_dev_init(void) + if (!kblockd_workqueue) + panic("Failed to create kblockd\n"); + ++ BUG_ON(swork_get()); ++ + request_cachep = kmem_cache_create("blkdev_requests", + sizeof(struct request), 0, SLAB_PANIC, NULL); + +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -27,6 +27,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -651,6 +652,7 @@ struct request_queue { + #endif + struct rcu_head rcu_head; + wait_queue_head_t mq_freeze_wq; ++ struct swork_event mq_pcpu_wake; + struct percpu_ref q_usage_counter; + struct list_head all_q_node; + diff --git a/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch b/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch new file mode 100644 index 000000000..2c1add2f3 --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch @@ -0,0 +1,107 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Jan 2015 15:10:08 +0100 +Subject: block/mq: don't complete requests via IPI +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The IPI runs in hardirq context and there are sleeping locks. This patch +moves the completion into a workqueue. + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-core.c | 3 +++ + block/blk-mq.c | 23 +++++++++++++++++++++++ + include/linux/blk-mq.h | 2 +- + include/linux/blkdev.h | 3 +++ + 4 files changed, 30 insertions(+), 1 deletion(-) + +--- a/block/blk-core.c ++++ b/block/blk-core.c +@@ -189,6 +189,9 @@ void blk_rq_init(struct request_queue *q + + INIT_LIST_HEAD(&rq->queuelist); + INIT_LIST_HEAD(&rq->timeout_list); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + rq->cpu = -1; + rq->q = q; + rq->__sector = (sector_t) -1; +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -320,6 +320,9 @@ static struct request *blk_mq_rq_ctx_ini + rq->extra_len = 0; + rq->__deadline = 0; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ INIT_WORK(&rq->work, __blk_mq_complete_request_remote_work); ++#endif + INIT_LIST_HEAD(&rq->timeout_list); + rq->timeout = 0; + +@@ -545,12 +548,24 @@ void blk_mq_end_request(struct request * + } + EXPORT_SYMBOL(blk_mq_end_request); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++void __blk_mq_complete_request_remote_work(struct work_struct *work) ++{ ++ struct request *rq = container_of(work, struct request, work); ++ ++ rq->q->softirq_done_fn(rq); ++} ++ ++#else ++ + static void __blk_mq_complete_request_remote(void *data) + { + struct request *rq = data; + + rq->q->softirq_done_fn(rq); + } ++#endif + + static void __blk_mq_complete_request(struct request *rq) + { +@@ -573,10 +588,18 @@ static void __blk_mq_complete_request(st + shared = cpus_share_cache(cpu, ctx->cpu); + + if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * We could force QUEUE_FLAG_SAME_FORCE then we would not get in ++ * here. But we could try to invoke it one the CPU like this. ++ */ ++ schedule_work_on(ctx->cpu, &rq->work); ++#else + rq->csd.func = __blk_mq_complete_request_remote; + rq->csd.info = rq; + rq->csd.flags = 0; + smp_call_function_single_async(ctx->cpu, &rq->csd); ++#endif + } else { + rq->q->softirq_done_fn(rq); + } +--- a/include/linux/blk-mq.h ++++ b/include/linux/blk-mq.h +@@ -247,7 +247,7 @@ static inline u16 blk_mq_unique_tag_to_t + return unique_tag & BLK_MQ_UNIQUE_TAG_MASK; + } + +- ++void __blk_mq_complete_request_remote_work(struct work_struct *work); + int blk_mq_request_started(struct request *rq); + void blk_mq_start_request(struct request *rq); + void blk_mq_end_request(struct request *rq, blk_status_t error); +--- a/include/linux/blkdev.h ++++ b/include/linux/blkdev.h +@@ -151,6 +151,9 @@ enum mq_rq_state { + */ + struct request { + struct request_queue *q; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct work_struct work; ++#endif + struct blk_mq_ctx *mq_ctx; + + int cpu; diff --git a/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch b/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch new file mode 100644 index 000000000..70fc350aa --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-drop-preempt-disable.patch @@ -0,0 +1,52 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: block/mq: do not invoke preempt_disable() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +preempt_disable() and get_cpu() don't play well together with the sleeping +locks it tries to allocate later. +It seems to be enough to replace it with get_cpu_light() and migrate_disable(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.c | 10 +++++----- + 1 file changed, 5 insertions(+), 5 deletions(-) + +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -568,7 +568,7 @@ static void __blk_mq_complete_request(st + return; + } + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + if (!test_bit(QUEUE_FLAG_SAME_FORCE, &rq->q->queue_flags)) + shared = cpus_share_cache(cpu, ctx->cpu); + +@@ -580,7 +580,7 @@ static void __blk_mq_complete_request(st + } else { + rq->q->softirq_done_fn(rq); + } +- put_cpu(); ++ put_cpu_light(); + } + + static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx) +@@ -1324,14 +1324,14 @@ static void __blk_mq_delay_run_hw_queue( + return; + + if (!async && !(hctx->flags & BLK_MQ_F_BLOCKING)) { +- int cpu = get_cpu(); ++ int cpu = get_cpu_light(); + if (cpumask_test_cpu(cpu, hctx->cpumask)) { + __blk_mq_run_hw_queue(hctx); +- put_cpu(); ++ put_cpu_light(); + return; + } + +- put_cpu(); ++ put_cpu_light(); + } + + kblockd_mod_delayed_work_on(blk_mq_hctx_next_cpu(hctx), &hctx->run_work, diff --git a/debian/patches/features/all/rt/block-mq-use-cpu_light.patch b/debian/patches/features/all/rt/block-mq-use-cpu_light.patch new file mode 100644 index 000000000..a0eadcb0b --- /dev/null +++ b/debian/patches/features/all/rt/block-mq-use-cpu_light.patch @@ -0,0 +1,30 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 9 Apr 2014 10:37:23 +0200 +Subject: block: mq: use cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +there is a might sleep splat because get_cpu() disables preemption and +later we grab a lock. As a workaround for this we use get_cpu_light(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.h | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/block/blk-mq.h ++++ b/block/blk-mq.h +@@ -112,12 +112,12 @@ static inline struct blk_mq_ctx *__blk_m + */ + static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q) + { +- return __blk_mq_get_ctx(q, get_cpu()); ++ return __blk_mq_get_ctx(q, get_cpu_light()); + } + + static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx) + { +- put_cpu(); ++ put_cpu_light(); + } + + struct blk_mq_alloc_data { diff --git a/debian/patches/features/all/rt/block-use-cpu-chill.patch b/debian/patches/features/all/rt/block-use-cpu-chill.patch new file mode 100644 index 000000000..7ee2bc305 --- /dev/null +++ b/debian/patches/features/all/rt/block-use-cpu-chill.patch @@ -0,0 +1,46 @@ +Subject: block: Use cpu_chill() for retry loops +From: Thomas Gleixner +Date: Thu, 20 Dec 2012 18:28:26 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Steven also observed a live lock when there was a +concurrent priority boosting going on. + +Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + block/blk-ioc.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/block/blk-ioc.c ++++ b/block/blk-ioc.c +@@ -9,6 +9,7 @@ + #include + #include + #include ++#include + + #include "blk.h" + +@@ -118,7 +119,7 @@ static void ioc_release_fn(struct work_s + spin_unlock(q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + spin_lock_irqsave_nested(&ioc->lock, flags, 1); + } + } +@@ -202,7 +203,7 @@ void put_io_context_active(struct io_con + spin_unlock(icq->q->queue_lock); + } else { + spin_unlock_irqrestore(&ioc->lock, flags); +- cpu_relax(); ++ cpu_chill(); + goto retry; + } + } diff --git a/debian/patches/features/all/rt/cgroup-tracing-Move-taking-of-spin-lock-out-of-trace.patch b/debian/patches/features/all/rt/cgroup-tracing-Move-taking-of-spin-lock-out-of-trace.patch new file mode 100644 index 000000000..fa982ad18 --- /dev/null +++ b/debian/patches/features/all/rt/cgroup-tracing-Move-taking-of-spin-lock-out-of-trace.patch @@ -0,0 +1,271 @@ +From: "Steven Rostedt (VMware)" +Date: Mon, 9 Jul 2018 17:48:54 -0400 +Subject: [PATCH] cgroup/tracing: Move taking of spin lock out of trace event + handlers +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +[ Upstream commit e4f8d81c738db6d3ffdabfb8329aa2feaa310699 ] + +It is unwise to take spin locks from the handlers of trace events. +Mainly, because they can introduce lockups, because it introduces locks +in places that are normally not tested. Worse yet, because trace events +are tucked away in the include/trace/events/ directory, locks that are +taken there are forgotten about. + +As a general rule, I tell people never to take any locks in a trace +event handler. + +Several cgroup trace event handlers call cgroup_path() which eventually +takes the kernfs_rename_lock spinlock. This injects the spinlock in the +code without people realizing it. It also can cause issues for the +PREEMPT_RT patch, as the spinlock becomes a mutex, and the trace event +handlers are called with preemption disabled. + +By moving the calculation of the cgroup_path() out of the trace event +handlers and into a macro (surrounded by a +trace_cgroup_##type##_enabled()), then we could place the cgroup_path +into a string, and pass that to the trace event. Not only does this +remove the taking of the spinlock out of the trace event handler, but +it also means that the cgroup_path() only needs to be called once (it +is currently called twice, once to get the length to reserver the +buffer for, and once again to get the path itself. Now it only needs to +be done once. + +Reported-by: Sebastian Andrzej Siewior +Signed-off-by: Steven Rostedt (VMware) +Signed-off-by: Tejun Heo +Signed-off-by: Sebastian Andrzej Siewior +--- + include/trace/events/cgroup.h | 47 +++++++++++++++++++--------------------- + kernel/cgroup/cgroup-internal.h | 26 ++++++++++++++++++++++ + kernel/cgroup/cgroup-v1.c | 4 +-- + kernel/cgroup/cgroup.c | 12 +++++----- + 4 files changed, 58 insertions(+), 31 deletions(-) + +--- a/include/trace/events/cgroup.h ++++ b/include/trace/events/cgroup.h +@@ -53,24 +53,22 @@ DEFINE_EVENT(cgroup_root, cgroup_remount + + DECLARE_EVENT_CLASS(cgroup, + +- TP_PROTO(struct cgroup *cgrp), ++ TP_PROTO(struct cgroup *cgrp, const char *path), + +- TP_ARGS(cgrp), ++ TP_ARGS(cgrp, path), + + TP_STRUCT__entry( + __field( int, root ) + __field( int, id ) + __field( int, level ) +- __dynamic_array(char, path, +- cgroup_path(cgrp, NULL, 0) + 1) ++ __string( path, path ) + ), + + TP_fast_assign( + __entry->root = cgrp->root->hierarchy_id; + __entry->id = cgrp->id; + __entry->level = cgrp->level; +- cgroup_path(cgrp, __get_dynamic_array(path), +- __get_dynamic_array_len(path)); ++ __assign_str(path, path); + ), + + TP_printk("root=%d id=%d level=%d path=%s", +@@ -79,45 +77,45 @@ DECLARE_EVENT_CLASS(cgroup, + + DEFINE_EVENT(cgroup, cgroup_mkdir, + +- TP_PROTO(struct cgroup *cgroup), ++ TP_PROTO(struct cgroup *cgrp, const char *path), + +- TP_ARGS(cgroup) ++ TP_ARGS(cgrp, path) + ); + + DEFINE_EVENT(cgroup, cgroup_rmdir, + +- TP_PROTO(struct cgroup *cgroup), ++ TP_PROTO(struct cgroup *cgrp, const char *path), + +- TP_ARGS(cgroup) ++ TP_ARGS(cgrp, path) + ); + + DEFINE_EVENT(cgroup, cgroup_release, + +- TP_PROTO(struct cgroup *cgroup), ++ TP_PROTO(struct cgroup *cgrp, const char *path), + +- TP_ARGS(cgroup) ++ TP_ARGS(cgrp, path) + ); + + DEFINE_EVENT(cgroup, cgroup_rename, + +- TP_PROTO(struct cgroup *cgroup), ++ TP_PROTO(struct cgroup *cgrp, const char *path), + +- TP_ARGS(cgroup) ++ TP_ARGS(cgrp, path) + ); + + DECLARE_EVENT_CLASS(cgroup_migrate, + +- TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), ++ TP_PROTO(struct cgroup *dst_cgrp, const char *path, ++ struct task_struct *task, bool threadgroup), + +- TP_ARGS(dst_cgrp, task, threadgroup), ++ TP_ARGS(dst_cgrp, path, task, threadgroup), + + TP_STRUCT__entry( + __field( int, dst_root ) + __field( int, dst_id ) + __field( int, dst_level ) +- __dynamic_array(char, dst_path, +- cgroup_path(dst_cgrp, NULL, 0) + 1) + __field( int, pid ) ++ __string( dst_path, path ) + __string( comm, task->comm ) + ), + +@@ -125,8 +123,7 @@ DECLARE_EVENT_CLASS(cgroup_migrate, + __entry->dst_root = dst_cgrp->root->hierarchy_id; + __entry->dst_id = dst_cgrp->id; + __entry->dst_level = dst_cgrp->level; +- cgroup_path(dst_cgrp, __get_dynamic_array(dst_path), +- __get_dynamic_array_len(dst_path)); ++ __assign_str(dst_path, path); + __entry->pid = task->pid; + __assign_str(comm, task->comm); + ), +@@ -138,16 +135,18 @@ DECLARE_EVENT_CLASS(cgroup_migrate, + + DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, + +- TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), ++ TP_PROTO(struct cgroup *dst_cgrp, const char *path, ++ struct task_struct *task, bool threadgroup), + +- TP_ARGS(dst_cgrp, task, threadgroup) ++ TP_ARGS(dst_cgrp, path, task, threadgroup) + ); + + DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, + +- TP_PROTO(struct cgroup *dst_cgrp, struct task_struct *task, bool threadgroup), ++ TP_PROTO(struct cgroup *dst_cgrp, const char *path, ++ struct task_struct *task, bool threadgroup), + +- TP_ARGS(dst_cgrp, task, threadgroup) ++ TP_ARGS(dst_cgrp, path, task, threadgroup) + ); + + #endif /* _TRACE_CGROUP_H */ +--- a/kernel/cgroup/cgroup-internal.h ++++ b/kernel/cgroup/cgroup-internal.h +@@ -8,6 +8,32 @@ + #include + #include + ++#define TRACE_CGROUP_PATH_LEN 1024 ++extern spinlock_t trace_cgroup_path_lock; ++extern char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; ++ ++/* ++ * cgroup_path() takes a spin lock. It is good practice not to take ++ * spin locks within trace point handlers, as they are mostly hidden ++ * from normal view. As cgroup_path() can take the kernfs_rename_lock ++ * spin lock, it is best to not call that function from the trace event ++ * handler. ++ * ++ * Note: trace_cgroup_##type##_enabled() is a static branch that will only ++ * be set when the trace event is enabled. ++ */ ++#define TRACE_CGROUP_PATH(type, cgrp, ...) \ ++ do { \ ++ if (trace_cgroup_##type##_enabled()) { \ ++ spin_lock(&trace_cgroup_path_lock); \ ++ cgroup_path(cgrp, trace_cgroup_path, \ ++ TRACE_CGROUP_PATH_LEN); \ ++ trace_cgroup_##type(cgrp, trace_cgroup_path, \ ++ ##__VA_ARGS__); \ ++ spin_unlock(&trace_cgroup_path_lock); \ ++ } \ ++ } while (0) ++ + /* + * A cgroup can be associated with multiple css_sets as different tasks may + * belong to different cgroups on different hierarchies. In the other +--- a/kernel/cgroup/cgroup-v1.c ++++ b/kernel/cgroup/cgroup-v1.c +@@ -135,7 +135,7 @@ int cgroup_transfer_tasks(struct cgroup + if (task) { + ret = cgroup_migrate(task, false, &mgctx); + if (!ret) +- trace_cgroup_transfer_tasks(to, task, false); ++ TRACE_CGROUP_PATH(transfer_tasks, to, task, false); + put_task_struct(task); + } + } while (task && !ret); +@@ -865,7 +865,7 @@ static int cgroup1_rename(struct kernfs_ + + ret = kernfs_rename(kn, new_parent, new_name_str); + if (!ret) +- trace_cgroup_rename(cgrp); ++ TRACE_CGROUP_PATH(rename, cgrp); + + mutex_unlock(&cgroup_mutex); + +--- a/kernel/cgroup/cgroup.c ++++ b/kernel/cgroup/cgroup.c +@@ -83,6 +83,9 @@ EXPORT_SYMBOL_GPL(cgroup_mutex); + EXPORT_SYMBOL_GPL(css_set_lock); + #endif + ++DEFINE_SPINLOCK(trace_cgroup_path_lock); ++char trace_cgroup_path[TRACE_CGROUP_PATH_LEN]; ++ + /* + * Protects cgroup_idr and css_idr so that IDs can be released without + * grabbing cgroup_mutex. +@@ -2638,7 +2641,7 @@ int cgroup_attach_task(struct cgroup *ds + cgroup_migrate_finish(&mgctx); + + if (!ret) +- trace_cgroup_attach_task(dst_cgrp, leader, threadgroup); ++ TRACE_CGROUP_PATH(attach_task, dst_cgrp, leader, threadgroup); + + return ret; + } +@@ -4634,7 +4637,7 @@ static void css_release_work_fn(struct w + struct cgroup *tcgrp; + + /* cgroup release path */ +- trace_cgroup_release(cgrp); ++ TRACE_CGROUP_PATH(release, cgrp); + + if (cgroup_on_dfl(cgrp)) + cgroup_rstat_flush(cgrp); +@@ -4977,7 +4980,7 @@ int cgroup_mkdir(struct kernfs_node *par + if (ret) + goto out_destroy; + +- trace_cgroup_mkdir(cgrp); ++ TRACE_CGROUP_PATH(mkdir, cgrp); + + /* let's create and online css's */ + kernfs_activate(kn); +@@ -5165,9 +5168,8 @@ int cgroup_rmdir(struct kernfs_node *kn) + return 0; + + ret = cgroup_destroy_locked(cgrp); +- + if (!ret) +- trace_cgroup_rmdir(cgrp); ++ TRACE_CGROUP_PATH(rmdir, cgrp); + + cgroup_kn_unlock(kn); + return ret; diff --git a/debian/patches/features/all/rt/cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch b/debian/patches/features/all/rt/cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch new file mode 100644 index 000000000..42c010c42 --- /dev/null +++ b/debian/patches/features/all/rt/cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch @@ -0,0 +1,44 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 3 Jul 2018 18:19:48 +0200 +Subject: [PATCH] cgroup: use irqsave in cgroup_rstat_flush_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +All callers of cgroup_rstat_flush_locked() acquire cgroup_rstat_lock +either with spin_lock_irq() or spin_lock_irqsave(). +cgroup_rstat_flush_locked() itself acquires cgroup_rstat_cpu_lock which +is a raw_spin_lock. This lock is also acquired in cgroup_rstat_updated() +in IRQ context and therefore requires _irqsave() locking suffix in +cgroup_rstat_flush_locked(). +Since there is no difference between spin_lock_t and raw_spin_lock_t +on !RT lockdep does not complain here. On RT lockdep complains because +the interrupts were not disabled here and a deadlock is possible. + +Acquire the raw_spin_lock_t with disabled interrupts. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cgroup/rstat.c | 5 +++-- + 1 file changed, 3 insertions(+), 2 deletions(-) + +--- a/kernel/cgroup/rstat.c ++++ b/kernel/cgroup/rstat.c +@@ -157,8 +157,9 @@ static void cgroup_rstat_flush_locked(st + raw_spinlock_t *cpu_lock = per_cpu_ptr(&cgroup_rstat_cpu_lock, + cpu); + struct cgroup *pos = NULL; ++ unsigned long flags; + +- raw_spin_lock(cpu_lock); ++ raw_spin_lock_irqsave(cpu_lock, flags); + while ((pos = cgroup_rstat_cpu_pop_updated(pos, cgrp, cpu))) { + struct cgroup_subsys_state *css; + +@@ -170,7 +171,7 @@ static void cgroup_rstat_flush_locked(st + css->ss->css_rstat_flush(css, cpu); + rcu_read_unlock(); + } +- raw_spin_unlock(cpu_lock); ++ raw_spin_unlock_irqrestore(cpu_lock, flags); + + /* if @may_sleep, play nice and yield if necessary */ + if (may_sleep && (need_resched() || diff --git a/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch b/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch new file mode 100644 index 000000000..893f866c6 --- /dev/null +++ b/debian/patches/features/all/rt/cgroups-use-simple-wait-in-css_release.patch @@ -0,0 +1,87 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 13 Feb 2015 15:52:24 +0100 +Subject: cgroups: use simple wait in css_release() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +To avoid: +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:914 +|in_atomic(): 1, irqs_disabled(): 0, pid: 92, name: rcuc/11 +|2 locks held by rcuc/11/92: +| #0: (rcu_callback){......}, at: [] rcu_cpu_kthread+0x3de/0x940 +| #1: (rcu_read_lock_sched){......}, at: [] percpu_ref_call_confirm_rcu+0x0/0xd0 +|Preemption disabled at:[] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +|CPU: 11 PID: 92 Comm: rcuc/11 Not tainted 3.18.7-rt0+ #1 +| ffff8802398cdf80 ffff880235f0bc28 ffffffff815b3a12 0000000000000000 +| 0000000000000000 ffff880235f0bc48 ffffffff8109aa16 0000000000000000 +| ffff8802398cdf80 ffff880235f0bc78 ffffffff815b8dd4 000000000000df80 +|Call Trace: +| [] dump_stack+0x4f/0x7c +| [] __might_sleep+0x116/0x190 +| [] rt_spin_lock+0x24/0x60 +| [] queue_work_on+0x6d/0x1d0 +| [] css_release+0x81/0x90 +| [] percpu_ref_call_confirm_rcu+0xbe/0xd0 +| [] percpu_ref_switch_to_atomic_rcu+0x82/0xc0 +| [] rcu_cpu_kthread+0x445/0x940 +| [] smpboot_thread_fn+0x18d/0x2d0 +| [] kthread+0xe8/0x100 +| [] ret_from_fork+0x7c/0xb0 + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/cgroup-defs.h | 2 ++ + kernel/cgroup/cgroup.c | 9 +++++---- + 2 files changed, 7 insertions(+), 4 deletions(-) + +--- a/include/linux/cgroup-defs.h ++++ b/include/linux/cgroup-defs.h +@@ -20,6 +20,7 @@ + #include + #include + #include ++#include + + #ifdef CONFIG_CGROUPS + +@@ -157,6 +158,7 @@ struct cgroup_subsys_state { + + /* percpu_ref killing and RCU release */ + struct work_struct destroy_work; ++ struct swork_event destroy_swork; + struct rcu_work destroy_rwork; + + /* +--- a/kernel/cgroup/cgroup.c ++++ b/kernel/cgroup/cgroup.c +@@ -4611,10 +4611,10 @@ static void css_free_rwork_fn(struct wor + } + } + +-static void css_release_work_fn(struct work_struct *work) ++static void css_release_work_fn(struct swork_event *sev) + { + struct cgroup_subsys_state *css = +- container_of(work, struct cgroup_subsys_state, destroy_work); ++ container_of(sev, struct cgroup_subsys_state, destroy_swork); + struct cgroup_subsys *ss = css->ss; + struct cgroup *cgrp = css->cgroup; + +@@ -4674,8 +4674,8 @@ static void css_release(struct percpu_re + struct cgroup_subsys_state *css = + container_of(ref, struct cgroup_subsys_state, refcnt); + +- INIT_WORK(&css->destroy_work, css_release_work_fn); +- queue_work(cgroup_destroy_wq, &css->destroy_work); ++ INIT_SWORK(&css->destroy_swork, css_release_work_fn); ++ swork_queue(&css->destroy_swork); + } + + static void init_and_link_css(struct cgroup_subsys_state *css, +@@ -5397,6 +5397,7 @@ static int __init cgroup_wq_init(void) + */ + cgroup_destroy_wq = alloc_workqueue("cgroup_destroy", 0, 1); + BUG_ON(!cgroup_destroy_wq); ++ BUG_ON(swork_get()); + return 0; + } + core_initcall(cgroup_wq_init); diff --git a/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch b/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch new file mode 100644 index 000000000..288d2b166 --- /dev/null +++ b/debian/patches/features/all/rt/clocksource-tclib-allow-higher-clockrates.patch @@ -0,0 +1,158 @@ +From: Benedikt Spranger +Date: Mon, 8 Mar 2010 18:57:04 +0100 +Subject: clocksource: TCLIB: Allow higher clock rates for clock events +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +As default the TCLIB uses the 32KiHz base clock rate for clock events. +Add a compile time selection to allow higher clock resulution. + +(fixed up by Sami Pietikäinen ) + +Signed-off-by: Benedikt Spranger +Signed-off-by: Thomas Gleixner +--- + drivers/clocksource/tcb_clksrc.c | 36 +++++++++++++++++++++--------------- + drivers/misc/Kconfig | 12 ++++++++++-- + 2 files changed, 31 insertions(+), 17 deletions(-) + +--- a/drivers/clocksource/tcb_clksrc.c ++++ b/drivers/clocksource/tcb_clksrc.c +@@ -25,8 +25,7 @@ + * this 32 bit free-running counter. the second channel is not used. + * + * - The third channel may be used to provide a 16-bit clockevent +- * source, used in either periodic or oneshot mode. This runs +- * at 32 KiHZ, and can handle delays of up to two seconds. ++ * source, used in either periodic or oneshot mode. + * + * A boot clocksource and clockevent source are also currently needed, + * unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so +@@ -127,6 +126,7 @@ struct tc_clkevt_device { + struct clock_event_device clkevt; + struct clk *clk; + bool clk_enabled; ++ u32 freq; + void __iomem *regs; + }; + +@@ -135,13 +135,6 @@ static struct tc_clkevt_device *to_tc_cl + return container_of(clkevt, struct tc_clkevt_device, clkevt); + } + +-/* For now, we always use the 32K clock ... this optimizes for NO_HZ, +- * because using one of the divided clocks would usually mean the +- * tick rate can never be less than several dozen Hz (vs 0.5 Hz). +- * +- * A divided clock could be good for high resolution timers, since +- * 30.5 usec resolution can seem "low". +- */ + static u32 timer_clock; + + static void tc_clk_disable(struct clock_event_device *d) +@@ -191,7 +184,7 @@ static int tc_set_oneshot(struct clock_e + + tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and stop */ ++ /* count up to RC, then irq and stop */ + writel(timer_clock | ATMEL_TC_CPCSTOP | ATMEL_TC_WAVE | + ATMEL_TC_WAVESEL_UP_AUTO, regs + ATMEL_TC_REG(2, CMR)); + writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -213,10 +206,10 @@ static int tc_set_periodic(struct clock_ + */ + tc_clk_enable(d); + +- /* slow clock, count up to RC, then irq and restart */ ++ /* count up to RC, then irq and restart */ + writel(timer_clock | ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO, + regs + ATMEL_TC_REG(2, CMR)); +- writel((32768 + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); ++ writel((tcd->freq + HZ / 2) / HZ, tcaddr + ATMEL_TC_REG(2, RC)); + + /* Enable clock and interrupts on RC compare */ + writel(ATMEL_TC_CPCS, regs + ATMEL_TC_REG(2, IER)); +@@ -243,7 +236,11 @@ static struct tc_clkevt_device clkevt = + .features = CLOCK_EVT_FEAT_PERIODIC | + CLOCK_EVT_FEAT_ONESHOT, + /* Should be lower than at91rm9200's system timer */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + .rating = 125, ++#else ++ .rating = 200, ++#endif + .set_next_event = tc_next_event, + .set_state_shutdown = tc_shutdown_clk_off, + .set_state_periodic = tc_set_periodic, +@@ -265,8 +262,9 @@ static irqreturn_t ch2_irq(int irq, void + return IRQ_NONE; + } + +-static int __init setup_clkevents(struct atmel_tc *tc, int clk32k_divisor_idx) ++static int __init setup_clkevents(struct atmel_tc *tc, int divisor_idx) + { ++ unsigned divisor = atmel_tc_divisors[divisor_idx]; + int ret; + struct clk *t2_clk = tc->clk[2]; + int irq = tc->irq[2]; +@@ -287,7 +285,11 @@ static int __init setup_clkevents(struct + clkevt.regs = tc->regs; + clkevt.clk = t2_clk; + +- timer_clock = clk32k_divisor_idx; ++ timer_clock = divisor_idx; ++ if (!divisor) ++ clkevt.freq = 32768; ++ else ++ clkevt.freq = clk_get_rate(t2_clk) / divisor; + + clkevt.clkevt.cpumask = cpumask_of(0); + +@@ -298,7 +300,7 @@ static int __init setup_clkevents(struct + return ret; + } + +- clockevents_config_and_register(&clkevt.clkevt, 32768, 1, 0xffff); ++ clockevents_config_and_register(&clkevt.clkevt, clkevt.freq, 1, 0xffff); + + return ret; + } +@@ -435,7 +437,11 @@ static int __init tcb_clksrc_init(void) + goto err_disable_t1; + + /* channel 2: periodic and oneshot timer support */ ++#ifdef CONFIG_ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK + ret = setup_clkevents(tc, clk32k_divisor_idx); ++#else ++ ret = setup_clkevents(tc, best_divisor_idx); ++#endif + if (ret) + goto err_unregister_clksrc; + +--- a/drivers/misc/Kconfig ++++ b/drivers/misc/Kconfig +@@ -69,8 +69,7 @@ config ATMEL_TCB_CLKSRC + are combined to make a single 32-bit timer. + + When GENERIC_CLOCKEVENTS is defined, the third timer channel +- may be used as a clock event device supporting oneshot mode +- (delays of up to two seconds) based on the 32 KiHz clock. ++ may be used as a clock event device supporting oneshot mode. + + config ATMEL_TCB_CLKSRC_BLOCK + int +@@ -83,6 +82,15 @@ config ATMEL_TCB_CLKSRC_BLOCK + TC can be used for other purposes, such as PWM generation and + interval timing. + ++config ATMEL_TCB_CLKSRC_USE_SLOW_CLOCK ++ bool "TC Block use 32 KiHz clock" ++ depends on ATMEL_TCB_CLKSRC ++ default y ++ help ++ Select this to use 32 KiHz base clock rate as TC block clock ++ source for clock events. ++ ++ + config DUMMY_IRQ + tristate "Dummy IRQ handler" + default n diff --git a/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch b/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch new file mode 100644 index 000000000..a9901415d --- /dev/null +++ b/debian/patches/features/all/rt/completion-use-simple-wait-queues.patch @@ -0,0 +1,336 @@ +Subject: completion: Use simple wait queues +From: Thomas Gleixner +Date: Fri, 11 Jan 2013 11:23:51 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Completions have no long lasting callbacks and therefor do not need +the complex waitqueue variant. Use simple waitqueues which reduces the +contention on the waitqueue lock. + +Signed-off-by: Thomas Gleixner +--- + drivers/net/wireless/intersil/orinoco/orinoco_usb.c | 2 - + drivers/usb/gadget/function/f_fs.c | 2 - + drivers/usb/gadget/legacy/inode.c | 4 +- + include/linux/completion.h | 8 ++-- + include/linux/suspend.h | 6 +++ + include/linux/swait.h | 1 + kernel/power/hibernate.c | 7 ++++ + kernel/power/suspend.c | 4 ++ + kernel/sched/completion.c | 34 ++++++++++---------- + kernel/sched/core.c | 10 ++++- + kernel/sched/swait.c | 19 +++++++++++ + 11 files changed, 70 insertions(+), 27 deletions(-) + +--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c ++++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c +@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ez + while (!ctx->done.done && msecs--) + udelay(1000); + } else { +- wait_event_interruptible(ctx->done.wait, ++ swait_event_interruptible(ctx->done.wait, + ctx->done.done); + } + break; +--- a/drivers/usb/gadget/function/f_fs.c ++++ b/drivers/usb/gadget/function/f_fs.c +@@ -1633,7 +1633,7 @@ static void ffs_data_put(struct ffs_data + pr_info("%s(): freeing\n", __func__); + ffs_data_clear(ffs); + BUG_ON(waitqueue_active(&ffs->ev.waitq) || +- waitqueue_active(&ffs->ep0req_completion.wait) || ++ swait_active(&ffs->ep0req_completion.wait) || + waitqueue_active(&ffs->wait)); + destroy_workqueue(ffs->io_completion_wq); + kfree(ffs->dev_name); +--- a/drivers/usb/gadget/legacy/inode.c ++++ b/drivers/usb/gadget/legacy/inode.c +@@ -343,7 +343,7 @@ ep_io (struct ep_data *epdata, void *buf + spin_unlock_irq (&epdata->dev->lock); + + if (likely (value == 0)) { +- value = wait_event_interruptible (done.wait, done.done); ++ value = swait_event_interruptible (done.wait, done.done); + if (value != 0) { + spin_lock_irq (&epdata->dev->lock); + if (likely (epdata->ep != NULL)) { +@@ -352,7 +352,7 @@ ep_io (struct ep_data *epdata, void *buf + usb_ep_dequeue (epdata->ep, epdata->req); + spin_unlock_irq (&epdata->dev->lock); + +- wait_event (done.wait, done.done); ++ swait_event (done.wait, done.done); + if (epdata->status == -ECONNRESET) + epdata->status = -EINTR; + } else { +--- a/include/linux/completion.h ++++ b/include/linux/completion.h +@@ -9,7 +9,7 @@ + * See kernel/sched/completion.c for details. + */ + +-#include ++#include + + /* + * struct completion - structure used to maintain state for a "completion" +@@ -25,7 +25,7 @@ + */ + struct completion { + unsigned int done; +- wait_queue_head_t wait; ++ struct swait_queue_head wait; + }; + + #define init_completion_map(x, m) __init_completion(x) +@@ -34,7 +34,7 @@ static inline void complete_acquire(stru + static inline void complete_release(struct completion *x) {} + + #define COMPLETION_INITIALIZER(work) \ +- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) } ++ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) } + + #define COMPLETION_INITIALIZER_ONSTACK_MAP(work, map) \ + (*({ init_completion_map(&(work), &(map)); &(work); })) +@@ -85,7 +85,7 @@ static inline void complete_release(stru + static inline void __init_completion(struct completion *x) + { + x->done = 0; +- init_waitqueue_head(&x->wait); ++ init_swait_queue_head(&x->wait); + } + + /** +--- a/include/linux/suspend.h ++++ b/include/linux/suspend.h +@@ -196,6 +196,12 @@ struct platform_s2idle_ops { + void (*end)(void); + }; + ++#if defined(CONFIG_SUSPEND) || defined(CONFIG_HIBERNATION) ++extern bool pm_in_action; ++#else ++# define pm_in_action false ++#endif ++ + #ifdef CONFIG_SUSPEND + extern suspend_state_t mem_sleep_current; + extern suspend_state_t mem_sleep_default; +--- a/include/linux/swait.h ++++ b/include/linux/swait.h +@@ -160,6 +160,7 @@ static inline bool swq_has_sleeper(struc + extern void swake_up(struct swait_queue_head *q); + extern void swake_up_all(struct swait_queue_head *q); + extern void swake_up_locked(struct swait_queue_head *q); ++extern void swake_up_all_locked(struct swait_queue_head *q); + + extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait); + extern void prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait, int state); +--- a/kernel/power/hibernate.c ++++ b/kernel/power/hibernate.c +@@ -679,6 +679,10 @@ static int load_image_and_restore(void) + return error; + } + ++#ifndef CONFIG_SUSPEND ++bool pm_in_action; ++#endif ++ + /** + * hibernate - Carry out system hibernation, including saving the image. + */ +@@ -692,6 +696,8 @@ int hibernate(void) + return -EPERM; + } + ++ pm_in_action = true; ++ + lock_system_sleep(); + /* The snapshot device should not be opened while we're running */ + if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { +@@ -770,6 +776,7 @@ int hibernate(void) + atomic_inc(&snapshot_device_available); + Unlock: + unlock_system_sleep(); ++ pm_in_action = false; + pr_info("hibernation exit\n"); + + return error; +--- a/kernel/power/suspend.c ++++ b/kernel/power/suspend.c +@@ -594,6 +594,8 @@ static int enter_state(suspend_state_t s + return error; + } + ++bool pm_in_action; ++ + /** + * pm_suspend - Externally visible function for suspending the system. + * @state: System sleep state to enter. +@@ -608,6 +610,7 @@ int pm_suspend(suspend_state_t state) + if (state <= PM_SUSPEND_ON || state >= PM_SUSPEND_MAX) + return -EINVAL; + ++ pm_in_action = true; + pr_info("suspend entry (%s)\n", mem_sleep_labels[state]); + error = enter_state(state); + if (error) { +@@ -617,6 +620,7 @@ int pm_suspend(suspend_state_t state) + suspend_stats.success++; + } + pr_info("suspend exit\n"); ++ pm_in_action = false; + return error; + } + EXPORT_SYMBOL(pm_suspend); +--- a/kernel/sched/completion.c ++++ b/kernel/sched/completion.c +@@ -29,12 +29,12 @@ void complete(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + + if (x->done != UINT_MAX) + x->done++; +- __wake_up_locked(&x->wait, TASK_NORMAL, 1); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete); + +@@ -58,10 +58,10 @@ void complete_all(struct completion *x) + { + unsigned long flags; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + x->done = UINT_MAX; +- __wake_up_locked(&x->wait, TASK_NORMAL, 0); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ swake_up_all_locked(&x->wait); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + } + EXPORT_SYMBOL(complete_all); + +@@ -70,20 +70,20 @@ do_wait_for_common(struct completion *x, + long (*action)(long), long timeout, int state) + { + if (!x->done) { +- DECLARE_WAITQUEUE(wait, current); ++ DECLARE_SWAITQUEUE(wait); + +- __add_wait_queue_entry_tail_exclusive(&x->wait, &wait); ++ __prepare_to_swait(&x->wait, &wait); + do { + if (signal_pending_state(state, current)) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + timeout = action(timeout); +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); +- __remove_wait_queue(&x->wait, &wait); ++ __finish_swait(&x->wait, &wait); + if (!x->done) + return timeout; + } +@@ -100,9 +100,9 @@ static inline long __sched + + complete_acquire(x); + +- spin_lock_irq(&x->wait.lock); ++ raw_spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, action, timeout, state); +- spin_unlock_irq(&x->wait.lock); ++ raw_spin_unlock_irq(&x->wait.lock); + + complete_release(x); + +@@ -291,12 +291,12 @@ bool try_wait_for_completion(struct comp + if (!READ_ONCE(x->done)) + return false; + +- spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); + if (!x->done) + ret = false; + else if (x->done != UINT_MAX) + x->done--; +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return ret; + } + EXPORT_SYMBOL(try_wait_for_completion); +@@ -322,8 +322,8 @@ bool completion_done(struct completion * + * otherwise we can end up freeing the completion before complete() + * is done referencing it. + */ +- spin_lock_irqsave(&x->wait.lock, flags); +- spin_unlock_irqrestore(&x->wait.lock, flags); ++ raw_spin_lock_irqsave(&x->wait.lock, flags); ++ raw_spin_unlock_irqrestore(&x->wait.lock, flags); + return true; + } + EXPORT_SYMBOL(completion_done); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7130,7 +7130,10 @@ void migrate_disable(void) + return; + } + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + + if (p->migrate_disable) { +@@ -7160,7 +7163,10 @@ void migrate_enable(void) + } + + #ifdef CONFIG_SCHED_DEBUG +- WARN_ON_ONCE(p->migrate_disable_atomic); ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } + #endif + + WARN_ON_ONCE(p->migrate_disable <= 0); +--- a/kernel/sched/swait.c ++++ b/kernel/sched/swait.c +@@ -32,6 +32,25 @@ void swake_up_locked(struct swait_queue_ + } + EXPORT_SYMBOL(swake_up_locked); + ++void swake_up_all_locked(struct swait_queue_head *q) ++{ ++ struct swait_queue *curr; ++ int wakes = 0; ++ ++ while (!list_empty(&q->task_list)) { ++ ++ curr = list_first_entry(&q->task_list, typeof(*curr), ++ task_list); ++ wake_up_process(curr->task); ++ list_del_init(&curr->task_list); ++ wakes++; ++ } ++ if (pm_in_action) ++ return; ++ WARN(wakes > 2, "complete_all() with %d waiters\n", wakes); ++} ++EXPORT_SYMBOL(swake_up_all_locked); ++ + void swake_up(struct swait_queue_head *q) + { + unsigned long flags; diff --git a/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch b/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch new file mode 100644 index 000000000..6fa6fc170 --- /dev/null +++ b/debian/patches/features/all/rt/cond-resched-lock-rt-tweak.patch @@ -0,0 +1,27 @@ +Subject: sched: Use the proper LOCK_OFFSET for cond_resched() +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 22:51:33 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +RT does not increment preempt count when a 'sleeping' spinlock is +locked. Update PREEMPT_LOCK_OFFSET for that case. + +Signed-off-by: Thomas Gleixner +--- + include/linux/preempt.h | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -118,7 +118,11 @@ + /* + * The preempt_count offset after spin_lock() + */ ++#if !defined(CONFIG_PREEMPT_RT_FULL) + #define PREEMPT_LOCK_OFFSET PREEMPT_DISABLE_OFFSET ++#else ++#define PREEMPT_LOCK_OFFSET 0 ++#endif + + /* + * The preempt_count offset needed for things like: diff --git a/debian/patches/features/all/rt/connector-cn_proc-Protect-send_msg-with-a-local-lock.patch b/debian/patches/features/all/rt/connector-cn_proc-Protect-send_msg-with-a-local-lock.patch new file mode 100644 index 000000000..a08fa9b75 --- /dev/null +++ b/debian/patches/features/all/rt/connector-cn_proc-Protect-send_msg-with-a-local-lock.patch @@ -0,0 +1,68 @@ +From: Mike Galbraith +Date: Sun, 16 Oct 2016 05:11:54 +0200 +Subject: [PATCH] connector/cn_proc: Protect send_msg() with a local lock + on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 +|in_atomic(): 1, irqs_disabled(): 0, pid: 31807, name: sleep +|Preemption disabled at:[] proc_exit_connector+0xbb/0x140 +| +|CPU: 4 PID: 31807 Comm: sleep Tainted: G W E 4.8.0-rt11-rt #106 +|Call Trace: +| [] dump_stack+0x65/0x88 +| [] ___might_sleep+0xf5/0x180 +| [] __rt_spin_lock+0x20/0x50 +| [] rt_read_lock+0x28/0x30 +| [] netlink_broadcast_filtered+0x49/0x3f0 +| [] ? __kmalloc_reserve.isra.33+0x31/0x90 +| [] netlink_broadcast+0x1d/0x20 +| [] cn_netlink_send_mult+0x19a/0x1f0 +| [] cn_netlink_send+0x1b/0x20 +| [] proc_exit_connector+0xf8/0x140 +| [] do_exit+0x5d1/0xba0 +| [] do_group_exit+0x4c/0xc0 +| [] SyS_exit_group+0x14/0x20 +| [] entry_SYSCALL_64_fastpath+0x1a/0xa4 + +Since ab8ed951080e ("connector: fix out-of-order cn_proc netlink message +delivery") which is v4.7-rc6. + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/connector/cn_proc.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/drivers/connector/cn_proc.c ++++ b/drivers/connector/cn_proc.c +@@ -32,6 +32,7 @@ + #include + + #include ++#include + + /* + * Size of a cn_msg followed by a proc_event structure. Since the +@@ -54,10 +55,11 @@ static struct cb_id cn_proc_event_id = { + + /* proc_event_counts is used as the sequence number of the netlink message */ + static DEFINE_PER_CPU(__u32, proc_event_counts) = { 0 }; ++static DEFINE_LOCAL_IRQ_LOCK(send_msg_lock); + + static inline void send_msg(struct cn_msg *msg) + { +- preempt_disable(); ++ local_lock(send_msg_lock); + + msg->seq = __this_cpu_inc_return(proc_event_counts) - 1; + ((struct proc_event *)msg->data)->cpu = smp_processor_id(); +@@ -70,7 +72,7 @@ static inline void send_msg(struct cn_ms + */ + cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT); + +- preempt_enable(); ++ local_unlock(send_msg_lock); + } + + void proc_fork_connector(struct task_struct *task) diff --git a/debian/patches/features/all/rt/cpu-hotplug--Implement-CPU-pinning.patch b/debian/patches/features/all/rt/cpu-hotplug--Implement-CPU-pinning.patch new file mode 100644 index 000000000..47fdf9bb2 --- /dev/null +++ b/debian/patches/features/all/rt/cpu-hotplug--Implement-CPU-pinning.patch @@ -0,0 +1,111 @@ +Subject: cpu/hotplug: Implement CPU pinning +From: Thomas Gleixner +Date: Wed, 19 Jul 2017 17:31:20 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 1 + + kernel/cpu.c | 40 ++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 41 insertions(+) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -671,6 +671,7 @@ struct task_struct { + #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; + int migrate_disable_update; ++ int pinned_on_cpu; + # ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; + # endif +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -73,6 +73,11 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_s + .fail = CPUHP_INVALID, + }; + ++#ifdef CONFIG_HOTPLUG_CPU ++static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ ++ __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); ++#endif ++ + #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) + static struct lockdep_map cpuhp_state_up_map = + STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); +@@ -287,7 +292,30 @@ static int cpu_hotplug_disabled; + */ + void pin_current_cpu(void) + { ++ struct rt_rw_lock *cpuhp_pin; ++ unsigned int cpu; ++ int ret; + ++again: ++ cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); ++ ret = __read_rt_trylock(cpuhp_pin); ++ if (ret) { ++ current->pinned_on_cpu = smp_processor_id(); ++ return; ++ } ++ cpu = smp_processor_id(); ++ preempt_lazy_enable(); ++ preempt_enable(); ++ ++ __read_rt_lock(cpuhp_pin); ++ ++ preempt_disable(); ++ preempt_lazy_disable(); ++ if (cpu != smp_processor_id()) { ++ __read_rt_unlock(cpuhp_pin); ++ goto again; ++ } ++ current->pinned_on_cpu = cpu; + } + + /** +@@ -295,6 +323,13 @@ void pin_current_cpu(void) + */ + void unpin_current_cpu(void) + { ++ struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); ++ ++ if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) ++ cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu); ++ ++ current->pinned_on_cpu = -1; ++ __read_rt_unlock(cpuhp_pin); + } + + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +@@ -764,6 +799,7 @@ static int take_cpu_down(void *_param) + + static int takedown_cpu(unsigned int cpu) + { ++ struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; + +@@ -777,11 +813,14 @@ static int takedown_cpu(unsigned int cpu + */ + irq_lock_sparse(); + ++ __write_rt_lock(cpuhp_pin); ++ + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); + if (err) { ++ __write_rt_unlock(cpuhp_pin); + /* CPU refused to die */ + irq_unlock_sparse(); + /* Unpark the hotplug thread so we can rollback there */ +@@ -800,6 +839,7 @@ static int takedown_cpu(unsigned int cpu + wait_for_ap_thread(st, false); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); + ++ __write_rt_unlock(cpuhp_pin); + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + diff --git a/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch b/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch new file mode 100644 index 000000000..54c4de224 --- /dev/null +++ b/debian/patches/features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch @@ -0,0 +1,33 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 9 Apr 2015 15:23:01 +0200 +Subject: cpufreq: drop K8's driver from beeing selected +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Ralf posted a picture of a backtrace from + +| powernowk8_target_fn() -> transition_frequency_fidvid() and then at the +| end: +| 932 policy = cpufreq_cpu_get(smp_processor_id()); +| 933 cpufreq_cpu_put(policy); + +crashing the system on -RT. I assumed that policy was a NULL pointer but +was rulled out. Since Ralf can't do any more investigations on this and +I have no machine with this, I simply switch it off. + +Reported-by: Ralf Mardorf +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/cpufreq/Kconfig.x86 | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/cpufreq/Kconfig.x86 ++++ b/drivers/cpufreq/Kconfig.x86 +@@ -125,7 +125,7 @@ config X86_POWERNOW_K7_ACPI + + config X86_POWERNOW_K8 + tristate "AMD Opteron/Athlon64 PowerNow!" +- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ ++ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE + help + This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors. + Support for K10 and newer processors is now in acpi-cpufreq. diff --git a/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch b/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch new file mode 100644 index 000000000..c24f5963c --- /dev/null +++ b/debian/patches/features/all/rt/cpumask-disable-offstack-on-rt.patch @@ -0,0 +1,68 @@ +Subject: cpumask: Disable CONFIG_CPUMASK_OFFSTACK for RT +From: Thomas Gleixner +Date: Wed, 14 Dec 2011 01:03:49 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There are "valid" GFP_ATOMIC allocations such as + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:931 +|in_atomic(): 1, irqs_disabled(): 0, pid: 2130, name: tar +|1 lock held by tar/2130: +| #0: (&mm->mmap_sem){++++++}, at: [] SyS_brk+0x39/0x190 +|Preemption disabled at:[] flush_tlb_mm_range+0x28/0x350 +| +|CPU: 1 PID: 2130 Comm: tar Tainted: G W 4.8.2-rt2+ #747 +|Call Trace: +| [] dump_stack+0x86/0xca +| [] ___might_sleep+0x14b/0x240 +| [] rt_spin_lock+0x24/0x60 +| [] get_page_from_freelist+0x83a/0x11b0 +| [] __alloc_pages_nodemask+0x15b/0x1190 +| [] alloc_pages_current+0xa1/0x1f0 +| [] new_slab+0x3e5/0x690 +| [] ___slab_alloc+0x495/0x660 +| [] __slab_alloc.isra.79+0x71/0xc0 +| [] __kmalloc_node+0xe7/0x240 +| [] alloc_cpumask_var_node+0x20/0x50 +| [] alloc_cpumask_var+0xe/0x10 +| [] native_send_call_func_ipi+0x21/0x130 +| [] smp_call_function_many+0x22f/0x370 +| [] native_flush_tlb_others+0x1a4/0x3a0 +| [] flush_tlb_mm_range+0x7b/0x350 +| [] tlb_flush_mmu_tlbonly+0x62/0xd0 +| [] tlb_finish_mmu+0x14/0x50 +| [] unmap_region+0xe4/0x110 +| [] do_munmap+0x293/0x470 +| [] SyS_brk+0x13c/0x190 +| [] do_fast_syscall_32+0xb2/0x2f0 +| [] entry_SYSENTER_compat+0x51/0x60 + +which forbid allocations at run-time. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/Kconfig | 2 +- + lib/Kconfig | 1 + + 2 files changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -938,7 +938,7 @@ config CALGARY_IOMMU_ENABLED_BY_DEFAULT + config MAXSMP + bool "Enable Maximum number of SMP Processors and NUMA Nodes" + depends on X86_64 && SMP && DEBUG_KERNEL +- select CPUMASK_OFFSTACK ++ select CPUMASK_OFFSTACK if !PREEMPT_RT_FULL + ---help--- + Enable maximum number of CPUS and NUMA Nodes for this architecture. + If unsure, say N. +--- a/lib/Kconfig ++++ b/lib/Kconfig +@@ -434,6 +434,7 @@ config CHECK_SIGNATURE + + config CPUMASK_OFFSTACK + bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS ++ depends on !PREEMPT_RT_FULL + help + Use dynamic allocation for cpumask_var_t, instead of putting + them on the stack. This is a bit more expensive, but avoids diff --git a/debian/patches/features/all/rt/cpuset-Convert-callback_lock-to-raw_spinlock_t.patch b/debian/patches/features/all/rt/cpuset-Convert-callback_lock-to-raw_spinlock_t.patch new file mode 100644 index 000000000..da9c2193c --- /dev/null +++ b/debian/patches/features/all/rt/cpuset-Convert-callback_lock-to-raw_spinlock_t.patch @@ -0,0 +1,287 @@ +From: Mike Galbraith +Date: Sun, 8 Jan 2017 09:32:25 +0100 +Subject: [PATCH] cpuset: Convert callback_lock to raw_spinlock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The two commits below add up to a cpuset might_sleep() splat for RT: + +8447a0fee974 cpuset: convert callback_mutex to a spinlock +344736f29b35 cpuset: simplify cpuset_node_allowed API + +BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:995 +in_atomic(): 0, irqs_disabled(): 1, pid: 11718, name: cset +CPU: 135 PID: 11718 Comm: cset Tainted: G E 4.10.0-rt1-rt #4 +Hardware name: Intel Corporation BRICKLAND/BRICKLAND, BIOS BRHSXSD1.86B.0056.R01.1409242327 09/24/2014 +Call Trace: + ? dump_stack+0x5c/0x81 + ? ___might_sleep+0xf4/0x170 + ? rt_spin_lock+0x1c/0x50 + ? __cpuset_node_allowed+0x66/0xc0 + ? ___slab_alloc+0x390/0x570 + ? anon_vma_fork+0x8f/0x140 + ? copy_page_range+0x6cf/0xb00 + ? anon_vma_fork+0x8f/0x140 + ? __slab_alloc.isra.74+0x5a/0x81 + ? anon_vma_fork+0x8f/0x140 + ? kmem_cache_alloc+0x1b5/0x1f0 + ? anon_vma_fork+0x8f/0x140 + ? copy_process.part.35+0x1670/0x1ee0 + ? _do_fork+0xdd/0x3f0 + ? _do_fork+0xdd/0x3f0 + ? do_syscall_64+0x61/0x170 + ? entry_SYSCALL64_slow_path+0x25/0x25 + +The later ensured that a NUMA box WILL take callback_lock in atomic +context by removing the allocator and reclaim path __GFP_HARDWALL +usage which prevented such contexts from taking callback_mutex. + +One option would be to reinstate __GFP_HARDWALL protections for +RT, however, as the 8447a0fee974 changelog states: + +The callback_mutex is only used to synchronize reads/updates of cpusets' +flags and cpu/node masks. These operations should always proceed fast so +there's no reason why we can't use a spinlock instead of the mutex. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cgroup/cpuset.c | 66 ++++++++++++++++++++++++------------------------- + 1 file changed, 33 insertions(+), 33 deletions(-) + +--- a/kernel/cgroup/cpuset.c ++++ b/kernel/cgroup/cpuset.c +@@ -288,7 +288,7 @@ static struct cpuset top_cpuset = { + */ + + static DEFINE_MUTEX(cpuset_mutex); +-static DEFINE_SPINLOCK(callback_lock); ++static DEFINE_RAW_SPINLOCK(callback_lock); + + static struct workqueue_struct *cpuset_migrate_mm_wq; + +@@ -922,9 +922,9 @@ static void update_cpumasks_hier(struct + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cp->effective_cpus, new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!is_in_v2_mode() && + !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); +@@ -989,9 +989,9 @@ static int update_cpumask(struct cpuset + if (retval < 0) + return retval; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->cpus_allowed as a temp variable */ + update_cpumasks_hier(cs, trialcs->cpus_allowed); +@@ -1175,9 +1175,9 @@ static void update_nodemasks_hier(struct + continue; + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cp->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + WARN_ON(!is_in_v2_mode() && + !nodes_equal(cp->mems_allowed, cp->effective_mems)); +@@ -1245,9 +1245,9 @@ static int update_nodemask(struct cpuset + if (retval < 0) + goto done; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = trialcs->mems_allowed; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* use trialcs->mems_allowed as a temp variable */ + update_nodemasks_hier(cs, &trialcs->mems_allowed); +@@ -1338,9 +1338,9 @@ static int update_flag(cpuset_flagbits_t + spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) + || (is_spread_page(cs) != is_spread_page(trialcs))); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->flags = trialcs->flags; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) + rebuild_sched_domains_locked(); +@@ -1755,7 +1755,7 @@ static int cpuset_common_seq_show(struct + cpuset_filetype_t type = seq_cft(sf)->private; + int ret = 0; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + switch (type) { + case FILE_CPULIST: +@@ -1774,7 +1774,7 @@ static int cpuset_common_seq_show(struct + ret = -EINVAL; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + return ret; + } + +@@ -1989,12 +1989,12 @@ static int cpuset_css_online(struct cgro + + cpuset_inc(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (is_in_v2_mode()) { + cpumask_copy(cs->effective_cpus, parent->effective_cpus); + cs->effective_mems = parent->effective_mems; + } +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) + goto out_unlock; +@@ -2021,12 +2021,12 @@ static int cpuset_css_online(struct cgro + } + rcu_read_unlock(); + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cs->mems_allowed = parent->mems_allowed; + cs->effective_mems = parent->mems_allowed; + cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); + cpumask_copy(cs->effective_cpus, parent->cpus_allowed); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + out_unlock: + mutex_unlock(&cpuset_mutex); + return 0; +@@ -2065,7 +2065,7 @@ static void cpuset_css_free(struct cgrou + static void cpuset_bind(struct cgroup_subsys_state *root_css) + { + mutex_lock(&cpuset_mutex); +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + + if (is_in_v2_mode()) { + cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); +@@ -2076,7 +2076,7 @@ static void cpuset_bind(struct cgroup_su + top_cpuset.mems_allowed = top_cpuset.effective_mems; + } + +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + mutex_unlock(&cpuset_mutex); + } + +@@ -2174,12 +2174,12 @@ hotplug_update_tasks_legacy(struct cpuse + { + bool is_empty; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->cpus_allowed, new_cpus); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->mems_allowed = *new_mems; + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + /* + * Don't call update_tasks_cpumask() if the cpuset becomes empty, +@@ -2216,10 +2216,10 @@ hotplug_update_tasks(struct cpuset *cs, + if (nodes_empty(*new_mems)) + *new_mems = parent_cs(cs)->effective_mems; + +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + cpumask_copy(cs->effective_cpus, new_cpus); + cs->effective_mems = *new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + + if (cpus_updated) + update_tasks_cpumask(cs); +@@ -2312,21 +2312,21 @@ static void cpuset_hotplug_workfn(struct + + /* synchronize cpus_allowed to cpu_active_mask */ + if (cpus_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); + cpumask_copy(top_cpuset.effective_cpus, &new_cpus); +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + /* we don't mess with cpumasks of tasks in top_cpuset */ + } + + /* synchronize mems_allowed to N_MEMORY */ + if (mems_updated) { +- spin_lock_irq(&callback_lock); ++ raw_spin_lock_irq(&callback_lock); + if (!on_dfl) + top_cpuset.mems_allowed = new_mems; + top_cpuset.effective_mems = new_mems; +- spin_unlock_irq(&callback_lock); ++ raw_spin_unlock_irq(&callback_lock); + update_tasks_nodemask(&top_cpuset); + } + +@@ -2425,11 +2425,11 @@ void cpuset_cpus_allowed(struct task_str + { + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_cpus(task_cs(tsk), pmask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + } + + void cpuset_cpus_allowed_fallback(struct task_struct *tsk) +@@ -2477,11 +2477,11 @@ nodemask_t cpuset_mems_allowed(struct ta + nodemask_t mask; + unsigned long flags; + +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + rcu_read_lock(); + guarantee_online_mems(task_cs(tsk), &mask); + rcu_read_unlock(); +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + + return mask; + } +@@ -2573,14 +2573,14 @@ bool __cpuset_node_allowed(int node, gfp + return true; + + /* Not hardwall and node outside mems_allowed: scan up cpusets */ +- spin_lock_irqsave(&callback_lock, flags); ++ raw_spin_lock_irqsave(&callback_lock, flags); + + rcu_read_lock(); + cs = nearest_hardwall_ancestor(task_cs(current)); + allowed = node_isset(node, cs->mems_allowed); + rcu_read_unlock(); + +- spin_unlock_irqrestore(&callback_lock, flags); ++ raw_spin_unlock_irqrestore(&callback_lock, flags); + return allowed; + } + diff --git a/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch b/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch new file mode 100644 index 000000000..9b8863de4 --- /dev/null +++ b/debian/patches/features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch @@ -0,0 +1,255 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 21 Feb 2014 17:24:04 +0100 +Subject: crypto: Reduce preempt disabled regions, more algos +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Don Estabrook reported +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() +| kernel: WARNING: CPU: 2 PID: 858 at kernel/sched/core.c:2462 migrate_enable+0x17b/0x200() +| kernel: WARNING: CPU: 3 PID: 865 at kernel/sched/core.c:2428 migrate_disable+0xed/0x100() + +and his backtrace showed some crypto functions which looked fine. + +The problem is the following sequence: + +glue_xts_crypt_128bit() +{ + blkcipher_walk_virt(); /* normal migrate_disable() */ + + glue_fpu_begin(); /* get atomic */ + + while (nbytes) { + __glue_xts_crypt_128bit(); + blkcipher_walk_done(); /* with nbytes = 0, migrate_enable() + * while we are atomic */ + }; + glue_fpu_end() /* no longer atomic */ +} + +and this is why the counter get out of sync and the warning is printed. +The other problem is that we are non-preemptible between +glue_fpu_begin() and glue_fpu_end() and the latency grows. To fix this, +I shorten the FPU off region and ensure blkcipher_walk_done() is called +with preemption enabled. This might hurt the performance because we now +enable/disable the FPU state more often but we gain lower latency and +the bug is gone. + + +Reported-by: Don Estabrook +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/crypto/cast5_avx_glue.c | 21 +++++++++------------ + arch/x86/crypto/glue_helper.c | 31 ++++++++++++++++--------------- + 2 files changed, 25 insertions(+), 27 deletions(-) + +--- a/arch/x86/crypto/cast5_avx_glue.c ++++ b/arch/x86/crypto/cast5_avx_glue.c +@@ -61,7 +61,7 @@ static inline void cast5_fpu_end(bool fp + + static int ecb_crypt(struct skcipher_request *req, bool enc) + { +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); + struct skcipher_walk walk; +@@ -76,7 +76,7 @@ static int ecb_crypt(struct skcipher_req + u8 *wsrc = walk.src.virt.addr; + u8 *wdst = walk.dst.virt.addr; + +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + + /* Process multi-block batch */ + if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) { +@@ -105,10 +105,9 @@ static int ecb_crypt(struct skcipher_req + } while (nbytes >= bsize); + + done: ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -212,7 +211,7 @@ static int cbc_decrypt(struct skcipher_r + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct skcipher_walk walk; + unsigned int nbytes; + int err; +@@ -220,12 +219,11 @@ static int cbc_decrypt(struct skcipher_r + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes)) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + nbytes = __cbc_decrypt(ctx, &walk); ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- cast5_fpu_end(fpu_enabled); + return err; + } + +@@ -292,7 +290,7 @@ static int ctr_crypt(struct skcipher_req + { + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + struct cast5_ctx *ctx = crypto_skcipher_ctx(tfm); +- bool fpu_enabled = false; ++ bool fpu_enabled; + struct skcipher_walk walk; + unsigned int nbytes; + int err; +@@ -300,13 +298,12 @@ static int ctr_crypt(struct skcipher_req + err = skcipher_walk_virt(&walk, req, false); + + while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) { +- fpu_enabled = cast5_fpu_begin(fpu_enabled, &walk, nbytes); ++ fpu_enabled = cast5_fpu_begin(false, &walk, nbytes); + nbytes = __ctr_crypt(&walk, ctx); ++ cast5_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- cast5_fpu_end(fpu_enabled); +- + if (walk.nbytes) { + ctr_crypt_final(&walk, ctx); + err = skcipher_walk_done(&walk, 0); +--- a/arch/x86/crypto/glue_helper.c ++++ b/arch/x86/crypto/glue_helper.c +@@ -38,7 +38,7 @@ int glue_ecb_req_128bit(const struct com + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -51,7 +51,7 @@ int glue_ecb_req_128bit(const struct com + unsigned int i; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + for (i = 0; i < gctx->num_funcs; i++) { + func_bytes = bsize * gctx->funcs[i].num_blocks; + +@@ -69,10 +69,9 @@ int glue_ecb_req_128bit(const struct com + if (nbytes < bsize) + break; + } ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } +- +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_ecb_req_128bit); +@@ -115,7 +114,7 @@ int glue_cbc_decrypt_req_128bit(const st + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -129,7 +128,7 @@ int glue_cbc_decrypt_req_128bit(const st + u128 last_iv; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + /* Start of the last block. */ + src += nbytes / bsize - 1; + dst += nbytes / bsize - 1; +@@ -161,10 +160,10 @@ int glue_cbc_decrypt_req_128bit(const st + done: + u128_xor(dst, dst, (u128 *)walk.iv); + *(u128 *)walk.iv = last_iv; ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); + return err; + } + EXPORT_SYMBOL_GPL(glue_cbc_decrypt_req_128bit); +@@ -175,7 +174,7 @@ int glue_ctr_req_128bit(const struct com + void *ctx = crypto_skcipher_ctx(crypto_skcipher_reqtfm(req)); + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -189,7 +188,7 @@ int glue_ctr_req_128bit(const struct com + le128 ctrblk; + + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, nbytes); ++ &walk, false, nbytes); + + be128_to_le128(&ctrblk, (be128 *)walk.iv); + +@@ -213,11 +212,10 @@ int glue_ctr_req_128bit(const struct com + } + + le128_to_be128((be128 *)walk.iv, &ctrblk); ++ glue_fpu_end(fpu_enabled); + err = skcipher_walk_done(&walk, nbytes); + } + +- glue_fpu_end(fpu_enabled); +- + if (nbytes) { + le128 ctrblk; + u128 tmp; +@@ -278,7 +276,7 @@ int glue_xts_req_128bit(const struct com + { + const unsigned int bsize = 128 / 8; + struct skcipher_walk walk; +- bool fpu_enabled = false; ++ bool fpu_enabled; + unsigned int nbytes; + int err; + +@@ -289,21 +287,24 @@ int glue_xts_req_128bit(const struct com + + /* set minimum length to bsize, for tweak_fn */ + fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, +- &walk, fpu_enabled, ++ &walk, false, + nbytes < bsize ? bsize : nbytes); + + /* calculate first value of T */ + tweak_fn(tweak_ctx, walk.iv, walk.iv); + + while (nbytes) { ++ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit, ++ &walk, fpu_enabled, ++ nbytes < bsize ? bsize : nbytes); + nbytes = __glue_xts_req_128bit(gctx, crypt_ctx, &walk); + ++ glue_fpu_end(fpu_enabled); ++ fpu_enabled = false; + err = skcipher_walk_done(&walk, nbytes); + nbytes = walk.nbytes; + } + +- glue_fpu_end(fpu_enabled); +- + return err; + } + EXPORT_SYMBOL_GPL(glue_xts_req_128bit); diff --git a/debian/patches/features/all/rt/crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch b/debian/patches/features/all/rt/crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch new file mode 100644 index 000000000..c29cd4d75 --- /dev/null +++ b/debian/patches/features/all/rt/crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch @@ -0,0 +1,79 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 26 Jul 2018 18:52:00 +0200 +Subject: [PATCH] crypto: cryptd - add a lock instead + preempt_disable/local_bh_disable +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +cryptd has a per-CPU lock which protected with local_bh_disable() and +preempt_disable(). +Add an explicit spin_lock to make the locking context more obvious and +visible to lockdep. Since it is a per-CPU lock, there should be no lock +contention on the actual spinlock. +There is a small race-window where we could be migrated to another CPU +after the cpu_queue has been obtain. This is not a problem because the +actual ressource is protected by the spinlock. + +Signed-off-by: Sebastian Andrzej Siewior +--- + crypto/cryptd.c | 19 +++++++++---------- + 1 file changed, 9 insertions(+), 10 deletions(-) + +--- a/crypto/cryptd.c ++++ b/crypto/cryptd.c +@@ -39,6 +39,7 @@ MODULE_PARM_DESC(cryptd_max_cpu_qlen, "S + struct cryptd_cpu_queue { + struct crypto_queue queue; + struct work_struct work; ++ spinlock_t qlock; + }; + + struct cryptd_queue { +@@ -117,6 +118,7 @@ static int cryptd_init_queue(struct cryp + cpu_queue = per_cpu_ptr(queue->cpu_queue, cpu); + crypto_init_queue(&cpu_queue->queue, max_cpu_qlen); + INIT_WORK(&cpu_queue->work, cryptd_queue_worker); ++ spin_lock_init(&cpu_queue->qlock); + } + pr_info("cryptd: max_cpu_qlen set to %d\n", max_cpu_qlen); + return 0; +@@ -141,8 +143,10 @@ static int cryptd_enqueue_request(struct + struct cryptd_cpu_queue *cpu_queue; + atomic_t *refcnt; + +- cpu = get_cpu(); +- cpu_queue = this_cpu_ptr(queue->cpu_queue); ++ cpu_queue = raw_cpu_ptr(queue->cpu_queue); ++ spin_lock_bh(&cpu_queue->qlock); ++ cpu = smp_processor_id(); ++ + err = crypto_enqueue_request(&cpu_queue->queue, request); + + refcnt = crypto_tfm_ctx(request->tfm); +@@ -158,7 +162,7 @@ static int cryptd_enqueue_request(struct + atomic_inc(refcnt); + + out_put_cpu: +- put_cpu(); ++ spin_unlock_bh(&cpu_queue->qlock); + + return err; + } +@@ -174,16 +178,11 @@ static void cryptd_queue_worker(struct w + cpu_queue = container_of(work, struct cryptd_cpu_queue, work); + /* + * Only handle one request at a time to avoid hogging crypto workqueue. +- * preempt_disable/enable is used to prevent being preempted by +- * cryptd_enqueue_request(). local_bh_disable/enable is used to prevent +- * cryptd_enqueue_request() being accessed from software interrupts. + */ +- local_bh_disable(); +- preempt_disable(); ++ spin_lock_bh(&cpu_queue->qlock); + backlog = crypto_get_backlog(&cpu_queue->queue); + req = crypto_dequeue_request(&cpu_queue->queue); +- preempt_enable(); +- local_bh_enable(); ++ spin_unlock_bh(&cpu_queue->qlock); + + if (!req) + return; diff --git a/debian/patches/features/all/rt/crypto-limit-more-FPU-enabled-sections.patch b/debian/patches/features/all/rt/crypto-limit-more-FPU-enabled-sections.patch new file mode 100644 index 000000000..03895d132 --- /dev/null +++ b/debian/patches/features/all/rt/crypto-limit-more-FPU-enabled-sections.patch @@ -0,0 +1,98 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 30 Nov 2017 13:40:10 +0100 +Subject: [PATCH] crypto: limit more FPU-enabled sections +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Those crypto drivers use SSE/AVX/… for their crypto work and in order to +do so in kernel they need to enable the "FPU" in kernel mode which +disables preemption. +There are two problems with the way they are used: +- the while loop which processes X bytes may create latency spikes and + should be avoided or limited. +- the cipher-walk-next part may allocate/free memory and may use + kmap_atomic(). + +The whole kernel_fpu_begin()/end() processing isn't probably that cheap. +It most likely makes sense to process as much of those as possible in one +go. The new *_fpu_sched_rt() schedules only if a RT task is pending. + +Probably we should measure the performance those ciphers in pure SW +mode and with this optimisations to see if it makes sense to keep them +for RT. + +This kernel_fpu_resched() makes the code more preemptible which might hurt +performance. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/crypto/chacha20_glue.c | 9 +++++---- + arch/x86/include/asm/fpu/api.h | 1 + + arch/x86/kernel/fpu/core.c | 12 ++++++++++++ + 3 files changed, 18 insertions(+), 4 deletions(-) + +--- a/arch/x86/crypto/chacha20_glue.c ++++ b/arch/x86/crypto/chacha20_glue.c +@@ -81,23 +81,24 @@ static int chacha20_simd(struct skcipher + + crypto_chacha20_init(state, ctx, walk.iv); + +- kernel_fpu_begin(); +- + while (walk.nbytes >= CHACHA20_BLOCK_SIZE) { ++ kernel_fpu_begin(); ++ + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + rounddown(walk.nbytes, CHACHA20_BLOCK_SIZE)); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, + walk.nbytes % CHACHA20_BLOCK_SIZE); + } + + if (walk.nbytes) { ++ kernel_fpu_begin(); + chacha20_dosimd(state, walk.dst.virt.addr, walk.src.virt.addr, + walk.nbytes); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, 0); + } + +- kernel_fpu_end(); +- + return err; + } + +--- a/arch/x86/include/asm/fpu/api.h ++++ b/arch/x86/include/asm/fpu/api.h +@@ -25,6 +25,7 @@ extern void __kernel_fpu_begin(void); + extern void __kernel_fpu_end(void); + extern void kernel_fpu_begin(void); + extern void kernel_fpu_end(void); ++extern void kernel_fpu_resched(void); + extern bool irq_fpu_usable(void); + + /* +--- a/arch/x86/kernel/fpu/core.c ++++ b/arch/x86/kernel/fpu/core.c +@@ -137,6 +137,18 @@ void kernel_fpu_end(void) + } + EXPORT_SYMBOL_GPL(kernel_fpu_end); + ++void kernel_fpu_resched(void) ++{ ++ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu)); ++ ++ if (should_resched(PREEMPT_OFFSET)) { ++ kernel_fpu_end(); ++ cond_resched(); ++ kernel_fpu_begin(); ++ } ++} ++EXPORT_SYMBOL_GPL(kernel_fpu_resched); ++ + /* + * Save the FPU state (mark it for reload if necessary): + * diff --git a/debian/patches/features/all/rt/crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch b/debian/patches/features/all/rt/crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch new file mode 100644 index 000000000..b0595f6bc --- /dev/null +++ b/debian/patches/features/all/rt/crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch @@ -0,0 +1,77 @@ +From: Mike Galbraith +Date: Wed, 11 Jul 2018 17:14:47 +0200 +Subject: [PATCH] crypto: scompress - serialize RT percpu scratch buffer + access with a local lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +| BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:974 +| in_atomic(): 1, irqs_disabled(): 0, pid: 1401, name: cryptomgr_test +| Preemption disabled at: +| [] scomp_acomp_comp_decomp+0x34/0x1a0 +| CPU: 21 PID: 1401 Comm: cryptomgr_test Tainted: G W 4.16.18-rt9-rt #1 +| Hardware name: www.cavium.com crb-1s/crb-1s, BIOS 0.3 Apr 25 2017 +| Call trace: +| dump_backtrace+0x0/0x1c8 +| show_stack+0x24/0x30 +| dump_stack+0xac/0xe8 +| ___might_sleep+0x124/0x188 +| rt_spin_lock+0x40/0x88 +| zip_load_instr+0x44/0x170 [thunderx_zip] +| zip_deflate+0x184/0x378 [thunderx_zip] +| zip_compress+0xb0/0x130 [thunderx_zip] +| zip_scomp_compress+0x48/0x60 [thunderx_zip] +| scomp_acomp_comp_decomp+0xd8/0x1a0 +| scomp_acomp_compress+0x24/0x30 +| test_acomp+0x15c/0x558 +| alg_test_comp+0xc0/0x128 +| alg_test.part.6+0x120/0x2c0 +| alg_test+0x6c/0xa0 +| cryptomgr_test+0x50/0x58 +| kthread+0x134/0x138 +| ret_from_fork+0x10/0x18 + +Mainline disables preemption to serialize percpu scratch buffer access, +causing the splat above. Serialize with a local lock for RT instead. + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + crypto/scompress.c | 6 ++++-- + 1 file changed, 4 insertions(+), 2 deletions(-) + +--- a/crypto/scompress.c ++++ b/crypto/scompress.c +@@ -24,6 +24,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -34,6 +35,7 @@ static void * __percpu *scomp_src_scratc + static void * __percpu *scomp_dst_scratches; + static int scomp_scratch_users; + static DEFINE_MUTEX(scomp_lock); ++static DEFINE_LOCAL_IRQ_LOCK(scomp_scratches_lock); + + #ifdef CONFIG_NET + static int crypto_scomp_report(struct sk_buff *skb, struct crypto_alg *alg) +@@ -146,7 +148,7 @@ static int scomp_acomp_comp_decomp(struc + void **tfm_ctx = acomp_tfm_ctx(tfm); + struct crypto_scomp *scomp = *tfm_ctx; + void **ctx = acomp_request_ctx(req); +- const int cpu = get_cpu(); ++ const int cpu = local_lock_cpu(scomp_scratches_lock); + u8 *scratch_src = *per_cpu_ptr(scomp_src_scratches, cpu); + u8 *scratch_dst = *per_cpu_ptr(scomp_dst_scratches, cpu); + int ret; +@@ -181,7 +183,7 @@ static int scomp_acomp_comp_decomp(struc + 1); + } + out: +- put_cpu(); ++ local_unlock_cpu(scomp_scratches_lock); + return ret; + } + diff --git a/debian/patches/features/all/rt/debugobjects-rt.patch b/debian/patches/features/all/rt/debugobjects-rt.patch new file mode 100644 index 000000000..045c5b94b --- /dev/null +++ b/debian/patches/features/all/rt/debugobjects-rt.patch @@ -0,0 +1,26 @@ +Subject: debugobjects: Make RT aware +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:41:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Avoid filling the pool / allocating memory with irqs off(). + +Signed-off-by: Thomas Gleixner +--- + lib/debugobjects.c | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/lib/debugobjects.c ++++ b/lib/debugobjects.c +@@ -374,7 +374,10 @@ static void + struct debug_obj *obj; + unsigned long flags; + +- fill_pool(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (preempt_count() == 0 && !irqs_disabled()) ++#endif ++ fill_pool(); + + db = get_bucket((unsigned long) addr); + diff --git a/debian/patches/features/all/rt/dm-rq-remove-BUG_ON-irqs_disabled-check.patch b/debian/patches/features/all/rt/dm-rq-remove-BUG_ON-irqs_disabled-check.patch new file mode 100644 index 000000000..69939cb63 --- /dev/null +++ b/debian/patches/features/all/rt/dm-rq-remove-BUG_ON-irqs_disabled-check.patch @@ -0,0 +1,31 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 27 Mar 2018 16:24:15 +0200 +Subject: [PATCH] dm rq: remove BUG_ON(!irqs_disabled) check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In commit 052189a2ec95 ("dm: remove superfluous irq disablement in +dm_request_fn") the spin_lock_irq() was replaced with spin_lock() + a +check for disabled interrupts. Later the locking part was removed in +commit 2eb6e1e3aa87 ("dm: submit stacked requests in irq enabled +context") but the BUG_ON() check remained. + +Since the original purpose for the "are-irqs-off" check is gone (the +->queue_lock has been removed) remove it. + +Cc: Keith Busch +Cc: Mike Snitzer +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/md/dm-rq.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/drivers/md/dm-rq.c ++++ b/drivers/md/dm-rq.c +@@ -688,7 +688,6 @@ static void dm_old_request_fn(struct req + /* Establish tio->ti before queuing work (map_tio_request) */ + tio->ti = ti; + kthread_queue_work(&md->kworker, &tio->work); +- BUG_ON(!irqs_disabled()); + } + } + diff --git a/debian/patches/features/all/rt/drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch b/debian/patches/features/all/rt/drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch new file mode 100644 index 000000000..3bd76e347 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch @@ -0,0 +1,86 @@ +From: Mike Galbraith +Date: Thu, 31 Mar 2016 04:08:28 +0200 +Subject: [PATCH] drivers/block/zram: Replace bit spinlocks with rtmutex + for -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +They're nondeterministic, and lead to ___might_sleep() splats in -rt. +OTOH, they're a lot less wasteful than an rtmutex per page. + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/block/zram/zram_drv.c | 28 ++++++++++++++++++++++++++++ + drivers/block/zram/zram_drv.h | 3 +++ + 2 files changed, 31 insertions(+) + +--- a/drivers/block/zram/zram_drv.c ++++ b/drivers/block/zram/zram_drv.c +@@ -53,6 +53,30 @@ static size_t huge_class_size; + + static void zram_free_page(struct zram *zram, size_t index); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) ++{ ++ size_t index; ++ ++ for (index = 0; index < num_pages; index++) ++ spin_lock_init(&zram->table[index].lock); ++} ++ ++static void zram_slot_lock(struct zram *zram, u32 index) ++{ ++ spin_lock(&zram->table[index].lock); ++ __set_bit(ZRAM_LOCK, &zram->table[index].value); ++} ++ ++static void zram_slot_unlock(struct zram *zram, u32 index) ++{ ++ __clear_bit(ZRAM_LOCK, &zram->table[index].value); ++ spin_unlock(&zram->table[index].lock); ++} ++ ++#else ++static void zram_meta_init_table_locks(struct zram *zram, size_t num_pages) { } ++ + static void zram_slot_lock(struct zram *zram, u32 index) + { + bit_spin_lock(ZRAM_LOCK, &zram->table[index].value); +@@ -62,6 +86,7 @@ static void zram_slot_unlock(struct zram + { + bit_spin_unlock(ZRAM_LOCK, &zram->table[index].value); + } ++#endif + + static inline bool init_done(struct zram *zram) + { +@@ -880,6 +905,8 @@ static DEVICE_ATTR_RO(io_stat); + static DEVICE_ATTR_RO(mm_stat); + static DEVICE_ATTR_RO(debug_stat); + ++ ++ + static void zram_meta_free(struct zram *zram, u64 disksize) + { + size_t num_pages = disksize >> PAGE_SHIFT; +@@ -910,6 +937,7 @@ static bool zram_meta_alloc(struct zram + + if (!huge_class_size) + huge_class_size = zs_huge_class_size(zram->mem_pool); ++ zram_meta_init_table_locks(zram, num_pages); + return true; + } + +--- a/drivers/block/zram/zram_drv.h ++++ b/drivers/block/zram/zram_drv.h +@@ -61,6 +61,9 @@ struct zram_table_entry { + unsigned long element; + }; + unsigned long value; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t lock; ++#endif + #ifdef CONFIG_ZRAM_MEMORY_TRACKING + ktime_t ac_time; + #endif diff --git a/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch b/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch new file mode 100644 index 000000000..b52edb387 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-tty-fix-omap-lock-crap.patch @@ -0,0 +1,43 @@ +Subject: tty/serial/omap: Make the locking RT aware +From: Thomas Gleixner +Date: Thu, 28 Jul 2011 13:32:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the +optimsation we are looking for. Redo it to make it work on -RT and +non-RT. + +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/omap-serial.c | 12 ++++-------- + 1 file changed, 4 insertions(+), 8 deletions(-) + +--- a/drivers/tty/serial/omap-serial.c ++++ b/drivers/tty/serial/omap-serial.c +@@ -1307,13 +1307,10 @@ serial_omap_console_write(struct console + + pm_runtime_get_sync(up->dev); + +- local_irq_save(flags); +- if (up->port.sysrq) +- locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock(&up->port.lock); ++ if (up->port.sysrq || oops_in_progress) ++ locked = spin_trylock_irqsave(&up->port.lock, flags); + else +- spin_lock(&up->port.lock); ++ spin_lock_irqsave(&up->port.lock, flags); + + /* + * First save the IER then disable the interrupts +@@ -1342,8 +1339,7 @@ serial_omap_console_write(struct console + pm_runtime_mark_last_busy(up->dev); + pm_runtime_put_autosuspend(up->dev); + if (locked) +- spin_unlock(&up->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&up->port.lock, flags); + } + + static int __init diff --git a/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch b/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch new file mode 100644 index 000000000..333aa4e24 --- /dev/null +++ b/debian/patches/features/all/rt/drivers-tty-pl011-irq-disable-madness.patch @@ -0,0 +1,48 @@ +Subject: tty/serial/pl011: Make the locking work on RT +From: Thomas Gleixner +Date: Tue, 08 Jan 2013 21:36:51 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The lock is a sleeping lock and local_irq_save() is not the optimsation +we are looking for. Redo it to make it work on -RT and non-RT. + +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/amba-pl011.c | 15 ++++++++++----- + 1 file changed, 10 insertions(+), 5 deletions(-) + +--- a/drivers/tty/serial/amba-pl011.c ++++ b/drivers/tty/serial/amba-pl011.c +@@ -2216,13 +2216,19 @@ pl011_console_write(struct console *co, + + clk_enable(uap->clk); + +- local_irq_save(flags); ++ /* ++ * local_irq_save(flags); ++ * ++ * This local_irq_save() is nonsense. If we come in via sysrq ++ * handling then interrupts are already disabled. Aside of ++ * that the port.sysrq check is racy on SMP regardless. ++ */ + if (uap->port.sysrq) + locked = 0; + else if (oops_in_progress) +- locked = spin_trylock(&uap->port.lock); ++ locked = spin_trylock_irqsave(&uap->port.lock, flags); + else +- spin_lock(&uap->port.lock); ++ spin_lock_irqsave(&uap->port.lock, flags); + + /* + * First save the CR then disable the interrupts +@@ -2248,8 +2254,7 @@ pl011_console_write(struct console *co, + pl011_write(old_cr, uap, REG_CR); + + if (locked) +- spin_unlock(&uap->port.lock); +- local_irq_restore(flags); ++ spin_unlock_irqrestore(&uap->port.lock, flags); + + clk_disable(uap->clk); + } diff --git a/debian/patches/features/all/rt/drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch b/debian/patches/features/all/rt/drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch new file mode 100644 index 000000000..c63401cae --- /dev/null +++ b/debian/patches/features/all/rt/drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch @@ -0,0 +1,97 @@ +From: Mike Galbraith +Date: Thu, 20 Oct 2016 11:15:22 +0200 +Subject: [PATCH] drivers/zram: Don't disable preemption in + zcomp_stream_get/put() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In v4.7, the driver switched to percpu compression streams, disabling +preemption via get/put_cpu_ptr(). Use a per-zcomp_strm lock here. We +also have to fix an lock order issue in zram_decompress_page() such +that zs_map_object() nests inside of zcomp_stream_put() as it does in +zram_bvec_write(). + +Signed-off-by: Mike Galbraith +[bigeasy: get_locked_var() -> per zcomp_strm lock] +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/block/zram/zcomp.c | 12 ++++++++++-- + drivers/block/zram/zcomp.h | 1 + + drivers/block/zram/zram_drv.c | 5 +++-- + 3 files changed, 14 insertions(+), 4 deletions(-) + +--- a/drivers/block/zram/zcomp.c ++++ b/drivers/block/zram/zcomp.c +@@ -116,12 +116,19 @@ ssize_t zcomp_available_show(const char + + struct zcomp_strm *zcomp_stream_get(struct zcomp *comp) + { +- return *get_cpu_ptr(comp->stream); ++ struct zcomp_strm *zstrm; ++ ++ zstrm = *this_cpu_ptr(comp->stream); ++ spin_lock(&zstrm->zcomp_lock); ++ return zstrm; + } + + void zcomp_stream_put(struct zcomp *comp) + { +- put_cpu_ptr(comp->stream); ++ struct zcomp_strm *zstrm; ++ ++ zstrm = *this_cpu_ptr(comp->stream); ++ spin_unlock(&zstrm->zcomp_lock); + } + + int zcomp_compress(struct zcomp_strm *zstrm, +@@ -171,6 +178,7 @@ int zcomp_cpu_up_prepare(unsigned int cp + pr_err("Can't allocate a compression stream\n"); + return -ENOMEM; + } ++ spin_lock_init(&zstrm->zcomp_lock); + *per_cpu_ptr(comp->stream, cpu) = zstrm; + return 0; + } +--- a/drivers/block/zram/zcomp.h ++++ b/drivers/block/zram/zcomp.h +@@ -14,6 +14,7 @@ struct zcomp_strm { + /* compression/decompression buffer */ + void *buffer; + struct crypto_comp *tfm; ++ spinlock_t zcomp_lock; + }; + + /* dynamic per-device compression frontend */ +--- a/drivers/block/zram/zram_drv.c ++++ b/drivers/block/zram/zram_drv.c +@@ -996,6 +996,7 @@ static int __zram_bvec_read(struct zram + unsigned long handle; + unsigned int size; + void *src, *dst; ++ struct zcomp_strm *zstrm; + + if (zram_wb_enabled(zram)) { + zram_slot_lock(zram, index); +@@ -1030,6 +1031,7 @@ static int __zram_bvec_read(struct zram + + size = zram_get_obj_size(zram, index); + ++ zstrm = zcomp_stream_get(zram->comp); + src = zs_map_object(zram->mem_pool, handle, ZS_MM_RO); + if (size == PAGE_SIZE) { + dst = kmap_atomic(page); +@@ -1037,14 +1039,13 @@ static int __zram_bvec_read(struct zram + kunmap_atomic(dst); + ret = 0; + } else { +- struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp); + + dst = kmap_atomic(page); + ret = zcomp_decompress(zstrm, src, size, dst); + kunmap_atomic(dst); +- zcomp_stream_put(zram->comp); + } + zs_unmap_object(zram->mem_pool, handle); ++ zcomp_stream_put(zram->comp); + zram_slot_unlock(zram, index); + + /* Should NEVER happen. Return bio error if it does. */ diff --git a/debian/patches/features/all/rt/drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch b/debian/patches/features/all/rt/drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch new file mode 100644 index 000000000..eb956b2cb --- /dev/null +++ b/debian/patches/features/all/rt/drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch @@ -0,0 +1,38 @@ +From: Mike Galbraith +Date: Wed, 23 Aug 2017 11:57:29 +0200 +Subject: [PATCH] drivers/zram: fix zcomp_stream_get() smp_processor_id() use + in preemptible code +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Use get_local_ptr() instead this_cpu_ptr() to avoid a warning regarding +smp_processor_id() in preemptible code. +raw_cpu_ptr() would be fine, too because the per-CPU data structure is +protected with a spin lock so it does not matter much if we take the +other one. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/block/zram/zcomp.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/drivers/block/zram/zcomp.c ++++ b/drivers/block/zram/zcomp.c +@@ -118,7 +118,7 @@ struct zcomp_strm *zcomp_stream_get(stru + { + struct zcomp_strm *zstrm; + +- zstrm = *this_cpu_ptr(comp->stream); ++ zstrm = *get_local_ptr(comp->stream); + spin_lock(&zstrm->zcomp_lock); + return zstrm; + } +@@ -129,6 +129,7 @@ void zcomp_stream_put(struct zcomp *comp + + zstrm = *this_cpu_ptr(comp->stream); + spin_unlock(&zstrm->zcomp_lock); ++ put_local_ptr(zstrm); + } + + int zcomp_compress(struct zcomp_strm *zstrm, diff --git a/debian/patches/features/all/rt/drmi915_Use_local_lockunlock_irq()_in_intel_pipe_update_startend().patch b/debian/patches/features/all/rt/drmi915_Use_local_lockunlock_irq()_in_intel_pipe_update_startend().patch new file mode 100644 index 000000000..5bf61dfa4 --- /dev/null +++ b/debian/patches/features/all/rt/drmi915_Use_local_lockunlock_irq()_in_intel_pipe_update_startend().patch @@ -0,0 +1,113 @@ +Subject: drm,i915: Use local_lock/unlock_irq() in intel_pipe_update_start/end() +From: Mike Galbraith +Date: Sat, 27 Feb 2016 09:01:42 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + + +[ 8.014039] BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:918 +[ 8.014041] in_atomic(): 0, irqs_disabled(): 1, pid: 78, name: kworker/u4:4 +[ 8.014045] CPU: 1 PID: 78 Comm: kworker/u4:4 Not tainted 4.1.7-rt7 #5 +[ 8.014055] Workqueue: events_unbound async_run_entry_fn +[ 8.014059] 0000000000000000 ffff880037153748 ffffffff815f32c9 0000000000000002 +[ 8.014063] ffff88013a50e380 ffff880037153768 ffffffff815ef075 ffff8800372c06c8 +[ 8.014066] ffff8800372c06c8 ffff880037153778 ffffffff8107c0b3 ffff880037153798 +[ 8.014067] Call Trace: +[ 8.014074] [] dump_stack+0x4a/0x61 +[ 8.014078] [] ___might_sleep.part.93+0xe9/0xee +[ 8.014082] [] ___might_sleep+0x53/0x80 +[ 8.014086] [] rt_spin_lock+0x24/0x50 +[ 8.014090] [] prepare_to_wait+0x2b/0xa0 +[ 8.014152] [] intel_pipe_update_start+0x17c/0x300 [i915] +[ 8.014156] [] ? prepare_to_wait_event+0x120/0x120 +[ 8.014201] [] intel_begin_crtc_commit+0x166/0x1e0 [i915] +[ 8.014215] [] drm_atomic_helper_commit_planes+0x5d/0x1a0 [drm_kms_helper] +[ 8.014260] [] intel_atomic_commit+0xab/0xf0 [i915] +[ 8.014288] [] drm_atomic_commit+0x37/0x60 [drm] +[ 8.014298] [] drm_atomic_helper_plane_set_property+0x8d/0xd0 [drm_kms_helper] +[ 8.014301] [] ? __ww_mutex_lock+0x39/0x40 +[ 8.014319] [] drm_mode_plane_set_obj_prop+0x2d/0x90 [drm] +[ 8.014328] [] restore_fbdev_mode+0x6b/0xf0 [drm_kms_helper] +[ 8.014337] [] drm_fb_helper_restore_fbdev_mode_unlocked+0x29/0x80 [drm_kms_helper] +[ 8.014346] [] drm_fb_helper_set_par+0x22/0x50 [drm_kms_helper] +[ 8.014390] [] intel_fbdev_set_par+0x1a/0x60 [i915] +[ 8.014394] [] fbcon_init+0x4f4/0x580 +[ 8.014398] [] visual_init+0xbc/0x120 +[ 8.014401] [] do_bind_con_driver+0x163/0x330 +[ 8.014405] [] do_take_over_console+0x11c/0x1c0 +[ 8.014408] [] do_fbcon_takeover+0x63/0xd0 +[ 8.014410] [] fbcon_event_notify+0x785/0x8d0 +[ 8.014413] [] ? __might_sleep+0x4d/0x90 +[ 8.014416] [] notifier_call_chain+0x4e/0x80 +[ 8.014419] [] __blocking_notifier_call_chain+0x4d/0x70 +[ 8.014422] [] blocking_notifier_call_chain+0x16/0x20 +[ 8.014425] [] fb_notifier_call_chain+0x1b/0x20 +[ 8.014428] [] register_framebuffer+0x21a/0x350 +[ 8.014439] [] drm_fb_helper_initial_config+0x274/0x3e0 [drm_kms_helper] +[ 8.014483] [] intel_fbdev_initial_config+0x1b/0x20 [i915] +[ 8.014486] [] async_run_entry_fn+0x4c/0x160 +[ 8.014490] [] process_one_work+0x14a/0x470 +[ 8.014493] [] worker_thread+0x169/0x4c0 +[ 8.014496] [] ? process_one_work+0x470/0x470 +[ 8.014499] [] kthread+0xc6/0xe0 +[ 8.014502] [] ? queue_work_on+0x80/0x110 +[ 8.014506] [] ? kthread_worker_fn+0x1c0/0x1c0 + +Signed-off-by: Mike Galbraith +Cc: Sebastian Andrzej Siewior +Cc: linux-rt-users +Signed-off-by: Thomas Gleixner +--- + drivers/gpu/drm/i915/intel_sprite.c | 11 +++++++---- + 1 file changed, 7 insertions(+), 4 deletions(-) + +--- a/drivers/gpu/drm/i915/intel_sprite.c ++++ b/drivers/gpu/drm/i915/intel_sprite.c +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + #include "intel_drv.h" + #include "intel_frontbuffer.h" + #include +@@ -74,6 +75,8 @@ int intel_usecs_to_scanlines(const struc + #define VBLANK_EVASION_TIME_US 100 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock); ++ + /** + * intel_pipe_update_start() - start update of a set of display registers + * @new_crtc_state: the new crtc state +@@ -107,7 +110,7 @@ void intel_pipe_update_start(const struc + VBLANK_EVASION_TIME_US); + max = vblank_start - 1; + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + + if (min <= 0 || max <= 0) + return; +@@ -137,11 +140,11 @@ void intel_pipe_update_start(const struc + break; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + timeout = schedule_timeout(timeout); + +- local_irq_disable(); ++ local_lock_irq(pipe_update_lock); + } + + finish_wait(wq, &wait); +@@ -206,7 +209,7 @@ void intel_pipe_update_end(struct intel_ + new_crtc_state->base.event = NULL; + } + +- local_irq_enable(); ++ local_unlock_irq(pipe_update_lock); + + if (intel_vgpu_active(dev_priv)) + return; diff --git a/debian/patches/features/all/rt/drmradeoni915_Use_preempt_disableenable_rt()_where_recommended.patch b/debian/patches/features/all/rt/drmradeoni915_Use_preempt_disableenable_rt()_where_recommended.patch new file mode 100644 index 000000000..fba0845a1 --- /dev/null +++ b/debian/patches/features/all/rt/drmradeoni915_Use_preempt_disableenable_rt()_where_recommended.patch @@ -0,0 +1,52 @@ +Subject: drm,radeon,i915: Use preempt_disable/enable_rt() where recommended +From: Mike Galbraith +Date: Sat, 27 Feb 2016 08:09:11 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +DRM folks identified the spots, so use them. + +Signed-off-by: Mike Galbraith +Cc: Sebastian Andrzej Siewior +Cc: linux-rt-users +Signed-off-by: Thomas Gleixner +--- + drivers/gpu/drm/i915/i915_irq.c | 2 ++ + drivers/gpu/drm/radeon/radeon_display.c | 2 ++ + 2 files changed, 4 insertions(+) + +--- a/drivers/gpu/drm/i915/i915_irq.c ++++ b/drivers/gpu/drm/i915/i915_irq.c +@@ -1009,6 +1009,7 @@ static bool i915_get_crtc_scanoutpos(str + spin_lock_irqsave(&dev_priv->uncore.lock, irqflags); + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1060,6 +1061,7 @@ static bool i915_get_crtc_scanoutpos(str + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags); + +--- a/drivers/gpu/drm/radeon/radeon_display.c ++++ b/drivers/gpu/drm/radeon/radeon_display.c +@@ -1813,6 +1813,7 @@ int radeon_get_crtc_scanoutpos(struct dr + struct radeon_device *rdev = dev->dev_private; + + /* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_disable_rt(); + + /* Get optional system timestamp before query. */ + if (stime) +@@ -1905,6 +1906,7 @@ int radeon_get_crtc_scanoutpos(struct dr + *etime = ktime_get(); + + /* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */ ++ preempt_enable_rt(); + + /* Decode into vertical and horizontal scanout position. */ + *vpos = position & 0x1fff; diff --git a/debian/patches/features/all/rt/efi-Allow-efi-runtime.patch b/debian/patches/features/all/rt/efi-Allow-efi-runtime.patch new file mode 100644 index 000000000..8af80e908 --- /dev/null +++ b/debian/patches/features/all/rt/efi-Allow-efi-runtime.patch @@ -0,0 +1,27 @@ +From 667af2f3d8ccf947fe7c9dac0b59b175963163ba Mon Sep 17 00:00:00 2001 +From: Sebastian Andrzej Siewior +Date: Thu, 26 Jul 2018 15:06:10 +0200 +Subject: [PATCH] efi: Allow efi=runtime +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In case the option "efi=noruntime" is default at built-time, the user +could overwrite its sate by `efi=runtime' and allow it again. + +Acked-by: Ard Biesheuvel +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/firmware/efi/efi.c | 3 +++ + 1 file changed, 3 insertions(+) + +--- a/drivers/firmware/efi/efi.c ++++ b/drivers/firmware/efi/efi.c +@@ -110,6 +110,9 @@ static int __init parse_efi_cmdline(char + if (parse_option_str(str, "noruntime")) + disable_runtime = true; + ++ if (parse_option_str(str, "runtime")) ++ disable_runtime = false; ++ + return 0; + } + early_param("efi", parse_efi_cmdline); diff --git a/debian/patches/features/all/rt/efi-Disable-runtime-services-on-RT.patch b/debian/patches/features/all/rt/efi-Disable-runtime-services-on-RT.patch new file mode 100644 index 000000000..bfff9fd4c --- /dev/null +++ b/debian/patches/features/all/rt/efi-Disable-runtime-services-on-RT.patch @@ -0,0 +1,40 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 26 Jul 2018 15:03:16 +0200 +Subject: [PATCH] efi: Disable runtime services on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Based on meassurements the EFI functions get_variable / +get_next_variable take up to 2us which looks okay. +The functions get_time, set_time take around 10ms. Those 10ms are too +much. Even one ms would be too much. +Ard mentioned that SetVariable might even trigger larger latencies if +the firware will erase flash blocks on NOR. + +The time-functions are used by efi-rtc and can be triggered during +runtimed (either via explicit read/write or ntp sync). + +The variable write could be used by pstore. +These functions can be disabled without much of a loss. The poweroff / +reboot hooks may be provided by PSCI. + +Disable EFI's runtime wrappers. + +This was observed on "EFI v2.60 by SoftIron Overdrive 1000". + +Acked-by: Ard Biesheuvel +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/firmware/efi/efi.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/firmware/efi/efi.c ++++ b/drivers/firmware/efi/efi.c +@@ -84,7 +84,7 @@ struct mm_struct efi_mm = { + .mmlist = LIST_HEAD_INIT(efi_mm.mmlist), + }; + +-static bool disable_runtime; ++static bool disable_runtime = IS_ENABLED(CONFIG_PREEMPT_RT_BASE); + static int __init setup_noefi(char *arg) + { + disable_runtime = true; diff --git a/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch b/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch new file mode 100644 index 000000000..be464271c --- /dev/null +++ b/debian/patches/features/all/rt/epoll-use-get-cpu-light.patch @@ -0,0 +1,31 @@ +Subject: fs/epoll: Do not disable preemption on RT +From: Thomas Gleixner +Date: Fri, 08 Jul 2011 16:35:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +ep_call_nested() takes a sleeping lock so we can't disable preemption. +The light version is enough since ep_call_nested() doesn't mind beeing +invoked twice on the same CPU. + +Signed-off-by: Thomas Gleixner +--- + fs/eventpoll.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/fs/eventpoll.c ++++ b/fs/eventpoll.c +@@ -563,12 +563,12 @@ static int ep_poll_wakeup_proc(void *pri + + static void ep_poll_safewake(wait_queue_head_t *wq) + { +- int this_cpu = get_cpu(); ++ int this_cpu = get_cpu_light(); + + ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS, + ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu); + +- put_cpu(); ++ put_cpu_light(); + } + + #else diff --git a/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch b/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch new file mode 100644 index 000000000..f78899a00 --- /dev/null +++ b/debian/patches/features/all/rt/fs-aio-simple-simple-work.patch @@ -0,0 +1,83 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 16 Feb 2015 18:49:10 +0100 +Subject: fs/aio: simple simple work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:768 +|in_atomic(): 1, irqs_disabled(): 0, pid: 26, name: rcuos/2 +|2 locks held by rcuos/2/26: +| #0: (rcu_callback){.+.+..}, at: [] rcu_nocb_kthread+0x1e2/0x380 +| #1: (rcu_read_lock_sched){.+.+..}, at: [] percpu_ref_kill_rcu+0xa6/0x1c0 +|Preemption disabled at:[] rcu_nocb_kthread+0x263/0x380 +|Call Trace: +| [] dump_stack+0x4e/0x9c +| [] __might_sleep+0xfb/0x170 +| [] rt_spin_lock+0x24/0x70 +| [] free_ioctx_users+0x30/0x130 +| [] percpu_ref_kill_rcu+0x1b4/0x1c0 +| [] rcu_nocb_kthread+0x263/0x380 +| [] kthread+0xd6/0xf0 +| [] ret_from_fork+0x7c/0xb0 + +replace this preempt_disable() friendly swork. + +Reported-By: Mike Galbraith +Suggested-by: Benjamin LaHaise +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/aio.c | 15 +++++++++++++-- + 1 file changed, 13 insertions(+), 2 deletions(-) + +--- a/fs/aio.c ++++ b/fs/aio.c +@@ -40,6 +40,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -118,6 +119,7 @@ struct kioctx { + long nr_pages; + + struct rcu_work free_rwork; /* see free_ioctx() */ ++ struct swork_event free_swork; /* see free_ioctx() */ + + /* + * signals when all in-flight requests are done +@@ -256,6 +258,7 @@ static int __init aio_setup(void) + .mount = aio_mount, + .kill_sb = kill_anon_super, + }; ++ BUG_ON(swork_get()); + aio_mnt = kern_mount(&aio_fs); + if (IS_ERR(aio_mnt)) + panic("Failed to create aio fs mount."); +@@ -597,9 +600,9 @@ static void free_ioctx_reqs(struct percp + * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - + * now it's safe to cancel any that need to be. + */ +-static void free_ioctx_users(struct percpu_ref *ref) ++static void free_ioctx_users_work(struct swork_event *sev) + { +- struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ struct kioctx *ctx = container_of(sev, struct kioctx, free_swork); + struct aio_kiocb *req; + + spin_lock_irq(&ctx->ctx_lock); +@@ -617,6 +620,14 @@ static void free_ioctx_users(struct perc + percpu_ref_put(&ctx->reqs); + } + ++static void free_ioctx_users(struct percpu_ref *ref) ++{ ++ struct kioctx *ctx = container_of(ref, struct kioctx, users); ++ ++ INIT_SWORK(&ctx->free_swork, free_ioctx_users_work); ++ swork_queue(&ctx->free_swork); ++} ++ + static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) + { + unsigned i, new_nr; diff --git a/debian/patches/features/all/rt/fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-in.patch b/debian/patches/features/all/rt/fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-in.patch new file mode 100644 index 000000000..392894487 --- /dev/null +++ b/debian/patches/features/all/rt/fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-in.patch @@ -0,0 +1,54 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 13 Sep 2017 12:32:34 +0200 +Subject: [PATCH] fs/dcache: bring back explicit INIT_HLIST_BL_HEAD init +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Commit 3d375d78593c ("mm: update callers to use HASH_ZERO flag") removed +INIT_HLIST_BL_HEAD and uses the ZERO flag instead for the init. However +on RT we have also a spinlock which needs an init call so we can't use +that. + +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/dcache.c | 11 +++++++++++ + 1 file changed, 11 insertions(+) + +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -3116,6 +3116,8 @@ static int __init set_dhash_entries(char + + static void __init dcache_init_early(void) + { ++ unsigned int loop; ++ + /* If hashes are distributed across NUMA nodes, defer + * hash allocation until vmalloc space is available. + */ +@@ -3132,11 +3134,16 @@ static void __init dcache_init_early(voi + NULL, + 0, + 0); ++ ++ for (loop = 0; loop < (1U << d_hash_shift); loop++) ++ INIT_HLIST_BL_HEAD(dentry_hashtable + loop); ++ + d_hash_shift = 32 - d_hash_shift; + } + + static void __init dcache_init(void) + { ++ unsigned int loop; + /* + * A constructor could be added for stable state like the lists, + * but it is probably not worth it because of the cache nature +@@ -3160,6 +3167,10 @@ static void __init dcache_init(void) + NULL, + 0, + 0); ++ ++ for (loop = 0; loop < (1U << d_hash_shift); loop++) ++ INIT_HLIST_BL_HEAD(dentry_hashtable + loop); ++ + d_hash_shift = 32 - d_hash_shift; + } + diff --git a/debian/patches/features/all/rt/fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch b/debian/patches/features/all/rt/fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch new file mode 100644 index 000000000..48faa196c --- /dev/null +++ b/debian/patches/features/all/rt/fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch @@ -0,0 +1,119 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 20 Oct 2017 11:29:53 +0200 +Subject: [PATCH] fs/dcache: disable preemption on i_dir_seq's write side +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +i_dir_seq is an opencoded seqcounter. Based on the code it looks like we +could have two writers in parallel despite the fact that the d_lock is +held. The problem is that during the write process on RT the preemption +is still enabled and if this process is interrupted by a reader with RT +priority then we lock up. +To avoid that lock up I am disabling the preemption during the update. +The rename of i_dir_seq is here to ensure to catch new write sides in +future. + +Cc: stable-rt@vger.kernel.org +Reported-by: Oleg.Karfich@wago.com +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/dcache.c | 12 +++++++----- + fs/inode.c | 2 +- + fs/libfs.c | 6 ++++-- + include/linux/fs.h | 2 +- + 4 files changed, 13 insertions(+), 9 deletions(-) + +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -2431,9 +2431,10 @@ EXPORT_SYMBOL(d_rehash); + static inline unsigned start_dir_add(struct inode *dir) + { + ++ preempt_disable_rt(); + for (;;) { +- unsigned n = dir->i_dir_seq; +- if (!(n & 1) && cmpxchg(&dir->i_dir_seq, n, n + 1) == n) ++ unsigned n = dir->__i_dir_seq; ++ if (!(n & 1) && cmpxchg(&dir->__i_dir_seq, n, n + 1) == n) + return n; + cpu_relax(); + } +@@ -2441,7 +2442,8 @@ static inline unsigned start_dir_add(str + + static inline void end_dir_add(struct inode *dir, unsigned n) + { +- smp_store_release(&dir->i_dir_seq, n + 2); ++ smp_store_release(&dir->__i_dir_seq, n + 2); ++ preempt_enable_rt(); + } + + static void d_wait_lookup(struct dentry *dentry) +@@ -2474,7 +2476,7 @@ struct dentry *d_alloc_parallel(struct d + + retry: + rcu_read_lock(); +- seq = smp_load_acquire(&parent->d_inode->i_dir_seq); ++ seq = smp_load_acquire(&parent->d_inode->__i_dir_seq); + r_seq = read_seqbegin(&rename_lock); + dentry = __d_lookup_rcu(parent, name, &d_seq); + if (unlikely(dentry)) { +@@ -2502,7 +2504,7 @@ struct dentry *d_alloc_parallel(struct d + } + + hlist_bl_lock(b); +- if (unlikely(READ_ONCE(parent->d_inode->i_dir_seq) != seq)) { ++ if (unlikely(READ_ONCE(parent->d_inode->__i_dir_seq) != seq)) { + hlist_bl_unlock(b); + rcu_read_unlock(); + goto retry; +--- a/fs/inode.c ++++ b/fs/inode.c +@@ -155,7 +155,7 @@ int inode_init_always(struct super_block + inode->i_bdev = NULL; + inode->i_cdev = NULL; + inode->i_link = NULL; +- inode->i_dir_seq = 0; ++ inode->__i_dir_seq = 0; + inode->i_rdev = 0; + inode->dirtied_when = 0; + +--- a/fs/libfs.c ++++ b/fs/libfs.c +@@ -90,7 +90,7 @@ static struct dentry *next_positive(stru + struct list_head *from, + int count) + { +- unsigned *seq = &parent->d_inode->i_dir_seq, n; ++ unsigned *seq = &parent->d_inode->__i_dir_seq, n; + struct dentry *res; + struct list_head *p; + bool skipped; +@@ -123,8 +123,9 @@ static struct dentry *next_positive(stru + static void move_cursor(struct dentry *cursor, struct list_head *after) + { + struct dentry *parent = cursor->d_parent; +- unsigned n, *seq = &parent->d_inode->i_dir_seq; ++ unsigned n, *seq = &parent->d_inode->__i_dir_seq; + spin_lock(&parent->d_lock); ++ preempt_disable_rt(); + for (;;) { + n = *seq; + if (!(n & 1) && cmpxchg(seq, n, n + 1) == n) +@@ -137,6 +138,7 @@ static void move_cursor(struct dentry *c + else + list_add_tail(&cursor->d_child, &parent->d_subdirs); + smp_store_release(seq, n + 2); ++ preempt_enable_rt(); + spin_unlock(&parent->d_lock); + } + +--- a/include/linux/fs.h ++++ b/include/linux/fs.h +@@ -657,7 +657,7 @@ struct inode { + struct block_device *i_bdev; + struct cdev *i_cdev; + char *i_link; +- unsigned i_dir_seq; ++ unsigned __i_dir_seq; + }; + + __u32 i_generation; diff --git a/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch b/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch new file mode 100644 index 000000000..418ea48d9 --- /dev/null +++ b/debian/patches/features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch @@ -0,0 +1,59 @@ +Subject: fs: dcache: Use cpu_chill() in trylock loops +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 21:00:34 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + fs/autofs/expire.c | 3 ++- + fs/namespace.c | 8 ++++++-- + 2 files changed, 8 insertions(+), 3 deletions(-) + +--- a/fs/autofs/expire.c ++++ b/fs/autofs/expire.c +@@ -8,6 +8,7 @@ + * option, any later version, incorporated herein by reference. + */ + ++#include + #include "autofs_i.h" + + static unsigned long now; +@@ -148,7 +149,7 @@ static struct dentry *get_next_positive_ + parent = p->d_parent; + if (!spin_trylock(&parent->d_lock)) { + spin_unlock(&p->d_lock); +- cpu_relax(); ++ cpu_chill(); + goto relock; + } + spin_unlock(&p->d_lock); +--- a/fs/namespace.c ++++ b/fs/namespace.c +@@ -14,6 +14,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -353,8 +354,11 @@ int __mnt_want_write(struct vfsmount *m) + * incremented count after it has set MNT_WRITE_HOLD. + */ + smp_mb(); +- while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) +- cpu_relax(); ++ while (READ_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) { ++ preempt_enable(); ++ cpu_chill(); ++ preempt_disable(); ++ } + /* + * After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will + * be set to match its requirements. So we must not load that until diff --git a/debian/patches/features/all/rt/fs-dcache-use-swait_queue-instead-of-waitqueue.patch b/debian/patches/features/all/rt/fs-dcache-use-swait_queue-instead-of-waitqueue.patch new file mode 100644 index 000000000..47583a512 --- /dev/null +++ b/debian/patches/features/all/rt/fs-dcache-use-swait_queue-instead-of-waitqueue.patch @@ -0,0 +1,215 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 14 Sep 2016 14:35:49 +0200 +Subject: [PATCH] fs/dcache: use swait_queue instead of waitqueue +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +__d_lookup_done() invokes wake_up_all() while holding a hlist_bl_lock() +which disables preemption. As a workaround convert it to swait. + +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/cifs/readdir.c | 2 +- + fs/dcache.c | 27 +++++++++++++++------------ + fs/fuse/dir.c | 2 +- + fs/namei.c | 4 ++-- + fs/nfs/dir.c | 4 ++-- + fs/nfs/unlink.c | 4 ++-- + fs/proc/base.c | 2 +- + fs/proc/proc_sysctl.c | 2 +- + include/linux/dcache.h | 4 ++-- + include/linux/nfs_xdr.h | 2 +- + kernel/sched/swait.c | 1 + + 11 files changed, 29 insertions(+), 25 deletions(-) + +--- a/fs/cifs/readdir.c ++++ b/fs/cifs/readdir.c +@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, + struct inode *inode; + struct super_block *sb = parent->d_sb; + struct cifs_sb_info *cifs_sb = CIFS_SB(sb); +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + cifs_dbg(FYI, "%s: for %s\n", __func__, name->name); + +--- a/fs/dcache.c ++++ b/fs/dcache.c +@@ -2448,21 +2448,24 @@ static inline void end_dir_add(struct in + + static void d_wait_lookup(struct dentry *dentry) + { +- if (d_in_lookup(dentry)) { +- DECLARE_WAITQUEUE(wait, current); +- add_wait_queue(dentry->d_wait, &wait); +- do { +- set_current_state(TASK_UNINTERRUPTIBLE); +- spin_unlock(&dentry->d_lock); +- schedule(); +- spin_lock(&dentry->d_lock); +- } while (d_in_lookup(dentry)); +- } ++ struct swait_queue __wait; ++ ++ if (!d_in_lookup(dentry)) ++ return; ++ ++ INIT_LIST_HEAD(&__wait.task_list); ++ do { ++ prepare_to_swait(dentry->d_wait, &__wait, TASK_UNINTERRUPTIBLE); ++ spin_unlock(&dentry->d_lock); ++ schedule(); ++ spin_lock(&dentry->d_lock); ++ } while (d_in_lookup(dentry)); ++ finish_swait(dentry->d_wait, &__wait); + } + + struct dentry *d_alloc_parallel(struct dentry *parent, + const struct qstr *name, +- wait_queue_head_t *wq) ++ struct swait_queue_head *wq) + { + unsigned int hash = name->hash; + struct hlist_bl_head *b = in_lookup_hash(parent, hash); +@@ -2577,7 +2580,7 @@ void __d_lookup_done(struct dentry *dent + hlist_bl_lock(b); + dentry->d_flags &= ~DCACHE_PAR_LOOKUP; + __hlist_bl_del(&dentry->d_u.d_in_lookup_hash); +- wake_up_all(dentry->d_wait); ++ swake_up_all(dentry->d_wait); + dentry->d_wait = NULL; + hlist_bl_unlock(b); + INIT_HLIST_NODE(&dentry->d_u.d_alias); +--- a/fs/fuse/dir.c ++++ b/fs/fuse/dir.c +@@ -1195,7 +1195,7 @@ static int fuse_direntplus_link(struct f + struct inode *dir = d_inode(parent); + struct fuse_conn *fc; + struct inode *inode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + if (!o->nodeid) { + /* +--- a/fs/namei.c ++++ b/fs/namei.c +@@ -1604,7 +1604,7 @@ static struct dentry *__lookup_slow(cons + { + struct dentry *dentry, *old; + struct inode *inode = dir->d_inode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + /* Don't go there if it's already dead */ + if (unlikely(IS_DEADDIR(inode))) +@@ -3121,7 +3121,7 @@ static int lookup_open(struct nameidata + struct dentry *dentry; + int error, create_error = 0; + umode_t mode = op->mode; +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + + if (unlikely(IS_DEADDIR(dir_inode))) + return -ENOENT; +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -445,7 +445,7 @@ static + void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) + { + struct qstr filename = QSTR_INIT(entry->name, entry->len); +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + struct dentry *dentry; + struct dentry *alias; + struct inode *dir = d_inode(parent); +@@ -1454,7 +1454,7 @@ int nfs_atomic_open(struct inode *dir, s + struct file *file, unsigned open_flags, + umode_t mode, int *opened) + { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + struct nfs_open_context *ctx; + struct dentry *res; + struct iattr attr = { .ia_valid = ATTR_OPEN }; +--- a/fs/nfs/unlink.c ++++ b/fs/nfs/unlink.c +@@ -13,7 +13,7 @@ + #include + #include + #include +-#include ++#include + #include + #include + +@@ -206,7 +206,7 @@ nfs_async_unlink(struct dentry *dentry, + goto out_free_name; + } + data->res.dir_attr = &data->dir_attr; +- init_waitqueue_head(&data->wq); ++ init_swait_queue_head(&data->wq); + + status = -EBUSY; + spin_lock(&dentry->d_lock); +--- a/fs/proc/base.c ++++ b/fs/proc/base.c +@@ -1864,7 +1864,7 @@ bool proc_fill_cache(struct file *file, + + child = d_hash_and_lookup(dir, &qname); + if (!child) { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + goto end_instantiate; +--- a/fs/proc/proc_sysctl.c ++++ b/fs/proc/proc_sysctl.c +@@ -678,7 +678,7 @@ static bool proc_sys_fill_cache(struct f + + child = d_lookup(dir, &qname); + if (!child) { +- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq); ++ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq); + child = d_alloc_parallel(dir, &qname, &wq); + if (IS_ERR(child)) + return false; +--- a/include/linux/dcache.h ++++ b/include/linux/dcache.h +@@ -105,7 +105,7 @@ struct dentry { + + union { + struct list_head d_lru; /* LRU list */ +- wait_queue_head_t *d_wait; /* in-lookup ones only */ ++ struct swait_queue_head *d_wait; /* in-lookup ones only */ + }; + struct list_head d_child; /* child of parent list */ + struct list_head d_subdirs; /* our children */ +@@ -238,7 +238,7 @@ extern struct dentry * d_alloc(struct de + extern struct dentry * d_alloc_anon(struct super_block *); + extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); + extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, +- wait_queue_head_t *); ++ struct swait_queue_head *); + extern struct dentry * d_splice_alias(struct inode *, struct dentry *); + extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); + extern struct dentry * d_exact_alias(struct dentry *, struct inode *); +--- a/include/linux/nfs_xdr.h ++++ b/include/linux/nfs_xdr.h +@@ -1536,7 +1536,7 @@ struct nfs_unlinkdata { + struct nfs_removeargs args; + struct nfs_removeres res; + struct dentry *dentry; +- wait_queue_head_t wq; ++ struct swait_queue_head wq; + struct rpc_cred *cred; + struct nfs_fattr dir_attr; + long timeout; +--- a/kernel/sched/swait.c ++++ b/kernel/sched/swait.c +@@ -70,6 +70,7 @@ void swake_up_all(struct swait_queue_hea + struct swait_queue *curr; + LIST_HEAD(tmp); + ++ WARN_ON(irqs_disabled()); + raw_spin_lock_irq(&q->lock); + list_splice_init(&q->task_list, &tmp); + while (!list_empty(&tmp)) { diff --git a/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch b/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch new file mode 100644 index 000000000..8d20bffb5 --- /dev/null +++ b/debian/patches/features/all/rt/fs-jbd-replace-bh_state-lock.patch @@ -0,0 +1,97 @@ +From: Thomas Gleixner +Date: Fri, 18 Mar 2011 10:11:25 +0100 +Subject: fs: jbd/jbd2: Make state lock and journal head lock rt safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +bit_spin_locks break under RT. + +Based on a previous patch from Steven Rostedt +Signed-off-by: Thomas Gleixner +-- + include/linux/buffer_head.h | 8 ++++++++ + include/linux/jbd2.h | 24 ++++++++++++++++++++++++ + 2 files changed, 32 insertions(+) + +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -78,6 +78,10 @@ struct buffer_head { + atomic_t b_count; /* users using this buffer_head */ + #ifdef CONFIG_PREEMPT_RT_BASE + spinlock_t b_uptodate_lock; ++#if IS_ENABLED(CONFIG_JBD2) ++ spinlock_t b_state_lock; ++ spinlock_t b_journal_head_lock; ++#endif + #endif + }; + +@@ -109,6 +113,10 @@ static inline void buffer_head_init_lock + { + #ifdef CONFIG_PREEMPT_RT_BASE + spin_lock_init(&bh->b_uptodate_lock); ++#if IS_ENABLED(CONFIG_JBD2) ++ spin_lock_init(&bh->b_state_lock); ++ spin_lock_init(&bh->b_journal_head_lock); ++#endif + #endif + } + +--- a/include/linux/jbd2.h ++++ b/include/linux/jbd2.h +@@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh + + static inline void jbd_lock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_State, &bh->b_state); ++#else ++ spin_lock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_trylock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_trylock(BH_State, &bh->b_state); ++#else ++ return spin_trylock(&bh->b_state_lock); ++#endif + } + + static inline int jbd_is_locked_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + return bit_spin_is_locked(BH_State, &bh->b_state); ++#else ++ return spin_is_locked(&bh->b_state_lock); ++#endif + } + + static inline void jbd_unlock_bh_state(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_State, &bh->b_state); ++#else ++ spin_unlock(&bh->b_state_lock); ++#endif + } + + static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(BH_JournalHead, &bh->b_state); ++#else ++ spin_lock(&bh->b_journal_head_lock); ++#endif + } + + static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_unlock(BH_JournalHead, &bh->b_state); ++#else ++ spin_unlock(&bh->b_journal_head_lock); ++#endif + } + + #define J_ASSERT(assert) BUG_ON(!(assert)) diff --git a/debian/patches/features/all/rt/fs-nfs-turn-rmdir_sem-into-a-semaphore.patch b/debian/patches/features/all/rt/fs-nfs-turn-rmdir_sem-into-a-semaphore.patch new file mode 100644 index 000000000..49c6d9239 --- /dev/null +++ b/debian/patches/features/all/rt/fs-nfs-turn-rmdir_sem-into-a-semaphore.patch @@ -0,0 +1,139 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 15 Sep 2016 10:51:27 +0200 +Subject: [PATCH] fs/nfs: turn rmdir_sem into a semaphore +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The RW semaphore had a reader side which used the _non_owner version +because it most likely took the reader lock in one thread and released it +in another which would cause lockdep to complain if the "regular" +version was used. +On -RT we need the owner because the rw lock is turned into a rtmutex. +The semaphores on the hand are "plain simple" and should work as +expected. We can't have multiple readers but on -RT we don't allow +multiple readers anyway so that is not a loss. + +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/nfs/dir.c | 8 ++++++++ + fs/nfs/inode.c | 4 ++++ + fs/nfs/unlink.c | 31 +++++++++++++++++++++++++++---- + include/linux/nfs_fs.h | 4 ++++ + 4 files changed, 43 insertions(+), 4 deletions(-) + +--- a/fs/nfs/dir.c ++++ b/fs/nfs/dir.c +@@ -1775,7 +1775,11 @@ int nfs_rmdir(struct inode *dir, struct + + trace_nfs_rmdir_enter(dir, dentry); + if (d_really_is_positive(dentry)) { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ down(&NFS_I(d_inode(dentry))->rmdir_sem); ++#else + down_write(&NFS_I(d_inode(dentry))->rmdir_sem); ++#endif + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + /* Ensure the VFS deletes this inode */ + switch (error) { +@@ -1785,7 +1789,11 @@ int nfs_rmdir(struct inode *dir, struct + case -ENOENT: + nfs_dentry_handle_enoent(dentry); + } ++#ifdef CONFIG_PREEMPT_RT_BASE ++ up(&NFS_I(d_inode(dentry))->rmdir_sem); ++#else + up_write(&NFS_I(d_inode(dentry))->rmdir_sem); ++#endif + } else + error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name); + trace_nfs_rmdir_exit(dir, dentry, error); +--- a/fs/nfs/inode.c ++++ b/fs/nfs/inode.c +@@ -2103,7 +2103,11 @@ static void init_once(void *foo) + atomic_long_set(&nfsi->nrequests, 0); + atomic_long_set(&nfsi->commit_info.ncommit, 0); + atomic_set(&nfsi->commit_info.rpcs_out, 0); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ sema_init(&nfsi->rmdir_sem, 1); ++#else + init_rwsem(&nfsi->rmdir_sem); ++#endif + mutex_init(&nfsi->commit_mutex); + nfs4_init_once(nfsi); + } +--- a/fs/nfs/unlink.c ++++ b/fs/nfs/unlink.c +@@ -52,6 +52,29 @@ static void nfs_async_unlink_done(struct + rpc_restart_call_prepare(task); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void nfs_down_anon(struct semaphore *sema) ++{ ++ down(sema); ++} ++ ++static void nfs_up_anon(struct semaphore *sema) ++{ ++ up(sema); ++} ++ ++#else ++static void nfs_down_anon(struct rw_semaphore *rwsem) ++{ ++ down_read_non_owner(rwsem); ++} ++ ++static void nfs_up_anon(struct rw_semaphore *rwsem) ++{ ++ up_read_non_owner(rwsem); ++} ++#endif ++ + /** + * nfs_async_unlink_release - Release the sillydelete data. + * @task: rpc_task of the sillydelete +@@ -65,7 +88,7 @@ static void nfs_async_unlink_release(voi + struct dentry *dentry = data->dentry; + struct super_block *sb = dentry->d_sb; + +- up_read_non_owner(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); ++ nfs_up_anon(&NFS_I(d_inode(dentry->d_parent))->rmdir_sem); + d_lookup_done(dentry); + nfs_free_unlinkdata(data); + dput(dentry); +@@ -118,10 +141,10 @@ static int nfs_call_unlink(struct dentry + struct inode *dir = d_inode(dentry->d_parent); + struct dentry *alias; + +- down_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_down_anon(&NFS_I(dir)->rmdir_sem); + alias = d_alloc_parallel(dentry->d_parent, &data->args.name, &data->wq); + if (IS_ERR(alias)) { +- up_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_up_anon(&NFS_I(dir)->rmdir_sem); + return 0; + } + if (!d_in_lookup(alias)) { +@@ -143,7 +166,7 @@ static int nfs_call_unlink(struct dentry + ret = 0; + spin_unlock(&alias->d_lock); + dput(alias); +- up_read_non_owner(&NFS_I(dir)->rmdir_sem); ++ nfs_up_anon(&NFS_I(dir)->rmdir_sem); + /* + * If we'd displaced old cached devname, free it. At that + * point dentry is definitely not a root, so we won't need +--- a/include/linux/nfs_fs.h ++++ b/include/linux/nfs_fs.h +@@ -163,7 +163,11 @@ struct nfs_inode { + + /* Readers: in-flight sillydelete RPC calls */ + /* Writers: rmdir */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct semaphore rmdir_sem; ++#else + struct rw_semaphore rmdir_sem; ++#endif + struct mutex commit_mutex; + + #if IS_ENABLED(CONFIG_NFS_V4) diff --git a/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch b/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch new file mode 100644 index 000000000..95f3164c6 --- /dev/null +++ b/debian/patches/features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch @@ -0,0 +1,208 @@ +From: Thomas Gleixner +Date: Fri, 18 Mar 2011 09:18:52 +0100 +Subject: buffer_head: Replace bh_uptodate_lock for -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Wrap the bit_spin_lock calls into a separate inline and add the RT +replacements with a real spinlock. + +Signed-off-by: Thomas Gleixner +--- + fs/buffer.c | 21 +++++++-------------- + fs/ext4/page-io.c | 6 ++---- + fs/ntfs/aops.c | 10 +++------- + fs/xfs/xfs_aops.c | 6 ++---- + include/linux/buffer_head.h | 34 ++++++++++++++++++++++++++++++++++ + 5 files changed, 48 insertions(+), 29 deletions(-) + +--- a/fs/buffer.c ++++ b/fs/buffer.c +@@ -273,8 +273,7 @@ static void end_buffer_async_read(struct + * decide that the page is now completely done. + */ + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -287,8 +286,7 @@ static void end_buffer_async_read(struct + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + + /* + * If none of the buffers had errors and they are all +@@ -300,9 +298,7 @@ static void end_buffer_async_read(struct + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /* +@@ -329,8 +325,7 @@ void end_buffer_async_write(struct buffe + } + + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + + clear_buffer_async_write(bh); + unlock_buffer(bh); +@@ -342,15 +337,12 @@ void end_buffer_async_write(struct buffe + } + tmp = tmp->b_this_page; + } +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + end_page_writeback(page); + return; + + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + EXPORT_SYMBOL(end_buffer_async_write); + +@@ -3349,6 +3341,7 @@ struct buffer_head *alloc_buffer_head(gf + struct buffer_head *ret = kmem_cache_zalloc(bh_cachep, gfp_flags); + if (ret) { + INIT_LIST_HEAD(&ret->b_assoc_buffers); ++ buffer_head_init_locks(ret); + preempt_disable(); + __this_cpu_inc(bh_accounting.nr); + recalc_bh_state(); +--- a/fs/ext4/page-io.c ++++ b/fs/ext4/page-io.c +@@ -95,8 +95,7 @@ static void ext4_finish_bio(struct bio * + * We check all buffers in the page under BH_Uptodate_Lock + * to avoid races with other end io clearing async_write flags + */ +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &head->b_state); ++ flags = bh_uptodate_lock_irqsave(head); + do { + if (bh_offset(bh) < bio_start || + bh_offset(bh) + bh->b_size > bio_end) { +@@ -108,8 +107,7 @@ static void ext4_finish_bio(struct bio * + if (bio->bi_status) + buffer_io_error(bh); + } while ((bh = bh->b_this_page) != head); +- bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(head, flags); + if (!under_io) { + #ifdef CONFIG_EXT4_FS_ENCRYPTION + if (data_page) +--- a/fs/ntfs/aops.c ++++ b/fs/ntfs/aops.c +@@ -106,8 +106,7 @@ static void ntfs_end_buffer_async_read(s + "0x%llx.", (unsigned long long)bh->b_blocknr); + } + first = page_buffers(page); +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &first->b_state); ++ flags = bh_uptodate_lock_irqsave(first); + clear_buffer_async_read(bh); + unlock_buffer(bh); + tmp = bh; +@@ -122,8 +121,7 @@ static void ntfs_end_buffer_async_read(s + } + tmp = tmp->b_this_page; + } while (tmp != bh); +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(first, flags); + /* + * If none of the buffers had errors then we can set the page uptodate, + * but we first have to perform the post read mst fixups, if the +@@ -156,9 +154,7 @@ static void ntfs_end_buffer_async_read(s + unlock_page(page); + return; + still_busy: +- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state); +- local_irq_restore(flags); +- return; ++ bh_uptodate_unlock_irqrestore(first, flags); + } + + /** +--- a/fs/xfs/xfs_aops.c ++++ b/fs/xfs/xfs_aops.c +@@ -108,8 +108,7 @@ xfs_finish_page_writeback( + ASSERT(bvec->bv_offset + bvec->bv_len <= PAGE_SIZE); + ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0); + +- local_irq_save(flags); +- bit_spin_lock(BH_Uptodate_Lock, &head->b_state); ++ flags = bh_uptodate_lock_irqsave(head); + do { + if (off >= bvec->bv_offset && + off < bvec->bv_offset + bvec->bv_len) { +@@ -131,8 +130,7 @@ xfs_finish_page_writeback( + } + off += bh->b_size; + } while ((bh = bh->b_this_page) != head); +- bit_spin_unlock(BH_Uptodate_Lock, &head->b_state); +- local_irq_restore(flags); ++ bh_uptodate_unlock_irqrestore(head, flags); + + if (!busy) + end_page_writeback(bvec->bv_page); +--- a/include/linux/buffer_head.h ++++ b/include/linux/buffer_head.h +@@ -76,8 +76,42 @@ struct buffer_head { + struct address_space *b_assoc_map; /* mapping this buffer is + associated with */ + atomic_t b_count; /* users using this buffer_head */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spinlock_t b_uptodate_lock; ++#endif + }; + ++static inline unsigned long bh_uptodate_lock_irqsave(struct buffer_head *bh) ++{ ++ unsigned long flags; ++ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ local_irq_save(flags); ++ bit_spin_lock(BH_Uptodate_Lock, &bh->b_state); ++#else ++ spin_lock_irqsave(&bh->b_uptodate_lock, flags); ++#endif ++ return flags; ++} ++ ++static inline void ++bh_uptodate_unlock_irqrestore(struct buffer_head *bh, unsigned long flags) ++{ ++#ifndef CONFIG_PREEMPT_RT_BASE ++ bit_spin_unlock(BH_Uptodate_Lock, &bh->b_state); ++ local_irq_restore(flags); ++#else ++ spin_unlock_irqrestore(&bh->b_uptodate_lock, flags); ++#endif ++} ++ ++static inline void buffer_head_init_locks(struct buffer_head *bh) ++{ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ spin_lock_init(&bh->b_uptodate_lock); ++#endif ++} ++ + /* + * macro tricks to expand the set_buffer_foo(), clear_buffer_foo() + * and buffer_foo() functions. diff --git a/debian/patches/features/all/rt/fscache-initialize-cookie-hash-table-raw-spinlocks.patch b/debian/patches/features/all/rt/fscache-initialize-cookie-hash-table-raw-spinlocks.patch new file mode 100644 index 000000000..2d36fb29d --- /dev/null +++ b/debian/patches/features/all/rt/fscache-initialize-cookie-hash-table-raw-spinlocks.patch @@ -0,0 +1,55 @@ +From 0277aff2b41aef9e2a6bd716ee0076036881334d Mon Sep 17 00:00:00 2001 +From: Clark Williams +Date: Tue, 3 Jul 2018 13:34:30 -0500 +Subject: [PATCH] fscache: initialize cookie hash table raw spinlocks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The fscache cookie mechanism uses a hash table of hlist_bl_head structures. The +PREEMPT_RT patcheset adds a raw spinlock to this structure and so on PREEMPT_RT +the structures get used uninitialized, causing warnings about bad magic numbers +when spinlock debugging is turned on. + +Use the init function for fscache cookies. + +Signed-off-by: Clark Williams +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/fscache/cookie.c | 8 ++++++++ + fs/fscache/main.c | 1 + + include/linux/fscache.h | 1 + + 3 files changed, 10 insertions(+) + +--- a/fs/fscache/cookie.c ++++ b/fs/fscache/cookie.c +@@ -973,3 +973,11 @@ int __fscache_check_consistency(struct f + return -ESTALE; + } + EXPORT_SYMBOL(__fscache_check_consistency); ++ ++void __init fscache_cookie_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < (1 << fscache_cookie_hash_shift) - 1; i++) ++ INIT_HLIST_BL_HEAD(&fscache_cookie_hash[i]); ++} +--- a/fs/fscache/main.c ++++ b/fs/fscache/main.c +@@ -151,6 +151,7 @@ static int __init fscache_init(void) + ret = -ENOMEM; + goto error_cookie_jar; + } ++ fscache_cookie_init(); + + fscache_root = kobject_create_and_add("fscache", kernel_kobj); + if (!fscache_root) +--- a/include/linux/fscache.h ++++ b/include/linux/fscache.h +@@ -230,6 +230,7 @@ extern void __fscache_readpages_cancel(s + extern void __fscache_disable_cookie(struct fscache_cookie *, const void *, bool); + extern void __fscache_enable_cookie(struct fscache_cookie *, const void *, loff_t, + bool (*)(void *), void *); ++extern void fscache_cookie_init(void); + + /** + * fscache_register_netfs - Register a filesystem as desiring caching services diff --git a/debian/patches/features/all/rt/ftrace-Fix-trace-header-alignment.patch b/debian/patches/features/all/rt/ftrace-Fix-trace-header-alignment.patch new file mode 100644 index 000000000..36cc01737 --- /dev/null +++ b/debian/patches/features/all/rt/ftrace-Fix-trace-header-alignment.patch @@ -0,0 +1,46 @@ +From: Mike Galbraith +Date: Sun, 16 Oct 2016 05:08:30 +0200 +Subject: [PATCH] ftrace: Fix trace header alignment +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Line up helper arrows to the right column. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Mike Galbraith +[bigeasy: fixup function tracer header] +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/trace/trace.c | 22 +++++++++++----------- + 1 file changed, 11 insertions(+), 11 deletions(-) + +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -3347,17 +3347,17 @@ get_total_entries(struct trace_buffer *b + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _--------=> CPU# \n" +- "# / _-------=> irqs-off \n" +- "# | / _------=> need-resched \n" +- "# || / _-----=> need-resched_lazy \n" +- "# ||| / _----=> hardirq/softirq \n" +- "# |||| / _---=> preempt-depth \n" +- "# ||||| / _--=> preempt-lazy-depth\n" +- "# |||||| / _-=> migrate-disable \n" +- "# ||||||| / delay \n" +- "# cmd pid |||||||| time | caller \n" +- "# \\ / |||||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) diff --git a/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch b/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch new file mode 100644 index 000000000..2bc2fd68c --- /dev/null +++ b/debian/patches/features/all/rt/ftrace-migrate-disable-tracing.patch @@ -0,0 +1,74 @@ +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:56:42 +0200 +Subject: trace: Add migrate-disabled counter to tracing output +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +--- + include/linux/trace_events.h | 2 ++ + kernel/trace/trace.c | 9 ++++++--- + kernel/trace/trace_events.c | 2 ++ + kernel/trace/trace_output.c | 5 +++++ + 4 files changed, 15 insertions(+), 3 deletions(-) + +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -62,6 +62,8 @@ struct trace_entry { + unsigned char flags; + unsigned char preempt_count; + int pid; ++ unsigned short migrate_disable; ++ unsigned short padding; + }; + + #define TRACE_EVENT_TYPE_MAX \ +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -2145,6 +2145,8 @@ tracing_generic_entry_update(struct trac + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | + (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); ++ ++ entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; + } + EXPORT_SYMBOL_GPL(tracing_generic_entry_update); + +@@ -3348,9 +3350,10 @@ static void print_lat_help_header(struct + "# | / _----=> need-resched \n" + "# || / _---=> hardirq/softirq \n" + "# ||| / _--=> preempt-depth \n" +- "# |||| / delay \n" +- "# cmd pid ||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ "# |||| / _--=> migrate-disable\n" ++ "# ||||| / delay \n" ++ "# cmd pid |||||| time | caller \n" ++ "# \\ / ||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +--- a/kernel/trace/trace_events.c ++++ b/kernel/trace/trace_events.c +@@ -187,6 +187,8 @@ static int trace_define_common_fields(vo + __common_field(unsigned char, flags); + __common_field(unsigned char, preempt_count); + __common_field(int, pid); ++ __common_field(unsigned short, migrate_disable); ++ __common_field(unsigned short, padding); + + return ret; + } +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -493,6 +493,11 @@ int trace_print_lat_fmt(struct trace_seq + else + trace_seq_putc(s, '.'); + ++ if (entry->migrate_disable) ++ trace_seq_printf(s, "%x", entry->migrate_disable); ++ else ++ trace_seq_putc(s, '.'); ++ + return !trace_seq_has_overflowed(s); + } + diff --git a/debian/patches/features/all/rt/futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch b/debian/patches/features/all/rt/futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch new file mode 100644 index 000000000..d88244313 --- /dev/null +++ b/debian/patches/features/all/rt/futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch @@ -0,0 +1,43 @@ +From: Thomas Gleixner +Date: Fri, 1 Mar 2013 11:17:42 +0100 +Subject: futex: Ensure lock/unlock symetry versus pi_lock and hash bucket lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In exit_pi_state_list() we have the following locking construct: + + spin_lock(&hb->lock); + raw_spin_lock_irq(&curr->pi_lock); + + ... + spin_unlock(&hb->lock); + +In !RT this works, but on RT the migrate_enable() function which is +called from spin_unlock() sees atomic context due to the held pi_lock +and just decrements the migrate_disable_atomic counter of the +task. Now the next call to migrate_disable() sees the counter being +negative and issues a warning. That check should be in +migrate_enable() already. + +Fix this by dropping pi_lock before unlocking hb->lock and reaquire +pi_lock after that again. This is safe as the loop code reevaluates +head again under the pi_lock. + +Reported-by: Yong Zhang +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/futex.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -918,7 +918,9 @@ void exit_pi_state_list(struct task_stru + if (head->next != next) { + /* retain curr->pi_lock for the loop invariant */ + raw_spin_unlock(&pi_state->pi_mutex.wait_lock); ++ raw_spin_unlock_irq(&curr->pi_lock); + spin_unlock(&hb->lock); ++ raw_spin_lock_irq(&curr->pi_lock); + put_pi_state(pi_state); + continue; + } diff --git a/debian/patches/features/all/rt/futex-requeue-pi-fix.patch b/debian/patches/features/all/rt/futex-requeue-pi-fix.patch new file mode 100644 index 000000000..a95c358ef --- /dev/null +++ b/debian/patches/features/all/rt/futex-requeue-pi-fix.patch @@ -0,0 +1,113 @@ +From: Steven Rostedt +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: futex: Fix bug on when a requeued RT task times out +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Requeue with timeout causes a bug with PREEMPT_RT_FULL. + +The bug comes from a timed out condition. + + + TASK 1 TASK 2 + ------ ------ + futex_wait_requeue_pi() + futex_wait_queue_me() + + + double_lock_hb(); + + raw_spin_lock(pi_lock); + if (current->pi_blocked_on) { + } else { + current->pi_blocked_on = PI_WAKE_INPROGRESS; + run_spin_unlock(pi_lock); + spin_lock(hb->lock); <-- blocked! + + + plist_for_each_entry_safe(this) { + rt_mutex_start_proxy_lock(); + task_blocks_on_rt_mutex(); + BUG_ON(task->pi_blocked_on)!!!! + +The BUG_ON() actually has a check for PI_WAKE_INPROGRESS, but the +problem is that, after TASK 1 sets PI_WAKE_INPROGRESS, it then tries to +grab the hb->lock, which it fails to do so. As the hb->lock is a mutex, +it will block and set the "pi_blocked_on" to the hb->lock. + +When TASK 2 goes to requeue it, the check for PI_WAKE_INPROGESS fails +because the task1's pi_blocked_on is no longer set to that, but instead, +set to the hb->lock. + +The fix: + +When calling rt_mutex_start_proxy_lock() a check is made to see +if the proxy tasks pi_blocked_on is set. If so, exit out early. +Otherwise set it to a new flag PI_REQUEUE_INPROGRESS, which notifies +the proxy task that it is being requeued, and will handle things +appropriately. + + +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner +--- + kernel/locking/rtmutex.c | 31 ++++++++++++++++++++++++++++++- + kernel/locking/rtmutex_common.h | 1 + + 2 files changed, 31 insertions(+), 1 deletion(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -137,7 +137,8 @@ static void fixup_rt_mutex_waiters(struc + + static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) + { +- return waiter && waiter != PI_WAKEUP_INPROGRESS; ++ return waiter && waiter != PI_WAKEUP_INPROGRESS && ++ waiter != PI_REQUEUE_INPROGRESS; + } + + /* +@@ -1763,6 +1764,34 @@ int __rt_mutex_start_proxy_lock(struct r + if (try_to_take_rt_mutex(lock, task, NULL)) + return 1; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * In PREEMPT_RT there's an added race. ++ * If the task, that we are about to requeue, times out, ++ * it can set the PI_WAKEUP_INPROGRESS. This tells the requeue ++ * to skip this task. But right after the task sets ++ * its pi_blocked_on to PI_WAKEUP_INPROGRESS it can then ++ * block on the spin_lock(&hb->lock), which in RT is an rtmutex. ++ * This will replace the PI_WAKEUP_INPROGRESS with the actual ++ * lock that it blocks on. We *must not* place this task ++ * on this proxy lock in that case. ++ * ++ * To prevent this race, we first take the task's pi_lock ++ * and check if it has updated its pi_blocked_on. If it has, ++ * we assume that it woke up and we return -EAGAIN. ++ * Otherwise, we set the task's pi_blocked_on to ++ * PI_REQUEUE_INPROGRESS, so that if the task is waking up ++ * it will know that we are in the process of requeuing it. ++ */ ++ raw_spin_lock(&task->pi_lock); ++ if (task->pi_blocked_on) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ task->pi_blocked_on = PI_REQUEUE_INPROGRESS; ++ raw_spin_unlock(&task->pi_lock); ++#endif ++ + /* We enforce deadlock detection for futexes */ + ret = task_blocks_on_rt_mutex(lock, waiter, task, + RT_MUTEX_FULL_CHAINWALK); +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -131,6 +131,7 @@ enum rtmutex_chainwalk { + * PI-futex support (proxy locking functions, etc.): + */ + #define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++#define PI_REQUEUE_INPROGRESS ((struct rt_mutex_waiter *) 2) + + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, diff --git a/debian/patches/features/all/rt/futex-workaround-migrate_disable-enable-in-different.patch b/debian/patches/features/all/rt/futex-workaround-migrate_disable-enable-in-different.patch new file mode 100644 index 000000000..d7643f616 --- /dev/null +++ b/debian/patches/features/all/rt/futex-workaround-migrate_disable-enable-in-different.patch @@ -0,0 +1,59 @@ +From: Thomas Gleixner +Date: Wed, 8 Mar 2017 14:23:35 +0100 +Subject: [PATCH] futex: workaround migrate_disable/enable in different context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +migrate_disable()/migrate_enable() takes a different path in atomic() vs +!atomic() context. These little hacks ensure that we don't underflow / overflow +the migrate code counts properly while we lock the hb lockwith interrupts +enabled and unlock it with interrupts disabled. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/futex.c | 19 +++++++++++++++++++ + 1 file changed, 19 insertions(+) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2798,9 +2798,18 @@ static int futex_lock_pi(u32 __user *uad + * lock handoff sequence. + */ + raw_spin_lock_irq(&q.pi_state->pi_mutex.wait_lock); ++ /* ++ * the migrate_disable() here disables migration in the in_atomic() fast ++ * path which is enabled again in the following spin_unlock(). We have ++ * one migrate_disable() pending in the slow-path which is reversed ++ * after the raw_spin_unlock_irq() where we leave the atomic context. ++ */ ++ migrate_disable(); ++ + spin_unlock(q.lock_ptr); + ret = __rt_mutex_start_proxy_lock(&q.pi_state->pi_mutex, &rt_waiter, current); + raw_spin_unlock_irq(&q.pi_state->pi_mutex.wait_lock); ++ migrate_enable(); + + if (ret) { + if (ret == 1) +@@ -2947,11 +2956,21 @@ static int futex_unlock_pi(u32 __user *u + * observed. + */ + raw_spin_lock_irq(&pi_state->pi_mutex.wait_lock); ++ /* ++ * Magic trickery for now to make the RT migrate disable ++ * logic happy. The following spin_unlock() happens with ++ * interrupts disabled so the internal migrate_enable() ++ * won't undo the migrate_disable() which was issued when ++ * locking hb->lock. ++ */ ++ migrate_disable(); + spin_unlock(&hb->lock); + + /* drops pi_state->pi_mutex.wait_lock */ + ret = wake_futex_pi(uaddr, uval, pi_state); + ++ migrate_enable(); ++ + put_pi_state(pi_state); + + /* diff --git a/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch b/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch new file mode 100644 index 000000000..77afbbee7 --- /dev/null +++ b/debian/patches/features/all/rt/genirq-disable-irqpoll-on-rt.patch @@ -0,0 +1,38 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:57 -0500 +Subject: genirq: Disable irqpoll on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Creates long latencies for no value + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + kernel/irq/spurious.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/kernel/irq/spurious.c ++++ b/kernel/irq/spurious.c +@@ -442,6 +442,10 @@ MODULE_PARM_DESC(noirqdebug, "Disable ir + + static int __init irqfixup_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqfixup boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 1; + printk(KERN_WARNING "Misrouted IRQ fixup support enabled.\n"); + printk(KERN_WARNING "This may impact system performance.\n"); +@@ -454,6 +458,10 @@ module_param(irqfixup, int, 0644); + + static int __init irqpoll_setup(char *str) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ pr_warn("irqpoll boot option not supported w/ CONFIG_PREEMPT_RT_BASE\n"); ++ return 1; ++#endif + irqfixup = 2; + printk(KERN_WARNING "Misrouted IRQ fixup and polling support " + "enabled\n"); diff --git a/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch b/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch new file mode 100644 index 000000000..bc59bc69f --- /dev/null +++ b/debian/patches/features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch @@ -0,0 +1,122 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 21 Aug 2013 17:48:46 +0200 +Subject: genirq: Do not invoke the affinity callback via a workqueue on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Joe Korty reported, that __irq_set_affinity_locked() schedules a +workqueue while holding a rawlock which results in a might_sleep() +warning. +This patch uses swork_queue() instead. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/interrupt.h | 6 ++++++ + kernel/irq/manage.c | 43 ++++++++++++++++++++++++++++++++++++++++--- + 2 files changed, 46 insertions(+), 3 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -13,6 +13,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -225,6 +226,7 @@ extern void resume_device_irqs(void); + * struct irq_affinity_notify - context for notification of IRQ affinity changes + * @irq: Interrupt to which notification applies + * @kref: Reference count, for internal use ++ * @swork: Swork item, for internal use + * @work: Work item, for internal use + * @notify: Function to be called on change. This will be + * called in process context. +@@ -236,7 +238,11 @@ extern void resume_device_irqs(void); + struct irq_affinity_notify { + unsigned int irq; + struct kref kref; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct swork_event swork; ++#else + struct work_struct work; ++#endif + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); + }; +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -259,7 +259,12 @@ int irq_set_affinity_locked(struct irq_d + + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ swork_queue(&desc->affinity_notify->swork); ++#else + schedule_work(&desc->affinity_notify->work); ++#endif + } + irqd_set(data, IRQD_AFFINITY_SET); + +@@ -297,10 +302,8 @@ int irq_set_affinity_hint(unsigned int i + } + EXPORT_SYMBOL_GPL(irq_set_affinity_hint); + +-static void irq_affinity_notify(struct work_struct *work) ++static void _irq_affinity_notify(struct irq_affinity_notify *notify) + { +- struct irq_affinity_notify *notify = +- container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; +@@ -322,6 +325,35 @@ static void irq_affinity_notify(struct w + kref_put(¬ify->kref, notify->release); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static void init_helper_thread(void) ++{ ++ static int init_sworker_once; ++ ++ if (init_sworker_once) ++ return; ++ if (WARN_ON(swork_get())) ++ return; ++ init_sworker_once = 1; ++} ++ ++static void irq_affinity_notify(struct swork_event *swork) ++{ ++ struct irq_affinity_notify *notify = ++ container_of(swork, struct irq_affinity_notify, swork); ++ _irq_affinity_notify(notify); ++} ++ ++#else ++ ++static void irq_affinity_notify(struct work_struct *work) ++{ ++ struct irq_affinity_notify *notify = ++ container_of(work, struct irq_affinity_notify, work); ++ _irq_affinity_notify(notify); ++} ++#endif ++ + /** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification +@@ -350,7 +382,12 @@ irq_set_affinity_notifier(unsigned int i + if (notify) { + notify->irq = irq; + kref_init(¬ify->kref); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ INIT_SWORK(¬ify->swork, irq_affinity_notify); ++ init_helper_thread(); ++#else + INIT_WORK(¬ify->work, irq_affinity_notify); ++#endif + } + + raw_spin_lock_irqsave(&desc->lock, flags); diff --git a/debian/patches/features/all/rt/genirq-force-threading.patch b/debian/patches/features/all/rt/genirq-force-threading.patch new file mode 100644 index 000000000..48e5842f0 --- /dev/null +++ b/debian/patches/features/all/rt/genirq-force-threading.patch @@ -0,0 +1,46 @@ +Subject: genirq: Force interrupt thread on RT +From: Thomas Gleixner +Date: Sun, 03 Apr 2011 11:57:29 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Force threaded_irqs and optimize the code (force_irqthreads) in regard +to this. + +Signed-off-by: Thomas Gleixner +--- + include/linux/interrupt.h | 4 ++++ + kernel/irq/manage.c | 2 ++ + 2 files changed, 6 insertions(+) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -427,7 +427,11 @@ extern int irq_set_irqchip_state(unsigne + bool state); + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifdef CONFIG_PREEMPT_RT_BASE ++# define force_irqthreads (true) ++# else + extern bool force_irqthreads; ++# endif + #else + #define force_irqthreads (0) + #endif +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -23,6 +23,7 @@ + #include "internals.h" + + #ifdef CONFIG_IRQ_FORCED_THREADING ++# ifndef CONFIG_PREEMPT_RT_BASE + __read_mostly bool force_irqthreads; + EXPORT_SYMBOL_GPL(force_irqthreads); + +@@ -32,6 +33,7 @@ static int __init setup_forced_irqthread + return 0; + } + early_param("threadirqs", setup_forced_irqthreads); ++# endif + #endif + + static void __synchronize_hardirq(struct irq_desc *desc) diff --git a/debian/patches/features/all/rt/genirq-update-irq_set_irqchip_state-documentation.patch b/debian/patches/features/all/rt/genirq-update-irq_set_irqchip_state-documentation.patch new file mode 100644 index 000000000..2b91c71e4 --- /dev/null +++ b/debian/patches/features/all/rt/genirq-update-irq_set_irqchip_state-documentation.patch @@ -0,0 +1,26 @@ +From: Josh Cartwright +Date: Thu, 11 Feb 2016 11:54:00 -0600 +Subject: genirq: update irq_set_irqchip_state documentation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On -rt kernels, the use of migrate_disable()/migrate_enable() is +sufficient to guarantee a task isn't moved to another CPU. Update the +irq_set_irqchip_state() documentation to reflect this. + +Signed-off-by: Josh Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/irq/manage.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -2261,7 +2261,7 @@ EXPORT_SYMBOL_GPL(irq_get_irqchip_state) + * This call sets the internal irqchip state of an interrupt, + * depending on the value of @which. + * +- * This function should be called with preemption disabled if the ++ * This function should be called with migration disabled if the + * interrupt controller has per-cpu registers. + */ + int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which, diff --git a/debian/patches/features/all/rt/hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch b/debian/patches/features/all/rt/hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch new file mode 100644 index 000000000..d7810f3d5 --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch @@ -0,0 +1,96 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 4 Aug 2017 18:31:00 +0200 +Subject: [PATCH] hotplug: duct-tape RT-rwlock usage for non-RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This type is only available on -RT. We need to craft something for +non-RT. Since the only migrate_disable() user is -RT only, there is no +damage. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/cpu.c | 14 +++++++++++++- + 1 file changed, 13 insertions(+), 1 deletion(-) + +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -73,7 +73,7 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_s + .fail = CPUHP_INVALID, + }; + +-#ifdef CONFIG_HOTPLUG_CPU ++#if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PREEMPT_RT_FULL) + static DEFINE_PER_CPU(struct rt_rw_lock, cpuhp_pin_lock) = \ + __RWLOCK_RT_INITIALIZER(cpuhp_pin_lock); + #endif +@@ -292,6 +292,7 @@ static int cpu_hotplug_disabled; + */ + void pin_current_cpu(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin; + unsigned int cpu; + int ret; +@@ -316,6 +317,7 @@ void pin_current_cpu(void) + goto again; + } + current->pinned_on_cpu = cpu; ++#endif + } + + /** +@@ -323,6 +325,7 @@ void pin_current_cpu(void) + */ + void unpin_current_cpu(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = this_cpu_ptr(&cpuhp_pin_lock); + + if (WARN_ON(current->pinned_on_cpu != smp_processor_id())) +@@ -330,6 +333,7 @@ void unpin_current_cpu(void) + + current->pinned_on_cpu = -1; + __read_rt_unlock(cpuhp_pin); ++#endif + } + + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); +@@ -799,7 +803,9 @@ static int take_cpu_down(void *_param) + + static int takedown_cpu(unsigned int cpu) + { ++#ifdef CONFIG_PREEMPT_RT_FULL + struct rt_rw_lock *cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, cpu); ++#endif + struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); + int err; + +@@ -813,14 +819,18 @@ static int takedown_cpu(unsigned int cpu + */ + irq_lock_sparse(); + ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_lock(cpuhp_pin); ++#endif + + /* + * So now all preempt/rcu users must observe !cpu_active(). + */ + err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); + if (err) { ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); ++#endif + /* CPU refused to die */ + irq_unlock_sparse(); + /* Unpark the hotplug thread so we can rollback there */ +@@ -839,7 +849,9 @@ static int takedown_cpu(unsigned int cpu + wait_for_ap_thread(st, false); + BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); + ++#ifdef CONFIG_PREEMPT_RT_FULL + __write_rt_unlock(cpuhp_pin); ++#endif + /* Interrupts are moved away from the dying cpu, reenable alloc/free */ + irq_unlock_sparse(); + diff --git a/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch b/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch new file mode 100644 index 000000000..db9f4be4b --- /dev/null +++ b/debian/patches/features/all/rt/hotplug-light-get-online-cpus.patch @@ -0,0 +1,91 @@ +Subject: hotplug: Lightweight get online cpus +From: Thomas Gleixner +Date: Wed, 15 Jun 2011 12:36:06 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +get_online_cpus() is a heavy weight function which involves a global +mutex. migrate_disable() wants a simpler construct which prevents only +a CPU from going doing while a task is in a migrate disabled section. + +Implement a per cpu lockless mechanism, which serializes only in the +real unplug case on a global mutex. That serialization affects only +tasks on the cpu which should be brought down. + +Signed-off-by: Thomas Gleixner +--- + include/linux/cpu.h | 5 +++++ + kernel/cpu.c | 15 +++++++++++++++ + kernel/sched/core.c | 4 ++++ + 3 files changed, 24 insertions(+) + +--- a/include/linux/cpu.h ++++ b/include/linux/cpu.h +@@ -108,6 +108,8 @@ extern void cpu_hotplug_disable(void); + extern void cpu_hotplug_enable(void); + void clear_tasks_mm_cpumask(int cpu); + int cpu_down(unsigned int cpu); ++extern void pin_current_cpu(void); ++extern void unpin_current_cpu(void); + + #else /* CONFIG_HOTPLUG_CPU */ + +@@ -118,6 +120,9 @@ static inline void cpus_read_unlock(void + static inline void lockdep_assert_cpus_held(void) { } + static inline void cpu_hotplug_disable(void) { } + static inline void cpu_hotplug_enable(void) { } ++static inline void pin_current_cpu(void) { } ++static inline void unpin_current_cpu(void) { } ++ + #endif /* !CONFIG_HOTPLUG_CPU */ + + /* Wrappers which go away once all code is converted */ +--- a/kernel/cpu.c ++++ b/kernel/cpu.c +@@ -282,6 +282,21 @@ static int cpu_hotplug_disabled; + + #ifdef CONFIG_HOTPLUG_CPU + ++/** ++ * pin_current_cpu - Prevent the current cpu from being unplugged ++ */ ++void pin_current_cpu(void) ++{ ++ ++} ++ ++/** ++ * unpin_current_cpu - Allow unplug of current cpu ++ */ ++void unpin_current_cpu(void) ++{ ++} ++ + DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); + + void cpus_read_lock(void) +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7225,6 +7225,7 @@ void migrate_disable(void) + } + + preempt_disable(); ++ pin_current_cpu(); + + migrate_disable_update_cpus_allowed(p); + p->migrate_disable = 1; +@@ -7290,12 +7291,15 @@ void migrate_enable(void) + arg.task = p; + arg.dest_cpu = dest_cpu; + ++ unpin_current_cpu(); + preempt_enable(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); ++ + return; + } + } ++ unpin_current_cpu(); + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); diff --git a/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch b/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch new file mode 100644 index 000000000..79c9d3cd9 --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch @@ -0,0 +1,92 @@ +From: Yang Shi +Date: Mon, 16 Sep 2013 14:09:19 -0700 +Subject: hrtimer: Move schedule_work call to helper thread +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When run ltp leapsec_timer test, the following call trace is caught: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 1, pid: 0, name: swapper/1 +Preemption disabled at:[] cpu_startup_entry+0x133/0x310 + +CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffffffff81c2f800 ffff880076843e40 ffffffff8169918d ffff880076843e58 +ffffffff8106db31 ffff88007684b4a0 ffff880076843e70 ffffffff8169d9c0 +ffff88007684b4a0 ffff880076843eb0 ffffffff81059da1 0000001876851200 +Call Trace: + [] dump_stack+0x19/0x1b +[] __might_sleep+0xf1/0x170 +[] rt_spin_lock+0x20/0x50 +[] queue_work_on+0x61/0x100 +[] clock_was_set_delayed+0x21/0x30 +[] do_timer+0x40e/0x660 +[] tick_do_update_jiffies64+0xf7/0x140 +[] tick_check_idle+0x92/0xc0 +[] irq_enter+0x57/0x70 +[] smp_apic_timer_interrupt+0x3e/0x9b +[] apic_timer_interrupt+0x6a/0x70 + [] ? cpuidle_enter_state+0x4c/0xc0 +[] cpuidle_idle_call+0xd8/0x2d0 +[] arch_cpu_idle+0xe/0x30 +[] cpu_startup_entry+0x19e/0x310 +[] start_secondary+0x1ad/0x1b0 + +The clock_was_set_delayed is called in hard IRQ handler (timer interrupt), which +calls schedule_work. + +Under PREEMPT_RT_FULL, schedule_work calls spinlocks which could sleep, so it's +not safe to call schedule_work in interrupt context. + +Reference upstream commit b68d61c705ef02384c0538b8d9374545097899ca +(rt,ntp: Move call to schedule_delayed_work() to helper thread) +from git://git.kernel.org/pub/scm/linux/kernel/git/rt/linux-stable-rt.git, which +makes a similar change. + +Signed-off-by: Yang Shi +[bigeasy: use swork_queue() instead a helper thread] +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/time/hrtimer.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -730,6 +730,29 @@ static void hrtimer_switch_to_hres(void) + retrigger_next_event(NULL); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++static struct swork_event clock_set_delay_work; ++ ++static void run_clock_set_delay(struct swork_event *event) ++{ ++ clock_was_set(); ++} ++ ++void clock_was_set_delayed(void) ++{ ++ swork_queue(&clock_set_delay_work); ++} ++ ++static __init int create_clock_set_delay_thread(void) ++{ ++ WARN_ON(swork_get()); ++ INIT_SWORK(&clock_set_delay_work, run_clock_set_delay); ++ return 0; ++} ++early_initcall(create_clock_set_delay_thread); ++#else /* PREEMPT_RT_FULL */ ++ + static void clock_was_set_work(struct work_struct *work) + { + clock_was_set(); +@@ -745,6 +768,7 @@ void clock_was_set_delayed(void) + { + schedule_work(&hrtimer_work); + } ++#endif + + #else + diff --git a/debian/patches/features/all/rt/hrtimer-by-timers-by-default-into-the-softirq-context.patch b/debian/patches/features/all/rt/hrtimer-by-timers-by-default-into-the-softirq-context.patch new file mode 100644 index 000000000..dc729ccec --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-by-timers-by-default-into-the-softirq-context.patch @@ -0,0 +1,210 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 3 Jul 2009 08:44:31 -0500 +Subject: hrtimer: by timers by default into the softirq context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +We can't have hrtimers callbacks running in hardirq context on RT. Therefore +the timers are deferred to the softirq context by default. +There are few timers which expect to be run in hardirq context even on RT. +Those are: +- very short running where low latency is critical (kvm lapic) +- timers which take raw locks and need run in hard-irq context (perf, sched) +- wake up related timer (kernel side of clock_nanosleep() and so on) + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/kvm/lapic.c | 2 +- + include/linux/hrtimer.h | 6 ++++++ + kernel/events/core.c | 4 ++-- + kernel/sched/core.c | 2 +- + kernel/sched/deadline.c | 2 +- + kernel/sched/fair.c | 4 ++-- + kernel/sched/rt.c | 4 ++-- + kernel/time/hrtimer.c | 21 +++++++++++++++++++-- + kernel/time/tick-broadcast-hrtimer.c | 2 +- + kernel/time/tick-sched.c | 2 +- + kernel/watchdog.c | 2 +- + 11 files changed, 37 insertions(+), 14 deletions(-) + +--- a/arch/x86/kvm/lapic.c ++++ b/arch/x86/kvm/lapic.c +@@ -2176,7 +2176,7 @@ int kvm_create_lapic(struct kvm_vcpu *vc + apic->vcpu = vcpu; + + hrtimer_init(&apic->lapic_timer.timer, CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS_PINNED); ++ HRTIMER_MODE_ABS_PINNED_HARD); + apic->lapic_timer.timer.function = apic_timer_fn; + + /* +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -42,6 +42,7 @@ enum hrtimer_mode { + HRTIMER_MODE_REL = 0x01, + HRTIMER_MODE_PINNED = 0x02, + HRTIMER_MODE_SOFT = 0x04, ++ HRTIMER_MODE_HARD = 0x08, + + HRTIMER_MODE_ABS_PINNED = HRTIMER_MODE_ABS | HRTIMER_MODE_PINNED, + HRTIMER_MODE_REL_PINNED = HRTIMER_MODE_REL | HRTIMER_MODE_PINNED, +@@ -52,6 +53,11 @@ enum hrtimer_mode { + HRTIMER_MODE_ABS_PINNED_SOFT = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_SOFT, + HRTIMER_MODE_REL_PINNED_SOFT = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_SOFT, + ++ HRTIMER_MODE_ABS_HARD = HRTIMER_MODE_ABS | HRTIMER_MODE_HARD, ++ HRTIMER_MODE_REL_HARD = HRTIMER_MODE_REL | HRTIMER_MODE_HARD, ++ ++ HRTIMER_MODE_ABS_PINNED_HARD = HRTIMER_MODE_ABS_PINNED | HRTIMER_MODE_HARD, ++ HRTIMER_MODE_REL_PINNED_HARD = HRTIMER_MODE_REL_PINNED | HRTIMER_MODE_HARD, + }; + + /* +--- a/kernel/events/core.c ++++ b/kernel/events/core.c +@@ -1102,7 +1102,7 @@ static void __perf_mux_hrtimer_init(stru + cpuctx->hrtimer_interval = ns_to_ktime(NSEC_PER_MSEC * interval); + + raw_spin_lock_init(&cpuctx->hrtimer_lock); +- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); ++ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); + timer->function = perf_mux_hrtimer_handler; + } + +@@ -9166,7 +9166,7 @@ static void perf_swevent_init_hrtimer(st + if (!is_sampling_event(event)) + return; + +- hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&hwc->hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + hwc->hrtimer.function = perf_swevent_hrtimer; + + /* +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -321,7 +321,7 @@ static void hrtick_rq_init(struct rq *rq + rq->hrtick_csd.info = rq; + #endif + +- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + rq->hrtick_timer.function = hrtick; + } + #else /* CONFIG_SCHED_HRTICK */ +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -1053,7 +1053,7 @@ void init_dl_task_timer(struct sched_dl_ + { + struct hrtimer *timer = &dl_se->dl_timer; + +- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + timer->function = dl_task_timer; + } + +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -5182,9 +5182,9 @@ void init_cfs_bandwidth(struct cfs_bandw + cfs_b->period = ns_to_ktime(default_cfs_period()); + + INIT_LIST_HEAD(&cfs_b->throttled_cfs_rq); +- hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); ++ hrtimer_init(&cfs_b->period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED_HARD); + cfs_b->period_timer.function = sched_cfs_period_timer; +- hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + cfs_b->slack_timer.function = sched_cfs_slack_timer; + } + +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -43,8 +43,8 @@ void init_rt_bandwidth(struct rt_bandwid + + raw_spin_lock_init(&rt_b->rt_runtime_lock); + +- hrtimer_init(&rt_b->rt_period_timer, +- CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, ++ HRTIMER_MODE_REL_HARD); + rt_b->rt_period_timer.function = sched_rt_period_timer; + } + +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1135,7 +1135,9 @@ void hrtimer_start_range_ns(struct hrtim + * Check whether the HRTIMER_MODE_SOFT bit and hrtimer.is_soft + * match. + */ ++#ifndef CONFIG_PREEMPT_RT_BASE + WARN_ON_ONCE(!(mode & HRTIMER_MODE_SOFT) ^ !timer->is_soft); ++#endif + + base = lock_hrtimer_base(timer, &flags); + +@@ -1295,10 +1297,17 @@ static inline int hrtimer_clockid_to_bas + static void __hrtimer_init(struct hrtimer *timer, clockid_t clock_id, + enum hrtimer_mode mode) + { +- bool softtimer = !!(mode & HRTIMER_MODE_SOFT); +- int base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; ++ bool softtimer; ++ int base; + struct hrtimer_cpu_base *cpu_base; + ++ softtimer = !!(mode & HRTIMER_MODE_SOFT); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!softtimer && !(mode & HRTIMER_MODE_HARD)) ++ softtimer = true; ++#endif ++ base = softtimer ? HRTIMER_MAX_CLOCK_BASES / 2 : 0; ++ + memset(timer, 0, sizeof(struct hrtimer)); + + cpu_base = raw_cpu_ptr(&hrtimer_bases); +@@ -1682,6 +1691,14 @@ static void __hrtimer_init_sleeper(struc + enum hrtimer_mode mode, + struct task_struct *task) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!(mode & (HRTIMER_MODE_SOFT | HRTIMER_MODE_HARD))) { ++ if (task_is_realtime(current) || system_state != SYSTEM_RUNNING) ++ mode |= HRTIMER_MODE_HARD; ++ else ++ mode |= HRTIMER_MODE_SOFT; ++ } ++#endif + __hrtimer_init(&sl->timer, clock_id, mode); + sl->timer.function = hrtimer_wakeup; + sl->task = task; +--- a/kernel/time/tick-broadcast-hrtimer.c ++++ b/kernel/time/tick-broadcast-hrtimer.c +@@ -106,7 +106,7 @@ static enum hrtimer_restart bc_handler(s + + void tick_setup_hrtimer_broadcast(void) + { +- hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&bctimer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + bctimer.function = bc_handler; + clockevents_register_device(&ce_broadcast_hrtimer); + } +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -1310,7 +1310,7 @@ void tick_setup_sched_timer(void) + /* + * Emulate tick processing via per-CPU hrtimers: + */ +- hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init(&ts->sched_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_HARD); + ts->sched_timer.function = tick_sched_timer; + + /* Get the next period (per-CPU) */ +--- a/kernel/watchdog.c ++++ b/kernel/watchdog.c +@@ -463,7 +463,7 @@ static void watchdog_enable(unsigned int + * Start the timer first to prevent the NMI watchdog triggering + * before the timer has a chance to fire. + */ +- hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); ++ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); + hrtimer->function = watchdog_timer_fn; + hrtimer_start(hrtimer, ns_to_ktime(sample_period), + HRTIMER_MODE_REL_PINNED); diff --git a/debian/patches/features/all/rt/hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch b/debian/patches/features/all/rt/hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch new file mode 100644 index 000000000..d085b197d --- /dev/null +++ b/debian/patches/features/all/rt/hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch @@ -0,0 +1,252 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 4 Sep 2017 18:31:50 +0200 +Subject: [PATCH] hrtimer: consolidate hrtimer_init() + hrtimer_init_sleeper() calls +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +hrtimer_init_sleeper() calls require a prior initialisation of the +hrtimer object with hrtimer_init(). Lets make the initialisation of +the hrtimer object part of hrtimer_init_sleeper(). To remain +consistent consider init_on_stack as well. + +Beside adapting the hrtimer_init_sleeper[_on_stack]() functions, call +sites need to be updated as well. + +[anna-maria: Updating the commit message] +Signed-off-by: Anna-Maria Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + block/blk-mq.c | 3 +-- + include/linux/hrtimer.h | 19 ++++++++++++++++--- + include/linux/wait.h | 4 ++-- + kernel/futex.c | 19 ++++++++----------- + kernel/time/hrtimer.c | 46 ++++++++++++++++++++++++++++++++++++---------- + net/core/pktgen.c | 4 ++-- + 6 files changed, 65 insertions(+), 30 deletions(-) + +--- a/block/blk-mq.c ++++ b/block/blk-mq.c +@@ -2982,10 +2982,9 @@ static bool blk_mq_poll_hybrid_sleep(str + kt = nsecs; + + mode = HRTIMER_MODE_REL; +- hrtimer_init_on_stack(&hs.timer, CLOCK_MONOTONIC, mode); ++ hrtimer_init_sleeper_on_stack(&hs, CLOCK_MONOTONIC, mode, current); + hrtimer_set_expires(&hs.timer, kt); + +- hrtimer_init_sleeper(&hs, current); + do { + if (blk_mq_rq_state(rq) == MQ_RQ_COMPLETE) + break; +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -364,10 +364,17 @@ DECLARE_PER_CPU(struct tick_device, tick + /* Initialize timers: */ + extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock, + enum hrtimer_mode mode); ++extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task); + + #ifdef CONFIG_DEBUG_OBJECTS_TIMERS + extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock, + enum hrtimer_mode mode); ++extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task); + + extern void destroy_hrtimer_on_stack(struct hrtimer *timer); + #else +@@ -377,6 +384,15 @@ static inline void hrtimer_init_on_stack + { + hrtimer_init(timer, which_clock, mode); + } ++ ++static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) ++{ ++ hrtimer_init_sleeper(sl, clock_id, mode, task); ++} ++ + static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { } + #endif + +@@ -480,9 +496,6 @@ extern long hrtimer_nanosleep(const stru + const enum hrtimer_mode mode, + const clockid_t clockid); + +-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, +- struct task_struct *tsk); +- + extern int schedule_hrtimeout_range(ktime_t *expires, u64 delta, + const enum hrtimer_mode mode); + extern int schedule_hrtimeout_range_clock(ktime_t *expires, +--- a/include/linux/wait.h ++++ b/include/linux/wait.h +@@ -489,8 +489,8 @@ do { \ + int __ret = 0; \ + struct hrtimer_sleeper __t; \ + \ +- hrtimer_init_on_stack(&__t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); \ +- hrtimer_init_sleeper(&__t, current); \ ++ hrtimer_init_sleeper_on_stack(&__t, CLOCK_MONOTONIC, HRTIMER_MODE_REL, \ ++ current); \ + if ((timeout) != KTIME_MAX) \ + hrtimer_start_range_ns(&__t.timer, timeout, \ + current->timer_slack_ns, \ +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2624,10 +2624,9 @@ static int futex_wait(u32 __user *uaddr, + if (abs_time) { + to = &timeout; + +- hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? +- CLOCK_REALTIME : CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? ++ CLOCK_REALTIME : CLOCK_MONOTONIC, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } +@@ -2726,9 +2725,8 @@ static int futex_lock_pi(u32 __user *uad + + if (time) { + to = &timeout; +- hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, CLOCK_REALTIME, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires(&to->timer, *time); + } + +@@ -3144,10 +3142,9 @@ static int futex_wait_requeue_pi(u32 __u + + if (abs_time) { + to = &timeout; +- hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ? +- CLOCK_REALTIME : CLOCK_MONOTONIC, +- HRTIMER_MODE_ABS); +- hrtimer_init_sleeper(to, current); ++ hrtimer_init_sleeper_on_stack(to, (flags & FLAGS_CLOCKRT) ? ++ CLOCK_REALTIME : CLOCK_MONOTONIC, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_range_ns(&to->timer, *abs_time, + current->timer_slack_ns); + } +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1649,13 +1649,44 @@ static enum hrtimer_restart hrtimer_wake + return HRTIMER_NORESTART; + } + +-void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, struct task_struct *task) ++static void __hrtimer_init_sleeper(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) + { ++ __hrtimer_init(&sl->timer, clock_id, mode); + sl->timer.function = hrtimer_wakeup; + sl->task = task; + } ++ ++/** ++ * hrtimer_init_sleeper - initialize sleeper to the given clock ++ * @sl: sleeper to be initialized ++ * @clock_id: the clock to be used ++ * @mode: timer mode abs/rel ++ * @task: the task to wake up ++ */ ++void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id, ++ enum hrtimer_mode mode, struct task_struct *task) ++{ ++ debug_init(&sl->timer, clock_id, mode); ++ __hrtimer_init_sleeper(sl, clock_id, mode, task); ++ ++} + EXPORT_SYMBOL_GPL(hrtimer_init_sleeper); + ++#ifdef CONFIG_DEBUG_OBJECTS_TIMERS ++void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl, ++ clockid_t clock_id, ++ enum hrtimer_mode mode, ++ struct task_struct *task) ++{ ++ debug_object_init_on_stack(&sl->timer, &hrtimer_debug_descr); ++ __hrtimer_init_sleeper(sl, clock_id, mode, task); ++} ++EXPORT_SYMBOL_GPL(hrtimer_init_sleeper_on_stack); ++#endif ++ + int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts) + { + switch(restart->nanosleep.type) { +@@ -1679,8 +1710,6 @@ static int __sched do_nanosleep(struct h + { + struct restart_block *restart; + +- hrtimer_init_sleeper(t, current); +- + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t->timer, mode); +@@ -1717,10 +1746,9 @@ static long __sched hrtimer_nanosleep_re + struct hrtimer_sleeper t; + int ret; + +- hrtimer_init_on_stack(&t.timer, restart->nanosleep.clockid, +- HRTIMER_MODE_ABS); ++ hrtimer_init_sleeper_on_stack(&t, restart->nanosleep.clockid, ++ HRTIMER_MODE_ABS, current); + hrtimer_set_expires_tv64(&t.timer, restart->nanosleep.expires); +- + ret = do_nanosleep(&t, HRTIMER_MODE_ABS); + destroy_hrtimer_on_stack(&t.timer); + return ret; +@@ -1738,7 +1766,7 @@ long hrtimer_nanosleep(const struct time + if (dl_task(current) || rt_task(current)) + slack = 0; + +- hrtimer_init_on_stack(&t.timer, clockid, mode); ++ hrtimer_init_sleeper_on_stack(&t, clockid, mode, current); + hrtimer_set_expires_range_ns(&t.timer, timespec64_to_ktime(*rqtp), slack); + ret = do_nanosleep(&t, mode); + if (ret != -ERESTART_RESTARTBLOCK) +@@ -1937,11 +1965,9 @@ schedule_hrtimeout_range_clock(ktime_t * + return -EINTR; + } + +- hrtimer_init_on_stack(&t.timer, clock_id, mode); ++ hrtimer_init_sleeper_on_stack(&t, clock_id, mode, current); + hrtimer_set_expires_range_ns(&t.timer, *expires, delta); + +- hrtimer_init_sleeper(&t, current); +- + hrtimer_start_expires(&t.timer, mode); + + if (likely(t.task)) +--- a/net/core/pktgen.c ++++ b/net/core/pktgen.c +@@ -2162,7 +2162,8 @@ static void spin(struct pktgen_dev *pkt_ + s64 remaining; + struct hrtimer_sleeper t; + +- hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); ++ hrtimer_init_sleeper_on_stack(&t, CLOCK_MONOTONIC, HRTIMER_MODE_ABS, ++ current); + hrtimer_set_expires(&t.timer, spin_until); + + remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); +@@ -2177,7 +2178,6 @@ static void spin(struct pktgen_dev *pkt_ + } while (ktime_compare(end_time, spin_until) < 0); + } else { + /* see do_nanosleep */ +- hrtimer_init_sleeper(&t, current); + do { + set_current_state(TASK_INTERRUPTIBLE); + hrtimer_start_expires(&t.timer, HRTIMER_MODE_ABS); diff --git a/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch b/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch new file mode 100644 index 000000000..2b7592836 --- /dev/null +++ b/debian/patches/features/all/rt/hrtimers-prepare-full-preemption.patch @@ -0,0 +1,273 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: hrtimers: Prepare full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Make cancellation of a running callback in softirq context safe +against preemption. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + fs/timerfd.c | 5 ++++- + include/linux/hrtimer.h | 13 ++++++++++++- + include/linux/posix-timers.h | 2 +- + kernel/time/alarmtimer.c | 2 +- + kernel/time/hrtimer.c | 33 ++++++++++++++++++++++++++++++++- + kernel/time/itimer.c | 1 + + kernel/time/posix-timers.c | 39 +++++++++++++++++++++++++++++++++++++-- + 7 files changed, 88 insertions(+), 7 deletions(-) + +--- a/fs/timerfd.c ++++ b/fs/timerfd.c +@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, i + break; + } + spin_unlock_irq(&ctx->wqh.lock); +- cpu_relax(); ++ if (isalarm(ctx)) ++ hrtimer_wait_for_timer(&ctx->t.alarm.timer); ++ else ++ hrtimer_wait_for_timer(&ctx->t.tmr); + } + + /* +--- a/include/linux/hrtimer.h ++++ b/include/linux/hrtimer.h +@@ -22,6 +22,7 @@ + #include + #include + #include ++#include + + struct hrtimer_clock_base; + struct hrtimer_cpu_base; +@@ -216,6 +217,9 @@ struct hrtimer_cpu_base { + ktime_t expires_next; + struct hrtimer *next_timer; + ktime_t softirq_expires_next; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ wait_queue_head_t wait; ++#endif + struct hrtimer *softirq_next_timer; + struct hrtimer_clock_base clock_base[HRTIMER_MAX_CLOCK_BASES]; + } ____cacheline_aligned; +@@ -433,6 +437,13 @@ static inline void hrtimer_restart(struc + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* Softirq preemption could deadlock timer removal */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ extern void hrtimer_wait_for_timer(const struct hrtimer *timer); ++#else ++# define hrtimer_wait_for_timer(timer) do { cpu_relax(); } while (0) ++#endif ++ + /* Query timers: */ + extern ktime_t __hrtimer_get_remaining(const struct hrtimer *timer, bool adjust); + +@@ -458,7 +469,7 @@ static inline int hrtimer_is_queued(stru + * Helper function to check, whether the timer is running the callback + * function + */ +-static inline int hrtimer_callback_running(struct hrtimer *timer) ++static inline int hrtimer_callback_running(const struct hrtimer *timer) + { + return timer->base->running == timer; + } +--- a/include/linux/posix-timers.h ++++ b/include/linux/posix-timers.h +@@ -114,8 +114,8 @@ struct k_itimer { + struct { + struct alarm alarmtimer; + } alarm; +- struct rcu_head rcu; + } it; ++ struct rcu_head rcu; + }; + + void run_posix_cpu_timers(struct task_struct *task); +--- a/kernel/time/alarmtimer.c ++++ b/kernel/time/alarmtimer.c +@@ -436,7 +436,7 @@ int alarm_cancel(struct alarm *alarm) + int ret = alarm_try_to_cancel(alarm); + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(&alarm->timer); + } + } + EXPORT_SYMBOL_GPL(alarm_cancel); +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -939,6 +939,33 @@ u64 hrtimer_forward(struct hrtimer *time + } + EXPORT_SYMBOL_GPL(hrtimer_forward); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define wake_up_timer_waiters(b) wake_up(&(b)->wait) ++ ++/** ++ * hrtimer_wait_for_timer - Wait for a running timer ++ * ++ * @timer: timer to wait for ++ * ++ * The function waits in case the timers callback function is ++ * currently executed on the waitqueue of the timer base. The ++ * waitqueue is woken up after the timer callback function has ++ * finished execution. ++ */ ++void hrtimer_wait_for_timer(const struct hrtimer *timer) ++{ ++ struct hrtimer_clock_base *base = timer->base; ++ ++ if (base && base->cpu_base && ++ base->index >= HRTIMER_BASE_MONOTONIC_SOFT) ++ wait_event(base->cpu_base->wait, ++ !(hrtimer_callback_running(timer))); ++} ++ ++#else ++# define wake_up_timer_waiters(b) do { } while (0) ++#endif ++ + /* + * enqueue_hrtimer - internal function to (re)start a timer + * +@@ -1171,7 +1198,7 @@ int hrtimer_cancel(struct hrtimer *timer + + if (ret >= 0) + return ret; +- cpu_relax(); ++ hrtimer_wait_for_timer(timer); + } + } + EXPORT_SYMBOL_GPL(hrtimer_cancel); +@@ -1477,6 +1504,7 @@ static __latent_entropy void hrtimer_run + hrtimer_update_softirq_timer(cpu_base, true); + + raw_spin_unlock_irqrestore(&cpu_base->lock, flags); ++ wake_up_timer_waiters(cpu_base); + } + + #ifdef CONFIG_HIGH_RES_TIMERS +@@ -1847,6 +1875,9 @@ int hrtimers_prepare_cpu(unsigned int cp + cpu_base->softirq_next_timer = NULL; + cpu_base->expires_next = KTIME_MAX; + cpu_base->softirq_expires_next = KTIME_MAX; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ init_waitqueue_head(&cpu_base->wait); ++#endif + return 0; + } + +--- a/kernel/time/itimer.c ++++ b/kernel/time/itimer.c +@@ -214,6 +214,7 @@ int do_setitimer(int which, struct itime + /* We are sharing ->siglock with it_real_fn() */ + if (hrtimer_try_to_cancel(timer) < 0) { + spin_unlock_irq(&tsk->sighand->siglock); ++ hrtimer_wait_for_timer(&tsk->signal->real_timer); + goto again; + } + expires = timeval_to_ktime(value->it_value); +--- a/kernel/time/posix-timers.c ++++ b/kernel/time/posix-timers.c +@@ -469,7 +469,7 @@ static struct k_itimer * alloc_posix_tim + + static void k_itimer_rcu_free(struct rcu_head *head) + { +- struct k_itimer *tmr = container_of(head, struct k_itimer, it.rcu); ++ struct k_itimer *tmr = container_of(head, struct k_itimer, rcu); + + kmem_cache_free(posix_timers_cache, tmr); + } +@@ -486,7 +486,7 @@ static void release_posix_timer(struct k + } + put_pid(tmr->it_pid); + sigqueue_free(tmr->sigq); +- call_rcu(&tmr->it.rcu, k_itimer_rcu_free); ++ call_rcu(&tmr->rcu, k_itimer_rcu_free); + } + + static int common_timer_create(struct k_itimer *new_timer) +@@ -825,6 +825,22 @@ static void common_hrtimer_arm(struct k_ + hrtimer_start_expires(timer, HRTIMER_MODE_ABS); + } + ++/* ++ * Protected by RCU! ++ */ ++static void timer_wait_for_callback(const struct k_clock *kc, struct k_itimer *timr) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (kc->timer_arm == common_hrtimer_arm) ++ hrtimer_wait_for_timer(&timr->it.real.timer); ++ else if (kc == &alarm_clock) ++ hrtimer_wait_for_timer(&timr->it.alarm.alarmtimer.timer); ++ else ++ /* FIXME: Whacky hack for posix-cpu-timers */ ++ schedule_timeout(1); ++#endif ++} ++ + static int common_hrtimer_try_to_cancel(struct k_itimer *timr) + { + return hrtimer_try_to_cancel(&timr->it.real.timer); +@@ -889,6 +905,7 @@ static int do_timer_settime(timer_t time + if (!timr) + return -EINVAL; + ++ rcu_read_lock(); + kc = timr->kclock; + if (WARN_ON_ONCE(!kc || !kc->timer_set)) + error = -EINVAL; +@@ -897,9 +914,12 @@ static int do_timer_settime(timer_t time + + unlock_timer(timr, flag); + if (error == TIMER_RETRY) { ++ timer_wait_for_callback(kc, timr); + old_spec64 = NULL; // We already got the old time... ++ rcu_read_unlock(); + goto retry; + } ++ rcu_read_unlock(); + + return error; + } +@@ -981,10 +1001,15 @@ SYSCALL_DEFINE1(timer_delete, timer_t, t + if (!timer) + return -EINVAL; + ++ rcu_read_lock(); + if (timer_delete_hook(timer) == TIMER_RETRY) { + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } ++ rcu_read_unlock(); + + spin_lock(¤t->sighand->siglock); + list_del(&timer->list); +@@ -1010,8 +1035,18 @@ static void itimer_delete(struct k_itime + retry_delete: + spin_lock_irqsave(&timer->it_lock, flags); + ++ /* On RT we can race with a deletion */ ++ if (!timer->it_signal) { ++ unlock_timer(timer, flags); ++ return; ++ } ++ + if (timer_delete_hook(timer) == TIMER_RETRY) { ++ rcu_read_lock(); + unlock_timer(timer, flags); ++ timer_wait_for_callback(clockid_to_kclock(timer->it_clock), ++ timer); ++ rcu_read_unlock(); + goto retry_delete; + } + list_del(&timer->list); diff --git a/debian/patches/features/all/rt/iommu-amd-drop-irqs_disabled-warn_on.patch b/debian/patches/features/all/rt/iommu-amd-drop-irqs_disabled-warn_on.patch new file mode 100644 index 000000000..a041c2c67 --- /dev/null +++ b/debian/patches/features/all/rt/iommu-amd-drop-irqs_disabled-warn_on.patch @@ -0,0 +1,53 @@ +From: Anna-Maria Gleixner +Subject: [PATCH] iommu/amd: Remove redundant WARN_ON() +Date: Fri, 20 Jul 2018 10:45:45 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The WARN_ON() was introduced in commit 272e4f99e966 ("iommu/amd: WARN +when __[attach|detach]_device are called with irqs enabled") to ensure +that the domain->lock is taken in proper irqs disabled context. This +is required, because the domain->lock is taken as well in irq +context. + +The proper context check by the WARN_ON() is redundant, because it is +already covered by LOCKDEP. When working with locks and changing +context, a run with LOCKDEP is required anyway and would detect the +wrong lock context. + +Furthermore all callers for those functions are within the same file +and all callers acquire another lock which already disables interrupts. + +Signed-off-by: Anna-Maria Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/iommu/amd_iommu.c | 12 ------------ + 1 file changed, 12 deletions(-) + +--- a/drivers/iommu/amd_iommu.c ++++ b/drivers/iommu/amd_iommu.c +@@ -1944,12 +1944,6 @@ static int __attach_device(struct iommu_ + { + int ret; + +- /* +- * Must be called with IRQs disabled. Warn here to detect early +- * when its not. +- */ +- WARN_ON(!irqs_disabled()); +- + /* lock domain */ + spin_lock(&domain->lock); + +@@ -2115,12 +2109,6 @@ static void __detach_device(struct iommu + { + struct protection_domain *domain; + +- /* +- * Must be called with IRQs disabled. Warn here to detect early +- * when its not. +- */ +- WARN_ON(!irqs_disabled()); +- + domain = dev_data->domain; + + spin_lock(&domain->lock); diff --git a/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch b/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch new file mode 100644 index 000000000..2db5ca355 --- /dev/null +++ b/debian/patches/features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch @@ -0,0 +1,147 @@ +Subject: genirq: Allow disabling of softirq processing in irq thread context +From: Thomas Gleixner +Date: Tue, 31 Jan 2012 13:01:27 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The processing of softirqs in irq thread context is a performance gain +for the non-rt workloads of a system, but it's counterproductive for +interrupts which are explicitely related to the realtime +workload. Allow such interrupts to prevent softirq processing in their +thread context. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/interrupt.h | 2 ++ + include/linux/irq.h | 4 +++- + kernel/irq/manage.c | 13 ++++++++++++- + kernel/irq/settings.h | 12 ++++++++++++ + kernel/softirq.c | 9 +++++++++ + 5 files changed, 38 insertions(+), 2 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -62,6 +62,7 @@ + * interrupt handler after suspending interrupts. For system + * wakeup devices users need to implement wakeup detection in + * their interrupt handlers. ++ * IRQF_NO_SOFTIRQ_CALL - Do not process softirqs in the irq thread context (RT) + */ + #define IRQF_SHARED 0x00000080 + #define IRQF_PROBE_SHARED 0x00000100 +@@ -75,6 +76,7 @@ + #define IRQF_NO_THREAD 0x00010000 + #define IRQF_EARLY_RESUME 0x00020000 + #define IRQF_COND_SUSPEND 0x00040000 ++#define IRQF_NO_SOFTIRQ_CALL 0x00080000 + + #define IRQF_TIMER (__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD) + +--- a/include/linux/irq.h ++++ b/include/linux/irq.h +@@ -69,6 +69,7 @@ enum irqchip_irq_state; + * IRQ_IS_POLLED - Always polled by another interrupt. Exclude + * it from the spurious interrupt detection + * mechanism and from core side polling. ++ * IRQ_NO_SOFTIRQ_CALL - No softirq processing in the irq thread context (RT) + * IRQ_DISABLE_UNLAZY - Disable lazy irq disable + */ + enum { +@@ -96,13 +97,14 @@ enum { + IRQ_PER_CPU_DEVID = (1 << 17), + IRQ_IS_POLLED = (1 << 18), + IRQ_DISABLE_UNLAZY = (1 << 19), ++ IRQ_NO_SOFTIRQ_CALL = (1 << 20), + }; + + #define IRQF_MODIFY_MASK \ + (IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \ + IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \ + IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \ +- IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY) ++ IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_NO_SOFTIRQ_CALL) + + #define IRQ_NO_BALANCING_MASK (IRQ_PER_CPU | IRQ_NO_BALANCING) + +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -960,7 +960,15 @@ irq_forced_thread_fn(struct irq_desc *de + local_bh_disable(); + ret = action->thread_fn(action->irq, action->dev_id); + irq_finalize_oneshot(desc, action); +- local_bh_enable(); ++ /* ++ * Interrupts which have real time requirements can be set up ++ * to avoid softirq processing in the thread handler. This is ++ * safe as these interrupts do not raise soft interrupts. ++ */ ++ if (irq_settings_no_softirq_call(desc)) ++ _local_bh_enable(); ++ else ++ local_bh_enable(); + return ret; + } + +@@ -1470,6 +1478,9 @@ static int + irqd_set(&desc->irq_data, IRQD_NO_BALANCING); + } + ++ if (new->flags & IRQF_NO_SOFTIRQ_CALL) ++ irq_settings_set_no_softirq_call(desc); ++ + if (irq_settings_can_autoenable(desc)) { + irq_startup(desc, IRQ_RESEND, IRQ_START_COND); + } else { +--- a/kernel/irq/settings.h ++++ b/kernel/irq/settings.h +@@ -17,6 +17,7 @@ enum { + _IRQ_PER_CPU_DEVID = IRQ_PER_CPU_DEVID, + _IRQ_IS_POLLED = IRQ_IS_POLLED, + _IRQ_DISABLE_UNLAZY = IRQ_DISABLE_UNLAZY, ++ _IRQ_NO_SOFTIRQ_CALL = IRQ_NO_SOFTIRQ_CALL, + _IRQF_MODIFY_MASK = IRQF_MODIFY_MASK, + }; + +@@ -31,6 +32,7 @@ enum { + #define IRQ_PER_CPU_DEVID GOT_YOU_MORON + #define IRQ_IS_POLLED GOT_YOU_MORON + #define IRQ_DISABLE_UNLAZY GOT_YOU_MORON ++#define IRQ_NO_SOFTIRQ_CALL GOT_YOU_MORON + #undef IRQF_MODIFY_MASK + #define IRQF_MODIFY_MASK GOT_YOU_MORON + +@@ -41,6 +43,16 @@ irq_settings_clr_and_set(struct irq_desc + desc->status_use_accessors |= (set & _IRQF_MODIFY_MASK); + } + ++static inline bool irq_settings_no_softirq_call(struct irq_desc *desc) ++{ ++ return desc->status_use_accessors & _IRQ_NO_SOFTIRQ_CALL; ++} ++ ++static inline void irq_settings_set_no_softirq_call(struct irq_desc *desc) ++{ ++ desc->status_use_accessors |= _IRQ_NO_SOFTIRQ_CALL; ++} ++ + static inline bool irq_settings_is_per_cpu(struct irq_desc *desc) + { + return desc->status_use_accessors & _IRQ_PER_CPU; +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -598,6 +598,15 @@ void __local_bh_enable(void) + } + EXPORT_SYMBOL(__local_bh_enable); + ++void _local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(_local_bh_enable); ++ + int in_serving_softirq(void) + { + return current->flags & PF_IN_SOFTIRQ; diff --git a/debian/patches/features/all/rt/irqchip-gic-v3-its-Make-its_lock-a-raw_spin_lock_t.patch b/debian/patches/features/all/rt/irqchip-gic-v3-its-Make-its_lock-a-raw_spin_lock_t.patch new file mode 100644 index 000000000..d1a11bcdd --- /dev/null +++ b/debian/patches/features/all/rt/irqchip-gic-v3-its-Make-its_lock-a-raw_spin_lock_t.patch @@ -0,0 +1,90 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 13 Jul 2018 15:30:52 +0200 +Subject: [PATCH] irqchip/gic-v3-its: Make its_lock a raw_spin_lock_t +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The its_lock lock is held while a new device is added to the list and +during setup while the CPU is booted. Even on -RT the CPU-bootup is +performed with disabled interrupts. + +Make its_lock a raw_spin_lock_t. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/irqchip/irq-gic-v3-its.c | 18 +++++++++--------- + 1 file changed, 9 insertions(+), 9 deletions(-) + +--- a/drivers/irqchip/irq-gic-v3-its.c ++++ b/drivers/irqchip/irq-gic-v3-its.c +@@ -160,7 +160,7 @@ static struct { + } vpe_proxy; + + static LIST_HEAD(its_nodes); +-static DEFINE_SPINLOCK(its_lock); ++static DEFINE_RAW_SPINLOCK(its_lock); + static struct rdists *gic_rdists; + static struct irq_domain *its_parent; + +@@ -1997,12 +1997,12 @@ static void its_cpu_init_collections(voi + { + struct its_node *its; + +- spin_lock(&its_lock); ++ raw_spin_lock(&its_lock); + + list_for_each_entry(its, &its_nodes, entry) + its_cpu_init_collection(its); + +- spin_unlock(&its_lock); ++ raw_spin_unlock(&its_lock); + } + + static struct its_device *its_find_device(struct its_node *its, u32 dev_id) +@@ -3070,7 +3070,7 @@ static int its_save_disable(void) + struct its_node *its; + int err = 0; + +- spin_lock(&its_lock); ++ raw_spin_lock(&its_lock); + list_for_each_entry(its, &its_nodes, entry) { + void __iomem *base; + +@@ -3102,7 +3102,7 @@ static int its_save_disable(void) + writel_relaxed(its->ctlr_save, base + GITS_CTLR); + } + } +- spin_unlock(&its_lock); ++ raw_spin_unlock(&its_lock); + + return err; + } +@@ -3112,7 +3112,7 @@ static void its_restore_enable(void) + struct its_node *its; + int ret; + +- spin_lock(&its_lock); ++ raw_spin_lock(&its_lock); + list_for_each_entry(its, &its_nodes, entry) { + void __iomem *base; + int i; +@@ -3164,7 +3164,7 @@ static void its_restore_enable(void) + GITS_TYPER_HCC(gic_read_typer(base + GITS_TYPER))) + its_cpu_init_collection(its); + } +- spin_unlock(&its_lock); ++ raw_spin_unlock(&its_lock); + } + + static struct syscore_ops its_syscore_ops = { +@@ -3398,9 +3398,9 @@ static int __init its_probe_one(struct r + if (err) + goto out_free_tables; + +- spin_lock(&its_lock); ++ raw_spin_lock(&its_lock); + list_add(&its->entry, &its_nodes); +- spin_unlock(&its_lock); ++ raw_spin_unlock(&its_lock); + + return 0; + diff --git a/debian/patches/features/all/rt/irqchip-gic-v3-its-Move-ITS-pend_page-allocation-int.patch b/debian/patches/features/all/rt/irqchip-gic-v3-its-Move-ITS-pend_page-allocation-int.patch new file mode 100644 index 000000000..cac14b72a --- /dev/null +++ b/debian/patches/features/all/rt/irqchip-gic-v3-its-Move-ITS-pend_page-allocation-int.patch @@ -0,0 +1,129 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 13 Jul 2018 15:45:36 +0200 +Subject: [PATCH] irqchip/gic-v3-its: Move ITS' ->pend_page allocation into + an early CPU up hook +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The AP-GIC-starting hook allocates memory for the ->pend_page while the +CPU is started during boot-up. This callback is invoked on the target +CPU with disabled interrupts. +This does not work on -RT beacuse memory allocations are not possible +with disabled interrupts. +Move the memory allocation to an earlier hotplug step which invoked with +enabled interrupts on the boot CPU. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/irqchip/irq-gic-v3-its.c | 60 ++++++++++++++++++++++++++------------- + 1 file changed, 41 insertions(+), 19 deletions(-) + +--- a/drivers/irqchip/irq-gic-v3-its.c ++++ b/drivers/irqchip/irq-gic-v3-its.c +@@ -171,6 +171,7 @@ static DEFINE_RAW_SPINLOCK(vmovp_lock); + static DEFINE_IDA(its_vpeid_ida); + + #define gic_data_rdist() (raw_cpu_ptr(gic_rdists->rdist)) ++#define gic_data_rdist_cpu(cpu) (per_cpu_ptr(gic_rdists->rdist, cpu)) + #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) + #define gic_data_rdist_vlpi_base() (gic_data_rdist_rd_base() + SZ_128K) + +@@ -1853,15 +1854,17 @@ static int its_alloc_collections(struct + return 0; + } + +-static struct page *its_allocate_pending_table(gfp_t gfp_flags) ++static struct page *its_allocate_pending_table(unsigned int cpu) + { + struct page *pend_page; ++ unsigned int order; + /* + * The pending pages have to be at least 64kB aligned, + * hence the 'max(LPI_PENDBASE_SZ, SZ_64K)' below. + */ +- pend_page = alloc_pages(gfp_flags | __GFP_ZERO, +- get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K))); ++ order = get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)); ++ pend_page = alloc_pages_node(cpu_to_node(cpu), GFP_KERNEL | __GFP_ZERO, ++ order); + if (!pend_page) + return NULL; + +@@ -1877,6 +1880,28 @@ static void its_free_pending_table(struc + get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K))); + } + ++static int its_alloc_pend_page(unsigned int cpu) ++{ ++ struct page *pend_page; ++ phys_addr_t paddr; ++ ++ pend_page = gic_data_rdist_cpu(cpu)->pend_page; ++ if (pend_page) ++ return 0; ++ ++ pend_page = its_allocate_pending_table(cpu); ++ if (!pend_page) { ++ pr_err("Failed to allocate PENDBASE for CPU%d\n", ++ smp_processor_id()); ++ return -ENOMEM; ++ } ++ ++ paddr = page_to_phys(pend_page); ++ pr_info("CPU%d: using LPI pending table @%pa\n", cpu, &paddr); ++ gic_data_rdist_cpu(cpu)->pend_page = pend_page; ++ return 0; ++} ++ + static void its_cpu_init_lpis(void) + { + void __iomem *rbase = gic_data_rdist_rd_base(); +@@ -1885,21 +1910,8 @@ static void its_cpu_init_lpis(void) + + /* If we didn't allocate the pending table yet, do it now */ + pend_page = gic_data_rdist()->pend_page; +- if (!pend_page) { +- phys_addr_t paddr; +- +- pend_page = its_allocate_pending_table(GFP_NOWAIT); +- if (!pend_page) { +- pr_err("Failed to allocate PENDBASE for CPU%d\n", +- smp_processor_id()); +- return; +- } +- +- paddr = page_to_phys(pend_page); +- pr_info("CPU%d: using LPI pending table @%pa\n", +- smp_processor_id(), &paddr); +- gic_data_rdist()->pend_page = pend_page; +- } ++ if (!pend_page) ++ return; + + /* set PROPBASE */ + val = (page_to_phys(gic_rdists->prop_page) | +@@ -2732,7 +2744,7 @@ static int its_vpe_init(struct its_vpe * + return vpe_id; + + /* Allocate VPT */ +- vpt_page = its_allocate_pending_table(GFP_KERNEL); ++ vpt_page = its_allocate_pending_table(raw_smp_processor_id()); + if (!vpt_page) { + its_vpe_id_free(vpe_id); + return -ENOMEM; +@@ -3706,6 +3718,16 @@ int __init its_init(struct fwnode_handle + if (err) + return err; + ++ err = cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "irqchip/arm/gicv3:prepare", ++ its_alloc_pend_page, NULL); ++ if (err < 0) { ++ pr_warn("ITS: Can't register CPU-hoplug callback.\n"); ++ return err; ++ } ++ err = its_alloc_pend_page(smp_processor_id()); ++ if (err < 0) ++ return err; ++ + list_for_each_entry(its, &its_nodes, entry) + has_v4 |= its->is_v4; + diff --git a/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch b/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch new file mode 100644 index 000000000..be1dec518 --- /dev/null +++ b/debian/patches/features/all/rt/irqwork-push_most_work_into_softirq_context.patch @@ -0,0 +1,222 @@ +Subject: irqwork: push most work into softirq context +From: Sebastian Andrzej Siewior +Date: Tue, 23 Jun 2015 15:32:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Initially we defered all irqwork into softirq because we didn't want the +latency spikes if perf or another user was busy and delayed the RT task. +The NOHZ trigger (nohz_full_kick_work) was the first user that did not work +as expected if it did not run in the original irqwork context so we had to +bring it back somehow for it. push_irq_work_func is the second one that +requires this. + +This patch adds the IRQ_WORK_HARD_IRQ which makes sure the callback runs +in raw-irq context. Everything else is defered into softirq context. Without +-RT we have the orignal behavior. + +This patch incorporates tglx orignal work which revoked a little bringing back +the arch_irq_work_raise() if possible and a few fixes from Steven Rostedt and +Mike Galbraith, + +[bigeasy: melt tglx's irq_work_tick_soft() which splits irq_work_tick() into a + hard and soft variant] +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/irq_work.h | 8 ++++++ + kernel/irq_work.c | 60 ++++++++++++++++++++++++++++++++++++----------- + kernel/rcu/tree.c | 1 + kernel/sched/topology.c | 1 + kernel/time/tick-sched.c | 1 + kernel/time/timer.c | 1 + 6 files changed, 59 insertions(+), 13 deletions(-) + +--- a/include/linux/irq_work.h ++++ b/include/linux/irq_work.h +@@ -18,6 +18,8 @@ + + /* Doesn't want IPI, wait for tick: */ + #define IRQ_WORK_LAZY BIT(2) ++/* Run hard IRQ context, even on RT */ ++#define IRQ_WORK_HARD_IRQ BIT(3) + + #define IRQ_WORK_CLAIMED (IRQ_WORK_PENDING | IRQ_WORK_BUSY) + +@@ -52,4 +54,10 @@ static inline bool irq_work_needs_cpu(vo + static inline void irq_work_run(void) { } + #endif + ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void); ++#else ++static inline void irq_work_tick_soft(void) { } ++#endif ++ + #endif /* _LINUX_IRQ_WORK_H */ +--- a/kernel/irq_work.c ++++ b/kernel/irq_work.c +@@ -17,6 +17,7 @@ + #include + #include + #include ++#include + #include + + +@@ -64,6 +65,8 @@ void __weak arch_irq_work_raise(void) + */ + bool irq_work_queue_on(struct irq_work *work, int cpu) + { ++ struct llist_head *list; ++ + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(cpu)); + +@@ -76,7 +79,12 @@ bool irq_work_queue_on(struct irq_work * + if (!irq_work_claim(work)) + return false; + +- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu))) ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && !(work->flags & IRQ_WORK_HARD_IRQ)) ++ list = &per_cpu(lazy_list, cpu); ++ else ++ list = &per_cpu(raised_list, cpu); ++ ++ if (llist_add(&work->llnode, list)) + arch_send_call_function_single_ipi(cpu); + + #else /* #ifdef CONFIG_SMP */ +@@ -89,6 +97,9 @@ bool irq_work_queue_on(struct irq_work * + /* Enqueue the irq work @work on the current CPU */ + bool irq_work_queue(struct irq_work *work) + { ++ struct llist_head *list; ++ bool lazy_work, realtime = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); ++ + /* Only queue if not already pending */ + if (!irq_work_claim(work)) + return false; +@@ -96,13 +107,15 @@ bool irq_work_queue(struct irq_work *wor + /* Queue the entry and raise the IPI if needed. */ + preempt_disable(); + +- /* If the work is "lazy", handle it from next tick if any */ +- if (work->flags & IRQ_WORK_LAZY) { +- if (llist_add(&work->llnode, this_cpu_ptr(&lazy_list)) && +- tick_nohz_tick_stopped()) +- arch_irq_work_raise(); +- } else { +- if (llist_add(&work->llnode, this_cpu_ptr(&raised_list))) ++ lazy_work = work->flags & IRQ_WORK_LAZY; ++ ++ if (lazy_work || (realtime && !(work->flags & IRQ_WORK_HARD_IRQ))) ++ list = this_cpu_ptr(&lazy_list); ++ else ++ list = this_cpu_ptr(&raised_list); ++ ++ if (llist_add(&work->llnode, list)) { ++ if (!lazy_work || tick_nohz_tick_stopped()) + arch_irq_work_raise(); + } + +@@ -119,9 +132,8 @@ bool irq_work_needs_cpu(void) + raised = this_cpu_ptr(&raised_list); + lazy = this_cpu_ptr(&lazy_list); + +- if (llist_empty(raised) || arch_irq_work_has_interrupt()) +- if (llist_empty(lazy)) +- return false; ++ if (llist_empty(raised) && llist_empty(lazy)) ++ return false; + + /* All work should have been flushed before going offline */ + WARN_ON_ONCE(cpu_is_offline(smp_processor_id())); +@@ -135,8 +147,12 @@ static void irq_work_run_list(struct lli + struct llist_node *llnode; + unsigned long flags; + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ /* ++ * nort: On RT IRQ-work may run in SOFTIRQ context. ++ */ + BUG_ON(!irqs_disabled()); +- ++#endif + if (llist_empty(list)) + return; + +@@ -168,7 +184,16 @@ static void irq_work_run_list(struct lli + void irq_work_run(void) + { + irq_work_run_list(this_cpu_ptr(&raised_list)); +- irq_work_run_list(this_cpu_ptr(&lazy_list)); ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) { ++ /* ++ * NOTE: we raise softirq via IPI for safety, ++ * and execute in irq_work_tick() to move the ++ * overhead from hard to soft irq context. ++ */ ++ if (!llist_empty(this_cpu_ptr(&lazy_list))) ++ raise_softirq(TIMER_SOFTIRQ); ++ } else ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); + } + EXPORT_SYMBOL_GPL(irq_work_run); + +@@ -178,8 +203,17 @@ void irq_work_tick(void) + + if (!llist_empty(raised) && !arch_irq_work_has_interrupt()) + irq_work_run_list(raised); ++ ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL)) ++ irq_work_run_list(this_cpu_ptr(&lazy_list)); ++} ++ ++#if defined(CONFIG_IRQ_WORK) && defined(CONFIG_PREEMPT_RT_FULL) ++void irq_work_tick_soft(void) ++{ + irq_work_run_list(this_cpu_ptr(&lazy_list)); + } ++#endif + + /* + * Synchronize against the irq_work @entry, ensures the entry is not +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -1294,6 +1294,7 @@ static int rcu_implicit_dynticks_qs(stru + !rdp->rcu_iw_pending && rdp->rcu_iw_gpnum != rnp->gpnum && + (rnp->ffmask & rdp->grpmask)) { + init_irq_work(&rdp->rcu_iw, rcu_iw_handler); ++ rdp->rcu_iw.flags = IRQ_WORK_HARD_IRQ; + rdp->rcu_iw_pending = true; + rdp->rcu_iw_gpnum = rnp->gpnum; + irq_work_queue_on(&rdp->rcu_iw, rdp->cpu); +--- a/kernel/sched/topology.c ++++ b/kernel/sched/topology.c +@@ -279,6 +279,7 @@ static int init_rootdomain(struct root_d + rd->rto_cpu = -1; + raw_spin_lock_init(&rd->rto_lock); + init_irq_work(&rd->rto_push_work, rto_push_irq_work_func); ++ rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ; + #endif + + init_dl_bw(&rd->dl_bw); +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -232,6 +232,7 @@ static void nohz_full_kick_func(struct i + + static DEFINE_PER_CPU(struct irq_work, nohz_full_kick_work) = { + .func = nohz_full_kick_func, ++ .flags = IRQ_WORK_HARD_IRQ, + }; + + /* +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -1717,6 +1717,7 @@ static __latent_entropy void run_timer_s + { + struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); + ++ irq_work_tick_soft(); + /* + * must_forward_clk must be cleared before running timers so that any + * timer functions that call mod_timer will not try to forward the diff --git a/debian/patches/features/all/rt/jump-label-rt.patch b/debian/patches/features/all/rt/jump-label-rt.patch new file mode 100644 index 000000000..1fdf285df --- /dev/null +++ b/debian/patches/features/all/rt/jump-label-rt.patch @@ -0,0 +1,36 @@ +Subject: jump-label: disable if stop_machine() is used +From: Thomas Gleixner +Date: Wed, 08 Jul 2015 17:14:48 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Some architectures are using stop_machine() while switching the opcode which +leads to latency spikes. +The architectures which use stop_machine() atm: +- ARM stop machine +- s390 stop machine + +The architecures which use other sorcery: +- MIPS +- X86 +- powerpc +- sparc +- arm64 + +Signed-off-by: Thomas Gleixner +[bigeasy: only ARM for now] +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/arm/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/arm/Kconfig ++++ b/arch/arm/Kconfig +@@ -50,7 +50,7 @@ config ARM + select HARDIRQS_SW_RESEND + select HAVE_ARCH_AUDITSYSCALL if (AEABI && !OABI_COMPAT) + select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6 +- select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU ++ select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU && !PREEMPT_RT_BASE + select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU + select HAVE_ARCH_MMAP_RND_BITS if MMU + select HAVE_ARCH_SECCOMP_FILTER if (AEABI && !OABI_COMPAT) diff --git a/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch b/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch new file mode 100644 index 000000000..59779179a --- /dev/null +++ b/debian/patches/features/all/rt/kconfig-disable-a-few-options-rt.patch @@ -0,0 +1,34 @@ +Subject: kconfig: Disable config options which are not RT compatible +From: Thomas Gleixner +Date: Sun, 24 Jul 2011 12:11:43 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Disable stuff which is known to have issues on RT + +Signed-off-by: Thomas Gleixner +--- + arch/Kconfig | 1 + + mm/Kconfig | 2 +- + 2 files changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/Kconfig ++++ b/arch/Kconfig +@@ -17,6 +17,7 @@ config OPROFILE + tristate "OProfile system profiling" + depends on PROFILING + depends on HAVE_OPROFILE ++ depends on !PREEMPT_RT_FULL + select RING_BUFFER + select RING_BUFFER_ALLOW_SWAP + help +--- a/mm/Kconfig ++++ b/mm/Kconfig +@@ -378,7 +378,7 @@ config NOMMU_INITIAL_TRIM_EXCESS + + config TRANSPARENT_HUGEPAGE + bool "Transparent Hugepage Support" +- depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE ++ depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE && !PREEMPT_RT_FULL + select COMPACTION + select RADIX_TREE_MULTIORDER + help diff --git a/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch b/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch new file mode 100644 index 000000000..9f1e7a929 --- /dev/null +++ b/debian/patches/features/all/rt/kconfig-preempt-rt-full.patch @@ -0,0 +1,59 @@ +Subject: kconfig: Add PREEMPT_RT_FULL +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 14:58:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Introduce the final symbol for PREEMPT_RT_FULL. + +Signed-off-by: Thomas Gleixner +--- + init/Makefile | 2 +- + kernel/Kconfig.preempt | 8 ++++++++ + scripts/mkcompile_h | 4 +++- + 3 files changed, 12 insertions(+), 2 deletions(-) + +--- a/init/Makefile ++++ b/init/Makefile +@@ -34,4 +34,4 @@ mounts-$(CONFIG_BLK_DEV_MD) += do_mounts + include/generated/compile.h: FORCE + @$($(quiet)chk_compile.h) + $(Q)$(CONFIG_SHELL) $(srctree)/scripts/mkcompile_h $@ \ +- "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CC) $(KBUILD_CFLAGS)" ++ "$(UTS_MACHINE)" "$(CONFIG_SMP)" "$(CONFIG_PREEMPT)" "$(CONFIG_PREEMPT_RT_FULL)" "$(CC) $(KBUILD_CFLAGS)" +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -67,6 +67,14 @@ config PREEMPT_RTB + enables changes which are preliminary for the full preemptible + RT kernel. + ++config PREEMPT_RT_FULL ++ bool "Fully Preemptible Kernel (RT)" ++ depends on IRQ_FORCED_THREADING ++ select PREEMPT_RT_BASE ++ select PREEMPT_RCU ++ help ++ All and everything ++ + endchoice + + config PREEMPT_COUNT +--- a/scripts/mkcompile_h ++++ b/scripts/mkcompile_h +@@ -5,7 +5,8 @@ TARGET=$1 + ARCH=$2 + SMP=$3 + PREEMPT=$4 +-CC=$5 ++RT=$5 ++CC=$6 + + vecho() { [ "${quiet}" = "silent_" ] || echo "$@" ; } + +@@ -53,6 +54,7 @@ UTS_VERSION="#$VERSION" + CONFIG_FLAGS="" + if [ -n "$SMP" ] ; then CONFIG_FLAGS="SMP"; fi + if [ -n "$PREEMPT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS PREEMPT"; fi ++if [ -n "$RT" ] ; then CONFIG_FLAGS="$CONFIG_FLAGS RT"; fi + UTS_VERSION="$UTS_VERSION $CONFIG_FLAGS $TIMESTAMP" + + # Truncate to maximum length diff --git a/debian/patches/features/all/rt/kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch b/debian/patches/features/all/rt/kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch new file mode 100644 index 000000000..7a147487c --- /dev/null +++ b/debian/patches/features/all/rt/kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch @@ -0,0 +1,42 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 19 May 2016 17:45:27 +0200 +Subject: [PATCH] kernel/printk: Don't try to print from IRQ/NMI region +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On -RT we try to acquire sleeping locks which might lead to warnings +from lockdep or a warn_on() from spin_try_lock() (which is a rtmutex on +RT). +We don't print in general from a IRQ off region so we should not try +this via console_unblank() / bust_spinlocks() as well. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/printk/printk.c | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1771,6 +1771,11 @@ static void call_console_drivers(const c + if (!console_drivers) + return; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) +@@ -2519,6 +2524,11 @@ void console_unblank(void) + { + struct console *c; + ++ if (IS_ENABLED(CONFIG_PREEMPT_RT_BASE)) { ++ if (in_irq() || in_nmi()) ++ return; ++ } ++ + /* + * console_unblank can no longer be called in interrupt context unless + * oops_in_progress is set to 1.. diff --git a/debian/patches/features/all/rt/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch b/debian/patches/features/all/rt/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch new file mode 100644 index 000000000..c703b70b7 --- /dev/null +++ b/debian/patches/features/all/rt/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch @@ -0,0 +1,722 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 4 Apr 2017 12:50:16 +0200 +Subject: [PATCH] kernel: sched: Provide a pointer to the valid CPU mask +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In commit 4b53a3412d66 ("sched/core: Remove the tsk_nr_cpus_allowed() +wrapper") the tsk_nr_cpus_allowed() wrapper was removed. There was not +much difference in !RT but in RT we used this to implement +migrate_disable(). Within a migrate_disable() section the CPU mask is +restricted to single CPU while the "normal" CPU mask remains untouched. + +As an alternative implementation Ingo suggested to use + struct task_struct { + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; + }; +with + t->cpus_allowed_ptr = &t->cpus_allowed; + +In -RT we then can switch the cpus_ptr to + t->cpus_allowed_ptr = &cpumask_of(task_cpu(p)); + +in a migration disabled region. The rules are simple: +- Code that 'uses' ->cpus_allowed would use the pointer. +- Code that 'modifies' ->cpus_allowed would use the direct mask. + +While converting the existing users I tried to stick with the rules +above however… well mostly CPUFREQ tries to temporary switch the CPU +mask to do something on a certain CPU and then switches the mask back it +its original value. So in theory `cpus_ptr' could or should be used. +However if this is invoked in a migration disabled region (which is not +the case because it would require something like preempt_disable() and +set_cpus_allowed_ptr() might sleep so it can't be) then the "restore" +part would restore the wrong mask. So it only looks strange and I go for +the pointer… + +Some drivers copy the cpumask without cpumask_copy() and others use +cpumask_copy but without alloc_cpumask_var(). I did not fix those as +part of this, could do this as a follow up… + +So is this the way we want it? +Is the usage of `cpus_ptr' vs `cpus_mask' for the set + restore part +(see cpufreq users) what we want? At some point it looks like they +should use a different interface for their doing. I am not sure why +switching to certain CPU is important but maybe it could be done via a +workqueue from the CPUFREQ core (so we have a comment desribing why are +doing this and a get_online_cpus() to ensure that the CPU does not go +offline too early). + +Cc: Peter Zijlstra +Cc: Thomas Gleixner +Cc: Mike Galbraith +Cc: Ingo Molnar +Cc: Rafael J. Wysocki +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/ia64/kernel/mca.c | 2 - + arch/mips/include/asm/switch_to.h | 4 +- + arch/mips/kernel/mips-mt-fpaff.c | 2 - + arch/mips/kernel/traps.c | 6 ++-- + arch/powerpc/platforms/cell/spufs/sched.c | 2 - + drivers/infiniband/hw/hfi1/affinity.c | 6 ++-- + drivers/infiniband/hw/hfi1/sdma.c | 3 -- + drivers/infiniband/hw/qib/qib_file_ops.c | 7 ++--- + fs/proc/array.c | 4 +- + include/linux/sched.h | 5 ++- + init/init_task.c | 3 +- + kernel/cgroup/cpuset.c | 2 - + kernel/fork.c | 2 + + kernel/sched/core.c | 40 ++++++++++++++--------------- + kernel/sched/cpudeadline.c | 4 +- + kernel/sched/cpupri.c | 4 +- + kernel/sched/deadline.c | 6 ++-- + kernel/sched/fair.c | 32 +++++++++++------------ + kernel/sched/rt.c | 4 +- + kernel/trace/trace_hwlat.c | 2 - + lib/smp_processor_id.c | 2 - + samples/trace_events/trace-events-sample.c | 2 - + 22 files changed, 73 insertions(+), 71 deletions(-) + +--- a/arch/ia64/kernel/mca.c ++++ b/arch/ia64/kernel/mca.c +@@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, un + ti->cpu = cpu; + p->stack = ti; + p->state = TASK_UNINTERRUPTIBLE; +- cpumask_set_cpu(cpu, &p->cpus_allowed); ++ cpumask_set_cpu(cpu, &p->cpus_mask); + INIT_LIST_HEAD(&p->tasks); + p->parent = p->real_parent = p->group_leader = p; + INIT_LIST_HEAD(&p->children); +--- a/arch/mips/include/asm/switch_to.h ++++ b/arch/mips/include/asm/switch_to.h +@@ -42,7 +42,7 @@ extern struct task_struct *ll_task; + * inline to try to keep the overhead down. If we have been forced to run on + * a "CPU" with an FPU because of a previous high level of FP computation, + * but did not actually use the FPU during the most recent time-slice (CU1 +- * isn't set), we undo the restriction on cpus_allowed. ++ * isn't set), we undo the restriction on cpus_mask. + * + * We're not calling set_cpus_allowed() here, because we have no need to + * force prompt migration - we're already switching the current CPU to a +@@ -57,7 +57,7 @@ do { \ + test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) && \ + (!(KSTK_STATUS(prev) & ST0_CU1))) { \ + clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND); \ +- prev->cpus_allowed = prev->thread.user_cpus_allowed; \ ++ prev->cpus_mask = prev->thread.user_cpus_allowed; \ + } \ + next->thread.emulated_fp = 0; \ + } while(0) +--- a/arch/mips/kernel/mips-mt-fpaff.c ++++ b/arch/mips/kernel/mips-mt-fpaff.c +@@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffi + if (retval) + goto out_unlock; + +- cpumask_or(&allowed, &p->thread.user_cpus_allowed, &p->cpus_allowed); ++ cpumask_or(&allowed, &p->thread.user_cpus_allowed, p->cpus_ptr); + cpumask_and(&mask, &allowed, cpu_active_mask); + + out_unlock: +--- a/arch/mips/kernel/traps.c ++++ b/arch/mips/kernel/traps.c +@@ -1176,12 +1176,12 @@ static void mt_ase_fp_affinity(void) + * restricted the allowed set to exclude any CPUs with FPUs, + * we'll skip the procedure. + */ +- if (cpumask_intersects(¤t->cpus_allowed, &mt_fpu_cpumask)) { ++ if (cpumask_intersects(¤t->cpus_mask, &mt_fpu_cpumask)) { + cpumask_t tmask; + + current->thread.user_cpus_allowed +- = current->cpus_allowed; +- cpumask_and(&tmask, ¤t->cpus_allowed, ++ = current->cpus_mask; ++ cpumask_and(&tmask, ¤t->cpus_mask, + &mt_fpu_cpumask); + set_cpus_allowed_ptr(current, &tmask); + set_thread_flag(TIF_FPUBOUND); +--- a/arch/powerpc/platforms/cell/spufs/sched.c ++++ b/arch/powerpc/platforms/cell/spufs/sched.c +@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_ + * runqueue. The context will be rescheduled on the proper node + * if it is timesliced or preempted. + */ +- cpumask_copy(&ctx->cpus_allowed, ¤t->cpus_allowed); ++ cpumask_copy(&ctx->cpus_allowed, current->cpus_ptr); + + /* Save the current cpu id for spu interrupt routing. */ + ctx->last_ran = raw_smp_processor_id(); +--- a/drivers/infiniband/hw/hfi1/affinity.c ++++ b/drivers/infiniband/hw/hfi1/affinity.c +@@ -1019,7 +1019,7 @@ int hfi1_get_proc_affinity(int node) + struct hfi1_affinity_node *entry; + cpumask_var_t diff, hw_thread_mask, available_mask, intrs_mask; + const struct cpumask *node_mask, +- *proc_mask = ¤t->cpus_allowed; ++ *proc_mask = current->cpus_ptr; + struct hfi1_affinity_node_list *affinity = &node_affinity; + struct cpu_mask_set *set = &affinity->proc; + +@@ -1027,7 +1027,7 @@ int hfi1_get_proc_affinity(int node) + * check whether process/context affinity has already + * been set + */ +- if (cpumask_weight(proc_mask) == 1) { ++ if (current->nr_cpus_allowed == 1) { + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); +@@ -1038,7 +1038,7 @@ int hfi1_get_proc_affinity(int node) + cpu = cpumask_first(proc_mask); + cpumask_set_cpu(cpu, &set->used); + goto done; +- } else if (cpumask_weight(proc_mask) < cpumask_weight(&set->mask)) { ++ } else if (current->nr_cpus_allowed < cpumask_weight(&set->mask)) { + hfi1_cdbg(PROC, "PID %u %s affinity set to CPU set(s) %*pbl", + current->pid, current->comm, + cpumask_pr_args(proc_mask)); +--- a/drivers/infiniband/hw/hfi1/sdma.c ++++ b/drivers/infiniband/hw/hfi1/sdma.c +@@ -855,14 +855,13 @@ struct sdma_engine *sdma_select_user_eng + { + struct sdma_rht_node *rht_node; + struct sdma_engine *sde = NULL; +- const struct cpumask *current_mask = ¤t->cpus_allowed; + unsigned long cpu_id; + + /* + * To ensure that always the same sdma engine(s) will be + * selected make sure the process is pinned to this CPU only. + */ +- if (cpumask_weight(current_mask) != 1) ++ if (current->nr_cpus_allowed != 1) + goto out; + + cpu_id = smp_processor_id(); +--- a/drivers/infiniband/hw/qib/qib_file_ops.c ++++ b/drivers/infiniband/hw/qib/qib_file_ops.c +@@ -1142,7 +1142,7 @@ static __poll_t qib_poll(struct file *fp + static void assign_ctxt_affinity(struct file *fp, struct qib_devdata *dd) + { + struct qib_filedata *fd = fp->private_data; +- const unsigned int weight = cpumask_weight(¤t->cpus_allowed); ++ const unsigned int weight = current->nr_cpus_allowed; + const struct cpumask *local_mask = cpumask_of_pcibus(dd->pcidev->bus); + int local_cpu; + +@@ -1623,9 +1623,8 @@ static int qib_assign_ctxt(struct file * + ret = find_free_ctxt(i_minor - 1, fp, uinfo); + else { + int unit; +- const unsigned int cpu = cpumask_first(¤t->cpus_allowed); +- const unsigned int weight = +- cpumask_weight(¤t->cpus_allowed); ++ const unsigned int cpu = cpumask_first(current->cpus_ptr); ++ const unsigned int weight = current->nr_cpus_allowed; + + if (weight == 1 && !test_bit(cpu, qib_cpulist)) + if (!find_hca(cpu, &unit) && unit >= 0) +--- a/fs/proc/array.c ++++ b/fs/proc/array.c +@@ -381,9 +381,9 @@ static inline void task_context_switch_c + static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) + { + seq_printf(m, "Cpus_allowed:\t%*pb\n", +- cpumask_pr_args(&task->cpus_allowed)); ++ cpumask_pr_args(task->cpus_ptr)); + seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", +- cpumask_pr_args(&task->cpus_allowed)); ++ cpumask_pr_args(task->cpus_ptr)); + } + + static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -660,7 +660,8 @@ struct task_struct { + + unsigned int policy; + int nr_cpus_allowed; +- cpumask_t cpus_allowed; ++ const cpumask_t *cpus_ptr; ++ cpumask_t cpus_mask; + + #ifdef CONFIG_PREEMPT_RCU + int rcu_read_lock_nesting; +@@ -1397,7 +1398,7 @@ extern struct pid *cad_pid; + #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ + #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ + #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +-#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ ++#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ + #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ + #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ + #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ +--- a/init/init_task.c ++++ b/init/init_task.c +@@ -64,7 +64,8 @@ struct task_struct init_task + .static_prio = MAX_PRIO - 20, + .normal_prio = MAX_PRIO - 20, + .policy = SCHED_NORMAL, +- .cpus_allowed = CPU_MASK_ALL, ++ .cpus_ptr = &init_task.cpus_mask, ++ .cpus_mask = CPU_MASK_ALL, + .nr_cpus_allowed= NR_CPUS, + .mm = NULL, + .active_mm = &init_mm, +--- a/kernel/cgroup/cpuset.c ++++ b/kernel/cgroup/cpuset.c +@@ -2090,7 +2090,7 @@ static void cpuset_fork(struct task_stru + if (task_css_is_root(task, cpuset_cgrp_id)) + return; + +- set_cpus_allowed_ptr(task, ¤t->cpus_allowed); ++ set_cpus_allowed_ptr(task, current->cpus_ptr); + task->mems_allowed = current->mems_allowed; + } + +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -845,6 +845,8 @@ static struct task_struct *dup_task_stru + #ifdef CONFIG_STACKPROTECTOR + tsk->stack_canary = get_random_canary(); + #endif ++ if (orig->cpus_ptr == &orig->cpus_mask) ++ tsk->cpus_ptr = &tsk->cpus_mask; + + /* + * One for us, one for whoever does the "release_task()" (usually +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -900,7 +900,7 @@ static inline bool is_per_cpu_kthread(st + */ + static inline bool is_cpu_allowed(struct task_struct *p, int cpu) + { +- if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + return false; + + if (is_per_cpu_kthread(p)) +@@ -995,7 +995,7 @@ static int migration_cpu_stop(void *data + local_irq_disable(); + /* + * We need to explicitly wake pending tasks before running +- * __migrate_task() such that we will not miss enforcing cpus_allowed ++ * __migrate_task() such that we will not miss enforcing cpus_ptr + * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test. + */ + sched_ttwu_pending(); +@@ -1026,7 +1026,7 @@ static int migration_cpu_stop(void *data + */ + void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) + { +- cpumask_copy(&p->cpus_allowed, new_mask); ++ cpumask_copy(&p->cpus_mask, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +@@ -1096,7 +1096,7 @@ static int __set_cpus_allowed_ptr(struct + goto out; + } + +- if (cpumask_equal(&p->cpus_allowed, new_mask)) ++ if (cpumask_equal(p->cpus_ptr, new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_valid_mask)) { +@@ -1258,10 +1258,10 @@ static int migrate_swap_stop(void *data) + if (task_cpu(arg->src_task) != arg->src_cpu) + goto unlock; + +- if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr)) + goto unlock; + +- if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr)) + goto unlock; + + __migrate_swap_task(arg->src_task, arg->dst_cpu); +@@ -1302,10 +1302,10 @@ int migrate_swap(struct task_struct *cur + if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) + goto out; + +- if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr)) + goto out; + +- if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) ++ if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr)) + goto out; + + trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); +@@ -1449,7 +1449,7 @@ void kick_process(struct task_struct *p) + EXPORT_SYMBOL_GPL(kick_process); + + /* +- * ->cpus_allowed is protected by both rq->lock and p->pi_lock ++ * ->cpus_ptr is protected by both rq->lock and p->pi_lock + * + * A few notes on cpu_active vs cpu_online: + * +@@ -1489,14 +1489,14 @@ static int select_fallback_rq(int cpu, s + for_each_cpu(dest_cpu, nodemask) { + if (!cpu_active(dest_cpu)) + continue; +- if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) ++ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) + return dest_cpu; + } + } + + for (;;) { + /* Any allowed, online CPU? */ +- for_each_cpu(dest_cpu, &p->cpus_allowed) { ++ for_each_cpu(dest_cpu, p->cpus_ptr) { + if (!is_cpu_allowed(p, dest_cpu)) + continue; + +@@ -1540,7 +1540,7 @@ static int select_fallback_rq(int cpu, s + } + + /* +- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable. ++ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable. + */ + static inline + int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) +@@ -1550,11 +1550,11 @@ int select_task_rq(struct task_struct *p + if (p->nr_cpus_allowed > 1) + cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); + else +- cpu = cpumask_any(&p->cpus_allowed); ++ cpu = cpumask_any(p->cpus_ptr); + + /* + * In order not to call set_task_cpu() on a blocking task we need +- * to rely on ttwu() to place the task on a valid ->cpus_allowed ++ * to rely on ttwu() to place the task on a valid ->cpus_ptr + * CPU. + * + * Since this is common to all placement strategies, this lives here. +@@ -2426,7 +2426,7 @@ void wake_up_new_task(struct task_struct + #ifdef CONFIG_SMP + /* + * Fork balancing, do it here and not earlier because: +- * - cpus_allowed can change in the fork path ++ * - cpus_ptr can change in the fork path + * - any previously selected CPU might disappear through hotplug + * + * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, +@@ -4297,7 +4297,7 @@ static int __sched_setscheduler(struct t + * the entire root_domain to become SCHED_DEADLINE. We + * will also fail if there's no bandwidth available. + */ +- if (!cpumask_subset(span, &p->cpus_allowed) || ++ if (!cpumask_subset(span, p->cpus_ptr) || + rq->rd->dl_bw.bw == 0) { + task_rq_unlock(rq, p, &rf); + return -EPERM; +@@ -4896,7 +4896,7 @@ long sched_getaffinity(pid_t pid, struct + goto out_unlock; + + raw_spin_lock_irqsave(&p->pi_lock, flags); +- cpumask_and(mask, &p->cpus_allowed, cpu_active_mask); ++ cpumask_and(mask, &p->cpus_mask, cpu_active_mask); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + out_unlock: +@@ -5476,7 +5476,7 @@ int task_can_attach(struct task_struct * + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks +- * before cpus_allowed may be changed. ++ * before cpus_mask may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) { + ret = -EINVAL; +@@ -5503,7 +5503,7 @@ int migrate_task_to(struct task_struct * + if (curr_cpu == target_cpu) + return 0; + +- if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(target_cpu, p->cpus_ptr)) + return -EINVAL; + + /* TODO: This is not properly updating schedstats */ +@@ -5641,7 +5641,7 @@ static void migrate_tasks(struct rq *dea + put_prev_task(rq, next); + + /* +- * Rules for changing task_struct::cpus_allowed are holding ++ * Rules for changing task_struct::cpus_mask are holding + * both pi_lock and rq->lock, such that holding either + * stabilizes the mask. + * +--- a/kernel/sched/cpudeadline.c ++++ b/kernel/sched/cpudeadline.c +@@ -124,14 +124,14 @@ int cpudl_find(struct cpudl *cp, struct + const struct sched_dl_entity *dl_se = &p->dl; + + if (later_mask && +- cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { ++ cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { + return 1; + } else { + int best_cpu = cpudl_maximum(cp); + + WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); + +- if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) && ++ if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && + dl_time_before(dl_se->deadline, cp->elements[0].dl)) { + if (later_mask) + cpumask_set_cpu(best_cpu, later_mask); +--- a/kernel/sched/cpupri.c ++++ b/kernel/sched/cpupri.c +@@ -98,11 +98,11 @@ int cpupri_find(struct cpupri *cp, struc + if (skip) + continue; + +- if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) ++ if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) + continue; + + if (lowest_mask) { +- cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); ++ cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); + + /* + * We have to ensure that we have at least one bit +--- a/kernel/sched/deadline.c ++++ b/kernel/sched/deadline.c +@@ -538,7 +538,7 @@ static struct rq *dl_task_offline_migrat + * If we cannot preempt any rq, fall back to pick any + * online CPU: + */ +- cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); ++ cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr); + if (cpu >= nr_cpu_ids) { + /* + * Failed to find any suitable CPU. +@@ -1820,7 +1820,7 @@ static void set_curr_task_dl(struct rq * + static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) + { + if (!task_running(rq, p) && +- cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ cpumask_test_cpu(cpu, p->cpus_ptr)) + return 1; + return 0; + } +@@ -1970,7 +1970,7 @@ static struct rq *find_lock_later_rq(str + /* Retry if something changed. */ + if (double_lock_balance(rq, later_rq)) { + if (unlikely(task_rq(task) != rq || +- !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || ++ !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || + task_running(rq, task) || + !dl_task(task) || + !task_on_rq_queued(task))) { +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -1614,7 +1614,7 @@ static void task_numa_compare(struct tas + */ + if (cur) { + /* Skip this swap candidate if cannot move to the source CPU: */ +- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) ++ if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr)) + goto unlock; + + /* +@@ -1724,7 +1724,7 @@ static void task_numa_find_cpu(struct ta + + for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { + /* Skip this CPU if the source task cannot migrate */ +- if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, env->p->cpus_ptr)) + continue; + + env->dst_cpu = cpu; +@@ -6016,7 +6016,7 @@ find_idlest_group(struct sched_domain *s + + /* Skip over this group if it has no CPUs allowed */ + if (!cpumask_intersects(sched_group_span(group), +- &p->cpus_allowed)) ++ p->cpus_ptr)) + continue; + + local_group = cpumask_test_cpu(this_cpu, +@@ -6148,7 +6148,7 @@ find_idlest_group_cpu(struct sched_group + return cpumask_first(sched_group_span(group)); + + /* Traverse only the allowed CPUs */ +- for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) { ++ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) { + if (available_idle_cpu(i)) { + struct rq *rq = cpu_rq(i); + struct cpuidle_state *idle = idle_get_state(rq); +@@ -6188,7 +6188,7 @@ static inline int find_idlest_cpu(struct + { + int new_cpu = cpu; + +- if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed)) ++ if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr)) + return prev_cpu; + + /* +@@ -6303,7 +6303,7 @@ static int select_idle_core(struct task_ + if (!test_idle_cores(target, false)) + return -1; + +- cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); ++ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr); + + for_each_cpu_wrap(core, cpus, target) { + bool idle = true; +@@ -6337,7 +6337,7 @@ static int select_idle_smt(struct task_s + return -1; + + for_each_cpu(cpu, cpu_smt_mask(target)) { +- if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + continue; + if (available_idle_cpu(cpu)) + return cpu; +@@ -6400,7 +6400,7 @@ static int select_idle_cpu(struct task_s + for_each_cpu_wrap(cpu, sched_domain_span(sd), target) { + if (!--nr) + return -1; +- if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + continue; + if (available_idle_cpu(cpu)) + break; +@@ -6437,7 +6437,7 @@ static int select_idle_sibling(struct ta + recent_used_cpu != target && + cpus_share_cache(recent_used_cpu, target) && + available_idle_cpu(recent_used_cpu) && +- cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) { ++ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) { + /* + * Replace recent_used_cpu with prev as it is a potential + * candidate for the next wake: +@@ -6621,7 +6621,7 @@ select_task_rq_fair(struct task_struct * + if (sd_flag & SD_BALANCE_WAKE) { + record_wakee(p); + want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) +- && cpumask_test_cpu(cpu, &p->cpus_allowed); ++ && cpumask_test_cpu(cpu, p->cpus_ptr); + } + + rcu_read_lock(); +@@ -7357,14 +7357,14 @@ int can_migrate_task(struct task_struct + /* + * We do not migrate tasks that are: + * 1) throttled_lb_pair, or +- * 2) cannot be migrated to this CPU due to cpus_allowed, or ++ * 2) cannot be migrated to this CPU due to cpus_ptr, or + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. + */ + if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + return 0; + +- if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { ++ if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) { + int cpu; + + schedstat_inc(p->se.statistics.nr_failed_migrations_affine); +@@ -7384,7 +7384,7 @@ int can_migrate_task(struct task_struct + + /* Prevent to re-select dst_cpu via env's CPUs: */ + for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { +- if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { ++ if (cpumask_test_cpu(cpu, p->cpus_ptr)) { + env->flags |= LBF_DST_PINNED; + env->new_dst_cpu = cpu; + break; +@@ -7981,7 +7981,7 @@ check_cpu_capacity(struct rq *rq, struct + + /* + * Group imbalance indicates (and tries to solve) the problem where balancing +- * groups is inadequate due to ->cpus_allowed constraints. ++ * groups is inadequate due to ->cpus_ptr constraints. + * + * Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a + * cpumask covering 1 CPU of the first group and 3 CPUs of the second group. +@@ -8596,7 +8596,7 @@ static struct sched_group *find_busiest_ + /* + * If the busiest group is imbalanced the below checks don't + * work because they assume all things are equal, which typically +- * isn't true due to cpus_allowed constraints and the like. ++ * isn't true due to cpus_ptr constraints and the like. + */ + if (busiest->group_type == group_imbalanced) + goto force_balance; +@@ -8992,7 +8992,7 @@ static int load_balance(int this_cpu, st + * if the curr task on busiest CPU can't be + * moved to this_cpu: + */ +- if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { ++ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) { + raw_spin_unlock_irqrestore(&busiest->lock, + flags); + env.flags |= LBF_ALL_PINNED; +--- a/kernel/sched/rt.c ++++ b/kernel/sched/rt.c +@@ -1601,7 +1601,7 @@ static void put_prev_task_rt(struct rq * + static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) + { + if (!task_running(rq, p) && +- cpumask_test_cpu(cpu, &p->cpus_allowed)) ++ cpumask_test_cpu(cpu, p->cpus_ptr)) + return 1; + + return 0; +@@ -1738,7 +1738,7 @@ static struct rq *find_lock_lowest_rq(st + * Also make sure that it wasn't scheduled on its rq. + */ + if (unlikely(task_rq(task) != rq || +- !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || ++ !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || + task_running(rq, task) || + !rt_task(task) || + !task_on_rq_queued(task))) { +--- a/kernel/trace/trace_hwlat.c ++++ b/kernel/trace/trace_hwlat.c +@@ -279,7 +279,7 @@ static void move_to_next_cpu(void) + * of this thread, than stop migrating for the duration + * of the current test. + */ +- if (!cpumask_equal(current_mask, ¤t->cpus_allowed)) ++ if (!cpumask_equal(current_mask, current->cpus_ptr)) + goto disable; + + get_online_cpus(); +--- a/lib/smp_processor_id.c ++++ b/lib/smp_processor_id.c +@@ -22,7 +22,7 @@ notrace static unsigned int check_preemp + * Kernel threads bound to a single CPU can safely use + * smp_processor_id(): + */ +- if (cpumask_equal(¤t->cpus_allowed, cpumask_of(this_cpu))) ++ if (cpumask_equal(current->cpus_ptr, cpumask_of(this_cpu))) + goto out; + + /* +--- a/samples/trace_events/trace-events-sample.c ++++ b/samples/trace_events/trace-events-sample.c +@@ -33,7 +33,7 @@ static void simple_thread_func(int cnt) + + /* Silly tracepoints */ + trace_foo_bar("hello", cnt, array, random_strings[len], +- ¤t->cpus_allowed); ++ current->cpus_ptr); + + trace_foo_with_template_simple("HELLO", cnt); + diff --git a/debian/patches/features/all/rt/kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch b/debian/patches/features/all/rt/kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch new file mode 100644 index 000000000..6c881c7f3 --- /dev/null +++ b/debian/patches/features/all/rt/kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch @@ -0,0 +1,62 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 21 Nov 2016 19:31:08 +0100 +Subject: [PATCH] kernel/sched: move stack + kprobe clean up to + __put_task_struct() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There is no need to free the stack before the task struct (except for reasons +mentioned in commit 68f24b08ee89 ("sched/core: Free the stack early if +CONFIG_THREAD_INFO_IN_TASK")). This also comes handy on -RT because we can't +free memory in preempt disabled region. + +Cc: stable-rt@vger.kernel.org #for kprobe_flush_task() +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/fork.c | 10 ++++++++++ + kernel/sched/core.c | 9 --------- + 2 files changed, 10 insertions(+), 9 deletions(-) + +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -40,6 +40,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -693,6 +694,15 @@ void __put_task_struct(struct task_struc + WARN_ON(atomic_read(&tsk->usage)); + WARN_ON(tsk == current); + ++ /* ++ * Remove function-return probe instances associated with this ++ * task and put them back on the free list. ++ */ ++ kprobe_flush_task(tsk); ++ ++ /* Task is done with its stack. */ ++ put_task_stack(tsk); ++ + cgroup_free(tsk); + task_numa_free(tsk); + security_task_free(tsk); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2764,15 +2764,6 @@ static struct rq *finish_task_switch(str + if (prev->sched_class->task_dead) + prev->sched_class->task_dead(prev); + +- /* +- * Remove function-return probe instances associated with this +- * task and put them back on the free list. +- */ +- kprobe_flush_task(prev); +- +- /* Task is done with its stack. */ +- put_task_stack(prev); +- + put_task_struct(prev); + } + diff --git a/debian/patches/features/all/rt/kgb-serial-hackaround.patch b/debian/patches/features/all/rt/kgb-serial-hackaround.patch new file mode 100644 index 000000000..a4ecf2ad0 --- /dev/null +++ b/debian/patches/features/all/rt/kgb-serial-hackaround.patch @@ -0,0 +1,77 @@ +From: Jason Wessel +Date: Thu, 28 Jul 2011 12:42:23 -0500 +Subject: kgdb/serial: Short term workaround +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On 07/27/2011 04:37 PM, Thomas Gleixner wrote: +> - KGDB (not yet disabled) is reportedly unusable on -rt right now due +> to missing hacks in the console locking which I dropped on purpose. +> + +To work around this in the short term you can use this patch, in +addition to the clocksource watchdog patch that Thomas brewed up. + +Comments are welcome of course. Ultimately the right solution is to +change separation between the console and the HW to have a polled mode ++ work queue so as not to introduce any kind of latency. + +Thanks, +Jason. + +--- + drivers/tty/serial/8250/8250_port.c | 3 +++ + include/linux/kdb.h | 2 ++ + kernel/debug/kdb/kdb_io.c | 2 ++ + 3 files changed, 7 insertions(+) + +--- a/drivers/tty/serial/8250/8250_port.c ++++ b/drivers/tty/serial/8250/8250_port.c +@@ -31,6 +31,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -3224,6 +3225,8 @@ void serial8250_console_write(struct uar + + if (port->sysrq || oops_in_progress) + locked = 0; ++ else if (in_kdb_printk()) ++ locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); + +--- a/include/linux/kdb.h ++++ b/include/linux/kdb.h +@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(en + extern __printf(1, 2) int kdb_printf(const char *, ...); + typedef __printf(1, 2) int (*kdb_printf_t)(const char *, ...); + ++#define in_kdb_printk() (kdb_trap_printk) + extern void kdb_init(int level); + + /* Access to kdb specific polling devices */ +@@ -201,6 +202,7 @@ extern int kdb_register_flags(char *, kd + extern int kdb_unregister(char *); + #else /* ! CONFIG_KGDB_KDB */ + static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; } ++#define in_kdb_printk() (0) + static inline void kdb_init(int level) {} + static inline int kdb_register(char *cmd, kdb_func_t func, char *usage, + char *help, short minlen) { return 0; } +--- a/kernel/debug/kdb/kdb_io.c ++++ b/kernel/debug/kdb/kdb_io.c +@@ -854,9 +854,11 @@ int kdb_printf(const char *fmt, ...) + va_list ap; + int r; + ++ kdb_trap_printk++; + va_start(ap, fmt); + r = vkdb_printf(KDB_MSGSRC_INTERNAL, fmt, ap); + va_end(ap); ++ kdb_trap_printk--; + + return r; + } diff --git a/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch b/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch new file mode 100644 index 000000000..05201c753 --- /dev/null +++ b/debian/patches/features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch @@ -0,0 +1,36 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 23 Jan 2014 14:45:59 +0100 +Subject: leds: trigger: disable CPU trigger on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +as it triggers: +|CPU: 0 PID: 0 Comm: swapper Not tainted 3.12.8-rt10 #141 +|[] (unwind_backtrace+0x0/0xf8) from [] (show_stack+0x1c/0x20) +|[] (show_stack+0x1c/0x20) from [] (dump_stack+0x20/0x2c) +|[] (dump_stack+0x20/0x2c) from [] (__might_sleep+0x13c/0x170) +|[] (__might_sleep+0x13c/0x170) from [] (__rt_spin_lock+0x28/0x38) +|[] (__rt_spin_lock+0x28/0x38) from [] (rt_read_lock+0x68/0x7c) +|[] (rt_read_lock+0x68/0x7c) from [] (led_trigger_event+0x2c/0x5c) +|[] (led_trigger_event+0x2c/0x5c) from [] (ledtrig_cpu+0x54/0x5c) +|[] (ledtrig_cpu+0x54/0x5c) from [] (arch_cpu_idle_exit+0x18/0x1c) +|[] (arch_cpu_idle_exit+0x18/0x1c) from [] (cpu_startup_entry+0xa8/0x234) +|[] (cpu_startup_entry+0xa8/0x234) from [] (rest_init+0xb8/0xe0) +|[] (rest_init+0xb8/0xe0) from [] (start_kernel+0x2c4/0x380) + + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/leds/trigger/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/drivers/leds/trigger/Kconfig ++++ b/drivers/leds/trigger/Kconfig +@@ -69,7 +69,7 @@ config LEDS_TRIGGER_BACKLIGHT + + config LEDS_TRIGGER_CPU + bool "LED CPU Trigger" +- depends on LEDS_TRIGGERS ++ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE + help + This allows LEDs to be controlled by active CPUs. This shows + the active CPUs across an array of LEDs so you can see which diff --git a/debian/patches/features/all/rt/libata-remove-ata_sff_data_xfer_noirq.patch b/debian/patches/features/all/rt/libata-remove-ata_sff_data_xfer_noirq.patch new file mode 100644 index 000000000..b840a4b5a --- /dev/null +++ b/debian/patches/features/all/rt/libata-remove-ata_sff_data_xfer_noirq.patch @@ -0,0 +1,197 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 19 Apr 2018 12:55:14 +0200 +Subject: [PATCH] libata: remove ata_sff_data_xfer_noirq() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +ata_sff_data_xfer_noirq() is invoked via the ->sff_data_xfer hook. The +latter is invoked by ata_pio_sector(), atapi_send_cdb() and +__atapi_pio_bytes() which in turn is invoked by ata_sff_hsm_move(). +The latter function requires that the "ap->lock" lock is held which +needs to be taken with disabled interrupts. + +There is no need have to have ata_sff_data_xfer_noirq() which invokes +ata_sff_data_xfer32() with disabled interrupts because at this point the +interrupts are already disabled. +Remove the function and its references to it and replace all callers +with ata_sff_data_xfer32(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + Documentation/driver-api/libata.rst | 3 +-- + drivers/ata/libata-sff.c | 30 ------------------------------ + drivers/ata/pata_cmd640.c | 2 +- + drivers/ata/pata_icside.c | 2 +- + drivers/ata/pata_imx.c | 2 +- + drivers/ata/pata_legacy.c | 6 +++--- + drivers/ata/pata_palmld.c | 2 +- + drivers/ata/pata_pcmcia.c | 2 +- + drivers/ata/pata_platform.c | 2 +- + drivers/ata/pata_via.c | 2 +- + include/linux/libata.h | 2 -- + 11 files changed, 11 insertions(+), 44 deletions(-) + +--- a/Documentation/driver-api/libata.rst ++++ b/Documentation/driver-api/libata.rst +@@ -118,8 +118,7 @@ PIO data read/write + All bmdma-style drivers must implement this hook. This is the low-level + operation that actually copies the data bytes during a PIO data + transfer. Typically the driver will choose one of +-:c:func:`ata_sff_data_xfer_noirq`, :c:func:`ata_sff_data_xfer`, or +-:c:func:`ata_sff_data_xfer32`. ++:c:func:`ata_sff_data_xfer`, or :c:func:`ata_sff_data_xfer32`. + + ATA command execute + ~~~~~~~~~~~~~~~~~~~ +--- a/drivers/ata/libata-sff.c ++++ b/drivers/ata/libata-sff.c +@@ -658,36 +658,6 @@ unsigned int ata_sff_data_xfer32(struct + EXPORT_SYMBOL_GPL(ata_sff_data_xfer32); + + /** +- * ata_sff_data_xfer_noirq - Transfer data by PIO +- * @qc: queued command +- * @buf: data buffer +- * @buflen: buffer length +- * @rw: read/write +- * +- * Transfer data from/to the device data register by PIO. Do the +- * transfer with interrupts disabled. +- * +- * LOCKING: +- * Inherited from caller. +- * +- * RETURNS: +- * Bytes consumed. +- */ +-unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, unsigned char *buf, +- unsigned int buflen, int rw) +-{ +- unsigned long flags; +- unsigned int consumed; +- +- local_irq_save(flags); +- consumed = ata_sff_data_xfer32(qc, buf, buflen, rw); +- local_irq_restore(flags); +- +- return consumed; +-} +-EXPORT_SYMBOL_GPL(ata_sff_data_xfer_noirq); +- +-/** + * ata_pio_sector - Transfer a sector of data. + * @qc: Command on going + * +--- a/drivers/ata/pata_cmd640.c ++++ b/drivers/ata/pata_cmd640.c +@@ -178,7 +178,7 @@ static struct scsi_host_template cmd640_ + static struct ata_port_operations cmd640_port_ops = { + .inherits = &ata_sff_port_ops, + /* In theory xfer_noirq is not needed once we kill the prefetcher */ +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .sff_irq_check = cmd640_sff_irq_check, + .qc_issue = cmd640_qc_issue, + .cable_detect = ata_cable_40wire, +--- a/drivers/ata/pata_icside.c ++++ b/drivers/ata/pata_icside.c +@@ -324,7 +324,7 @@ static struct ata_port_operations pata_i + .inherits = &ata_bmdma_port_ops, + /* no need to build any PRD tables for DMA */ + .qc_prep = ata_noop_qc_prep, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .bmdma_setup = pata_icside_bmdma_setup, + .bmdma_start = pata_icside_bmdma_start, + .bmdma_stop = pata_icside_bmdma_stop, +--- a/drivers/ata/pata_imx.c ++++ b/drivers/ata/pata_imx.c +@@ -102,7 +102,7 @@ static struct scsi_host_template pata_im + + static struct ata_port_operations pata_imx_port_ops = { + .inherits = &ata_sff_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .cable_detect = ata_cable_unknown, + .set_piomode = pata_imx_set_piomode, + }; +--- a/drivers/ata/pata_legacy.c ++++ b/drivers/ata/pata_legacy.c +@@ -246,12 +246,12 @@ static const struct ata_port_operations + + static struct ata_port_operations simple_port_ops = { + .inherits = &legacy_base_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + }; + + static struct ata_port_operations legacy_port_ops = { + .inherits = &legacy_base_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .set_mode = legacy_set_mode, + }; + +@@ -341,7 +341,7 @@ static unsigned int pdc_data_xfer_vlb(st + } + local_irq_restore(flags); + } else +- buflen = ata_sff_data_xfer_noirq(qc, buf, buflen, rw); ++ buflen = ata_sff_data_xfer32(qc, buf, buflen, rw); + + return buflen; + } +--- a/drivers/ata/pata_palmld.c ++++ b/drivers/ata/pata_palmld.c +@@ -44,7 +44,7 @@ static struct scsi_host_template palmld_ + + static struct ata_port_operations palmld_port_ops = { + .inherits = &ata_sff_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .cable_detect = ata_cable_40wire, + }; + +--- a/drivers/ata/pata_pcmcia.c ++++ b/drivers/ata/pata_pcmcia.c +@@ -151,7 +151,7 @@ static struct scsi_host_template pcmcia_ + + static struct ata_port_operations pcmcia_port_ops = { + .inherits = &ata_sff_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .cable_detect = ata_cable_40wire, + .set_mode = pcmcia_set_mode, + }; +--- a/drivers/ata/pata_platform.c ++++ b/drivers/ata/pata_platform.c +@@ -49,7 +49,7 @@ static struct scsi_host_template pata_pl + + static struct ata_port_operations pata_platform_port_ops = { + .inherits = &ata_sff_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + .cable_detect = ata_cable_unknown, + .set_mode = pata_platform_set_mode, + }; +--- a/drivers/ata/pata_via.c ++++ b/drivers/ata/pata_via.c +@@ -471,7 +471,7 @@ static struct ata_port_operations via_po + + static struct ata_port_operations via_port_ops_noirq = { + .inherits = &via_port_ops, +- .sff_data_xfer = ata_sff_data_xfer_noirq, ++ .sff_data_xfer = ata_sff_data_xfer32, + }; + + /** +--- a/include/linux/libata.h ++++ b/include/linux/libata.h +@@ -1856,8 +1856,6 @@ extern unsigned int ata_sff_data_xfer(st + unsigned char *buf, unsigned int buflen, int rw); + extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc, + unsigned char *buf, unsigned int buflen, int rw); +-extern unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, +- unsigned char *buf, unsigned int buflen, int rw); + extern void ata_sff_irq_on(struct ata_port *ap); + extern void ata_sff_irq_clear(struct ata_port *ap); + extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc, diff --git a/debian/patches/features/all/rt/list_bl-fixup-bogus-lockdep-warning.patch b/debian/patches/features/all/rt/list_bl-fixup-bogus-lockdep-warning.patch new file mode 100644 index 000000000..cd5523c23 --- /dev/null +++ b/debian/patches/features/all/rt/list_bl-fixup-bogus-lockdep-warning.patch @@ -0,0 +1,98 @@ +From: Josh Cartwright +Date: Thu, 31 Mar 2016 00:04:25 -0500 +Subject: [PATCH] list_bl: fixup bogus lockdep warning +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +At first glance, the use of 'static inline' seems appropriate for +INIT_HLIST_BL_HEAD(). + +However, when a 'static inline' function invocation is inlined by gcc, +all callers share any static local data declared within that inline +function. + +This presents a problem for how lockdep classes are setup. raw_spinlocks, for +example, when CONFIG_DEBUG_SPINLOCK, + + # define raw_spin_lock_init(lock) \ + do { \ + static struct lock_class_key __key; \ + \ + __raw_spin_lock_init((lock), #lock, &__key); \ + } while (0) + +When this macro is expanded into a 'static inline' caller, like +INIT_HLIST_BL_HEAD(): + + static inline INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) + { + h->first = NULL; + raw_spin_lock_init(&h->lock); + } + +...the static local lock_class_key object is made a function static. + +For compilation units which initialize invoke INIT_HLIST_BL_HEAD() more +than once, then, all of the invocations share this same static local +object. + +This can lead to some very confusing lockdep splats (example below). +Solve this problem by forcing the INIT_HLIST_BL_HEAD() to be a macro, +which prevents the lockdep class object sharing. + + ============================================= + [ INFO: possible recursive locking detected ] + 4.4.4-rt11 #4 Not tainted + --------------------------------------------- + kswapd0/59 is trying to acquire lock: + (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + + but task is already holding lock: + (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + + other info that might help us debug this: + Possible unsafe locking scenario: + + CPU0 + ---- + lock(&h->lock#2); + lock(&h->lock#2); + + *** DEADLOCK *** + + May be due to missing lock nesting notation + + 2 locks held by kswapd0/59: + #0: (shrinker_rwsem){+.+...}, at: rt_down_read_trylock + #1: (&h->lock#2){+.+.-.}, at: mb_cache_shrink_scan + +Reported-by: Luis Claudio R. Goncalves +Tested-by: Luis Claudio R. Goncalves +Signed-off-by: Josh Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/list_bl.h | 12 +++++++----- + 1 file changed, 7 insertions(+), 5 deletions(-) + +--- a/include/linux/list_bl.h ++++ b/include/linux/list_bl.h +@@ -43,13 +43,15 @@ struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; + +-static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) +-{ +- h->first = NULL; + #ifdef CONFIG_PREEMPT_RT_BASE +- raw_spin_lock_init(&h->lock); ++#define INIT_HLIST_BL_HEAD(h) \ ++do { \ ++ (h)->first = NULL; \ ++ raw_spin_lock_init(&(h)->lock); \ ++} while (0) ++#else ++#define INIT_HLIST_BL_HEAD(h) (h)->first = NULL + #endif +-} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { diff --git a/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch b/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch new file mode 100644 index 000000000..cc0b29da0 --- /dev/null +++ b/debian/patches/features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch @@ -0,0 +1,115 @@ +From: Paul Gortmaker +Date: Fri, 21 Jun 2013 15:07:25 -0400 +Subject: list_bl: Make list head locking RT safe +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +As per changes in include/linux/jbd_common.h for avoiding the +bit_spin_locks on RT ("fs: jbd/jbd2: Make state lock and journal +head lock rt safe") we do the same thing here. + +We use the non atomic __set_bit and __clear_bit inside the scope of +the lock to preserve the ability of the existing LIST_DEBUG code to +use the zero'th bit in the sanity checks. + +As a bit spinlock, we had no lockdep visibility into the usage +of the list head locking. Now, if we were to implement it as a +standard non-raw spinlock, we would see: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:658 +in_atomic(): 1, irqs_disabled(): 0, pid: 122, name: udevd +5 locks held by udevd/122: + #0: (&sb->s_type->i_mutex_key#7/1){+.+.+.}, at: [] lock_rename+0xe8/0xf0 + #1: (rename_lock){+.+...}, at: [] d_move+0x2c/0x60 + #2: (&dentry->d_lock){+.+...}, at: [] dentry_lock_for_move+0xf3/0x130 + #3: (&dentry->d_lock/2){+.+...}, at: [] dentry_lock_for_move+0xc4/0x130 + #4: (&dentry->d_lock/3){+.+...}, at: [] dentry_lock_for_move+0xd7/0x130 +Pid: 122, comm: udevd Not tainted 3.4.47-rt62 #7 +Call Trace: + [] __might_sleep+0x134/0x1f0 + [] rt_spin_lock+0x24/0x60 + [] __d_shrink+0x5c/0xa0 + [] __d_drop+0x1d/0x40 + [] __d_move+0x8e/0x320 + [] d_move+0x3e/0x60 + [] vfs_rename+0x198/0x4c0 + [] sys_renameat+0x213/0x240 + [] ? _raw_spin_unlock+0x35/0x60 + [] ? do_page_fault+0x1ec/0x4b0 + [] ? retint_swapgs+0xe/0x13 + [] ? trace_hardirqs_on_thunk+0x3a/0x3f + [] sys_rename+0x1b/0x20 + [] system_call_fastpath+0x1a/0x1f + +Since we are only taking the lock during short lived list operations, +lets assume for now that it being raw won't be a significant latency +concern. + + +Signed-off-by: Paul Gortmaker +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/list_bl.h | 28 ++++++++++++++++++++++++++-- + 1 file changed, 26 insertions(+), 2 deletions(-) + +--- a/include/linux/list_bl.h ++++ b/include/linux/list_bl.h +@@ -3,6 +3,7 @@ + #define _LINUX_LIST_BL_H + + #include ++#include + #include + + /* +@@ -33,13 +34,22 @@ + + struct hlist_bl_head { + struct hlist_bl_node *first; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spinlock_t lock; ++#endif + }; + + struct hlist_bl_node { + struct hlist_bl_node *next, **pprev; + }; +-#define INIT_HLIST_BL_HEAD(ptr) \ +- ((ptr)->first = NULL) ++ ++static inline void INIT_HLIST_BL_HEAD(struct hlist_bl_head *h) ++{ ++ h->first = NULL; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ raw_spin_lock_init(&h->lock); ++#endif ++} + + static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) + { +@@ -119,12 +129,26 @@ static inline void hlist_bl_del_init(str + + static inline void hlist_bl_lock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + bit_spin_lock(0, (unsigned long *)b); ++#else ++ raw_spin_lock(&b->lock); ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __set_bit(0, (unsigned long *)b); ++#endif ++#endif + } + + static inline void hlist_bl_unlock(struct hlist_bl_head *b) + { ++#ifndef CONFIG_PREEMPT_RT_BASE + __bit_spin_unlock(0, (unsigned long *)b); ++#else ++#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) ++ __clear_bit(0, (unsigned long *)b); ++#endif ++ raw_spin_unlock(&b->lock); ++#endif + } + + static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) diff --git a/debian/patches/features/all/rt/locallock-provide-get-put-_locked_ptr-variants.patch b/debian/patches/features/all/rt/locallock-provide-get-put-_locked_ptr-variants.patch new file mode 100644 index 000000000..c405af752 --- /dev/null +++ b/debian/patches/features/all/rt/locallock-provide-get-put-_locked_ptr-variants.patch @@ -0,0 +1,43 @@ +From: Julia Cartwright +Date: Mon, 7 May 2018 08:58:56 -0500 +Subject: [PATCH] locallock: provide {get,put}_locked_ptr() variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Provide a set of locallocked accessors for pointers to per-CPU data; +this is useful for dynamically-allocated per-CPU regions, for example. + +These are symmetric with the {get,put}_cpu_ptr() per-CPU accessor +variants. + +Signed-off-by: Julia Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/locallock.h | 10 ++++++++++ + 1 file changed, 10 insertions(+) + +--- a/include/linux/locallock.h ++++ b/include/linux/locallock.h +@@ -222,6 +222,14 @@ static inline int __local_unlock_irqrest + + #define put_locked_var(lvar, var) local_unlock(lvar); + ++#define get_locked_ptr(lvar, var) \ ++ ({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(var); \ ++ }) ++ ++#define put_locked_ptr(lvar, var) local_unlock(lvar); ++ + #define local_lock_cpu(lvar) \ + ({ \ + local_lock(lvar); \ +@@ -262,6 +270,8 @@ static inline void local_irq_lock_init(i + + #define get_locked_var(lvar, var) get_cpu_var(var) + #define put_locked_var(lvar, var) put_cpu_var(var) ++#define get_locked_ptr(lvar, var) get_cpu_ptr(var) ++#define put_locked_ptr(lvar, var) put_cpu_ptr(var) + + #define local_lock_cpu(lvar) get_cpu() + #define local_unlock_cpu(lvar) put_cpu() diff --git a/debian/patches/features/all/rt/localversion.patch b/debian/patches/features/all/rt/localversion.patch new file mode 100644 index 000000000..3f7637b5d --- /dev/null +++ b/debian/patches/features/all/rt/localversion.patch @@ -0,0 +1,14 @@ +Subject: Add localversion for -RT release +From: Thomas Gleixner +Date: Fri, 08 Jul 2011 20:25:16 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +--- + localversion-rt | 1 + + 1 file changed, 1 insertion(+) + +--- /dev/null ++++ b/localversion-rt +@@ -0,0 +1 @@ ++-rt1 diff --git a/debian/patches/features/all/rt/lockdep-disable-self-test.patch b/debian/patches/features/all/rt/lockdep-disable-self-test.patch new file mode 100644 index 000000000..fe6a892b8 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-disable-self-test.patch @@ -0,0 +1,29 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 17 Oct 2017 16:36:18 +0200 +Subject: [PATCH] lockdep: disable self-test +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The self-test wasn't always 100% accurate for RT. We disabled a few +tests which failed because they had a different semantic for RT. Some +still reported false positives. Now the selftest locks up the system +during boot and it needs to be investigated… + +Signed-off-by: Sebastian Andrzej Siewior +--- + lib/Kconfig.debug | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/lib/Kconfig.debug ++++ b/lib/Kconfig.debug +@@ -1201,7 +1201,7 @@ config DEBUG_ATOMIC_SLEEP + + config DEBUG_LOCKING_API_SELFTESTS + bool "Locking API boot-time self-tests" +- depends on DEBUG_KERNEL ++ depends on DEBUG_KERNEL && !PREEMPT_RT_FULL + help + Say Y here if you want the kernel to run a short self-test during + bootup. The self-test checks whether common types of locking bugs diff --git a/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch b/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch new file mode 100644 index 000000000..6ebfaef63 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-no-softirq-accounting-on-rt.patch @@ -0,0 +1,70 @@ +Subject: lockdep: Make it RT aware +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 18:51:23 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +teach lockdep that we don't really do softirqs on -RT. + +Signed-off-by: Thomas Gleixner +--- + include/linux/irqflags.h | 23 +++++++++++++++-------- + kernel/locking/lockdep.c | 2 ++ + 2 files changed, 17 insertions(+), 8 deletions(-) + +--- a/include/linux/irqflags.h ++++ b/include/linux/irqflags.h +@@ -32,14 +32,6 @@ do { \ + do { \ + current->hardirq_context--; \ + } while (0) +-# define lockdep_softirq_enter() \ +-do { \ +- current->softirq_context++; \ +-} while (0) +-# define lockdep_softirq_exit() \ +-do { \ +- current->softirq_context--; \ +-} while (0) + #else + # define trace_hardirqs_on() do { } while (0) + # define trace_hardirqs_off() do { } while (0) +@@ -54,6 +46,21 @@ do { \ + # define lockdep_softirq_enter() do { } while (0) + # define lockdep_softirq_exit() do { } while (0) + #endif ++ ++#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL) ++# define lockdep_softirq_enter() \ ++do { \ ++ current->softirq_context++; \ ++} while (0) ++# define lockdep_softirq_exit() \ ++do { \ ++ current->softirq_context--; \ ++} while (0) ++ ++#else ++# define lockdep_softirq_enter() do { } while (0) ++# define lockdep_softirq_exit() do { } while (0) ++#endif + + #if defined(CONFIG_IRQSOFF_TRACER) || \ + defined(CONFIG_PREEMPT_TRACER) +--- a/kernel/locking/lockdep.c ++++ b/kernel/locking/lockdep.c +@@ -3847,6 +3847,7 @@ static void check_flags(unsigned long fl + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * We dont accurately track softirq state in e.g. + * hardirq contexts (such as on 4KSTACKS), so only +@@ -3861,6 +3862,7 @@ static void check_flags(unsigned long fl + DEBUG_LOCKS_WARN_ON(!current->softirqs_enabled); + } + } ++#endif + + if (!debug_locks) + print_irqtrace_events(current); diff --git a/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch b/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch new file mode 100644 index 000000000..eb2e63da7 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch @@ -0,0 +1,142 @@ +From: Josh Cartwright +Date: Wed, 28 Jan 2015 13:08:45 -0600 +Subject: lockdep: selftest: fix warnings due to missing PREEMPT_RT conditionals +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +"lockdep: Selftest: Only do hardirq context test for raw spinlock" +disabled the execution of certain tests with PREEMPT_RT_FULL, but did +not prevent the tests from still being defined. This leads to warnings +like: + + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:574:1: warning: 'irqsafe1_hard_rlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_12' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:577:1: warning: 'irqsafe1_hard_wlock_21' defined but not used [-Wunused-function] + ./linux/lib/locking-selftest.c:580:1: warning: 'irqsafe1_soft_spin_12' defined but not used [-Wunused-function] + ... + +Fixed by wrapping the test definitions in #ifndef CONFIG_PREEMPT_RT_FULL +conditionals. + + +Signed-off-by: Josh Cartwright +Signed-off-by: Xander Huff +Acked-by: Gratian Crisan +Signed-off-by: Sebastian Andrzej Siewior +--- + lib/locking-selftest.c | 27 +++++++++++++++++++++++++++ + 1 file changed, 27 insertions(+) + +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -742,6 +742,8 @@ GENERATE_TESTCASE(init_held_rtmutex); + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_hard_rlock) + +@@ -757,9 +759,12 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe1_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Enabling hardirqs with a softirq-safe lock held: + */ +@@ -792,6 +797,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #undef E1 + #undef E2 + ++#endif ++ + /* + * Enabling irqs with an irq-safe lock held: + */ +@@ -815,6 +822,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2A + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_hard_rlock) + +@@ -830,6 +839,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + +@@ -861,6 +872,8 @@ GENERATE_PERMUTATIONS_2_EVENTS(irqsafe2B + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_hard_rlock) + +@@ -876,6 +889,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 +@@ -909,6 +924,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe3_ + #include "locking-selftest-spin-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_spin) + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #include "locking-selftest-rlock-hardirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_hard_rlock) + +@@ -924,10 +941,14 @@ GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_ + #include "locking-selftest-wlock-softirq.h" + GENERATE_PERMUTATIONS_3_EVENTS(irqsafe4_soft_wlock) + ++#endif ++ + #undef E1 + #undef E2 + #undef E3 + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock irq inversion. + * +@@ -990,6 +1011,10 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_inver + #undef E2 + #undef E3 + ++#endif ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * read-lock / write-lock recursion that is actually safe. + */ +@@ -1028,6 +1053,8 @@ GENERATE_PERMUTATIONS_3_EVENTS(irq_read_ + #undef E2 + #undef E3 + ++#endif ++ + /* + * read-lock / write-lock recursion that is unsafe. + */ diff --git a/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch b/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch new file mode 100644 index 000000000..f028d8e17 --- /dev/null +++ b/debian/patches/features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch @@ -0,0 +1,57 @@ +Subject: lockdep: selftest: Only do hardirq context test for raw spinlock +From: Yong Zhang +Date: Mon, 16 Apr 2012 15:01:56 +0800 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +From: Yong Zhang + +On -rt there is no softirq context any more and rwlock is sleepable, +disable softirq context test and rwlock+irq test. + +Signed-off-by: Yong Zhang +Cc: Yong Zhang +Link: http://lkml.kernel.org/r/1334559716-18447-3-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +--- + lib/locking-selftest.c | 23 +++++++++++++++++++++++ + 1 file changed, 23 insertions(+) + +--- a/lib/locking-selftest.c ++++ b/lib/locking-selftest.c +@@ -2057,6 +2057,7 @@ void locking_selftest(void) + + printk(" --------------------------------------------------------------------------\n"); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * irq-context testcases: + */ +@@ -2069,6 +2070,28 @@ void locking_selftest(void) + + DO_TESTCASE_6x2("irq read-recursion", irq_read_recursion); + // DO_TESTCASE_6x2B("irq read-recursion #2", irq_read_recursion2); ++#else ++ /* On -rt, we only do hardirq context test for raw spinlock */ ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 12); ++ DO_TESTCASE_1B("hard-irqs-on + irq-safe-A", irqsafe1_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 12); ++ DO_TESTCASE_1B("hard-safe-A + irqs-on", irqsafe2B_hard_spin, 21); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #1", irqsafe3_hard_spin, 321); ++ ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 123); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 132); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 213); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 231); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 312); ++ DO_TESTCASE_1B("hard-safe-A + unsafe-B #2", irqsafe4_hard_spin, 321); ++#endif + + ww_tests(); + diff --git a/debian/patches/features/all/rt/locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch b/debian/patches/features/all/rt/locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch new file mode 100644 index 000000000..a4a5784b5 --- /dev/null +++ b/debian/patches/features/all/rt/locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch @@ -0,0 +1,158 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 4 Aug 2017 17:40:42 +0200 +Subject: [PATCH 1/2] locking: don't check for __LINUX_SPINLOCK_TYPES_H on -RT + archs +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Upstream uses arch_spinlock_t within spinlock_t and requests that +spinlock_types.h header file is included first. +On -RT we have the rt_mutex with its raw_lock wait_lock which needs +architectures' spinlock_types.h header file for its definition. However +we need rt_mutex first because it is used to build the spinlock_t so +that check does not work for us. +Therefore I am dropping that check. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/alpha/include/asm/spinlock_types.h | 4 ---- + arch/arm/include/asm/spinlock_types.h | 4 ---- + arch/arm64/include/asm/spinlock_types.h | 4 ---- + arch/hexagon/include/asm/spinlock_types.h | 4 ---- + arch/ia64/include/asm/spinlock_types.h | 4 ---- + arch/powerpc/include/asm/spinlock_types.h | 4 ---- + arch/s390/include/asm/spinlock_types.h | 4 ---- + arch/sh/include/asm/spinlock_types.h | 4 ---- + arch/xtensa/include/asm/spinlock_types.h | 4 ---- + include/linux/spinlock_types_up.h | 4 ---- + 10 files changed, 40 deletions(-) + +--- a/arch/alpha/include/asm/spinlock_types.h ++++ b/arch/alpha/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ALPHA_SPINLOCK_TYPES_H + #define _ALPHA_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +--- a/arch/arm/include/asm/spinlock_types.h ++++ b/arch/arm/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + #define TICKET_SHIFT 16 + + typedef struct { +--- a/arch/arm64/include/asm/spinlock_types.h ++++ b/arch/arm64/include/asm/spinlock_types.h +@@ -16,10 +16,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H) +-# error "please don't include this file directly" +-#endif +- + #include + + #define TICKET_SHIFT 16 +--- a/arch/hexagon/include/asm/spinlock_types.h ++++ b/arch/hexagon/include/asm/spinlock_types.h +@@ -21,10 +21,6 @@ + #ifndef _ASM_SPINLOCK_TYPES_H + #define _ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +--- a/arch/ia64/include/asm/spinlock_types.h ++++ b/arch/ia64/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ASM_IA64_SPINLOCK_TYPES_H + #define _ASM_IA64_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +--- a/arch/powerpc/include/asm/spinlock_types.h ++++ b/arch/powerpc/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef _ASM_POWERPC_SPINLOCK_TYPES_H + #define _ASM_POWERPC_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int slock; + } arch_spinlock_t; +--- a/arch/s390/include/asm/spinlock_types.h ++++ b/arch/s390/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + int lock; + } __attribute__ ((aligned (4))) arch_spinlock_t; +--- a/arch/sh/include/asm/spinlock_types.h ++++ b/arch/sh/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SH_SPINLOCK_TYPES_H + #define __ASM_SH_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int lock; + } arch_spinlock_t; +--- a/arch/xtensa/include/asm/spinlock_types.h ++++ b/arch/xtensa/include/asm/spinlock_types.h +@@ -2,10 +2,6 @@ + #ifndef __ASM_SPINLOCK_TYPES_H + #define __ASM_SPINLOCK_TYPES_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + typedef struct { + volatile unsigned int slock; + } arch_spinlock_t; +--- a/include/linux/spinlock_types_up.h ++++ b/include/linux/spinlock_types_up.h +@@ -1,10 +1,6 @@ + #ifndef __LINUX_SPINLOCK_TYPES_UP_H + #define __LINUX_SPINLOCK_TYPES_UP_H + +-#ifndef __LINUX_SPINLOCK_TYPES_H +-# error "please don't include this file directly" +-#endif +- + /* + * include/linux/spinlock_types_up.h - spinlock type definitions for UP + * diff --git a/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch b/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch new file mode 100644 index 000000000..5c363f76d --- /dev/null +++ b/debian/patches/features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch @@ -0,0 +1,27 @@ +From: "Wolfgang M. Reimer" +Date: Tue, 21 Jul 2015 16:20:07 +0200 +Subject: locking: locktorture: Do NOT include rwlock.h directly +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Including rwlock.h directly will cause kernel builds to fail +if CONFIG_PREEMPT_RT_FULL is defined. The correct header file +(rwlock_rt.h OR rwlock.h) will be included by spinlock.h which +is included by locktorture.c anyway. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Wolfgang M. Reimer +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/locktorture.c | 1 - + 1 file changed, 1 deletion(-) + +--- a/kernel/locking/locktorture.c ++++ b/kernel/locking/locktorture.c +@@ -26,7 +26,6 @@ + #include + #include + #include +-#include + #include + #include + #include diff --git a/debian/patches/features/all/rt/locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch b/debian/patches/features/all/rt/locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch new file mode 100644 index 000000000..695b1e0a2 --- /dev/null +++ b/debian/patches/features/all/rt/locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch @@ -0,0 +1,74 @@ +From: Mikulas Patocka +Date: Mon, 13 Nov 2017 12:56:53 -0500 +Subject: [PATCH] locking/rt-mutex: fix deadlock in device mapper / block-IO +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When some block device driver creates a bio and submits it to another +block device driver, the bio is added to current->bio_list (in order to +avoid unbounded recursion). + +However, this queuing of bios can cause deadlocks, in order to avoid them, +device mapper registers a function flush_current_bio_list. This function +is called when device mapper driver blocks. It redirects bios queued on +current->bio_list to helper workqueues, so that these bios can proceed +even if the driver is blocked. + +The problem with CONFIG_PREEMPT_RT_FULL is that when the device mapper +driver blocks, it won't call flush_current_bio_list (because +tsk_is_pi_blocked returns true in sched_submit_work), so deadlocks in +block device stack can happen. + +Note that we can't call blk_schedule_flush_plug if tsk_is_pi_blocked +returns true - that would cause +BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in +task_blocks_on_rt_mutex when flush_current_bio_list attempts to take a +spinlock. + +So the proper fix is to call blk_schedule_flush_plug in rt_mutex_fastlock, +when fast acquire failed and when the task is about to block. + +CC: stable-rt@vger.kernel.org +[bigeasy: The deadlock is not device-mapper specific, it can also occur + in plain EXT4] +Signed-off-by: Mikulas Patocka +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 13 +++++++++++++ + 1 file changed, 13 insertions(+) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -24,6 +24,7 @@ + #include + #include + #include ++#include + + #include "rtmutex_common.h" + +@@ -1919,6 +1920,15 @@ rt_mutex_fastlock(struct rt_mutex *lock, + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + ++ /* ++ * If rt_mutex blocks, the function sched_submit_work will not call ++ * blk_schedule_flush_plug (because tsk_is_pi_blocked would be true). ++ * We must call blk_schedule_flush_plug here, if we don't call it, ++ * a deadlock in device mapper may happen. ++ */ ++ if (unlikely(blk_needs_flush_plug(current))) ++ blk_schedule_flush_plug(current); ++ + return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); + } + +@@ -1936,6 +1946,9 @@ rt_mutex_timed_fastlock(struct rt_mutex + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + ++ if (unlikely(blk_needs_flush_plug(current))) ++ blk_schedule_flush_plug(current); ++ + return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + diff --git a/debian/patches/features/all/rt/locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch b/debian/patches/features/all/rt/locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch new file mode 100644 index 000000000..a7274d625 --- /dev/null +++ b/debian/patches/features/all/rt/locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch @@ -0,0 +1,33 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 16 Nov 2017 16:48:48 +0100 +Subject: [PATCH] locking/rtmutex: re-init the wait_lock in + rt_mutex_init_proxy_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +We could provide a key-class for the lockdep (and fixup all callers) or +move the init to all callers (like it was) in order to avoid lockdep +seeing a double-lock of the wait_lock. + +Reported-by: Fernando Lopez-Lezcano +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -2281,6 +2281,14 @@ void rt_mutex_init_proxy_locked(struct r + struct task_struct *proxy_owner) + { + __rt_mutex_init(lock, NULL, NULL); ++#ifdef CONFIG_DEBUG_SPINLOCK ++ /* ++ * get another key class for the wait_lock. LOCK_PI and UNLOCK_PI is ++ * holding the ->wait_lock of the proxy_lock while unlocking a sleeping ++ * lock. ++ */ ++ raw_spin_lock_init(&lock->wait_lock); ++#endif + debug_rt_mutex_proxy_lock(lock, proxy_owner); + rt_mutex_set_owner(lock, proxy_owner); + } diff --git a/debian/patches/features/all/rt/md-disable-bcache.patch b/debian/patches/features/all/rt/md-disable-bcache.patch new file mode 100644 index 000000000..8f982d762 --- /dev/null +++ b/debian/patches/features/all/rt/md-disable-bcache.patch @@ -0,0 +1,32 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Aug 2013 11:48:57 +0200 +Subject: md: disable bcache +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +It uses anon semaphores +|drivers/md/bcache/request.c: In function ‘cached_dev_write_complete’: +|drivers/md/bcache/request.c:1007:2: error: implicit declaration of function ‘up_read_non_owner’ [-Werror=implicit-function-declaration] +| up_read_non_owner(&dc->writeback_lock); +| ^ +|drivers/md/bcache/request.c: In function ‘request_write’: +|drivers/md/bcache/request.c:1033:2: error: implicit declaration of function ‘down_read_non_owner’ [-Werror=implicit-function-declaration] +| down_read_non_owner(&dc->writeback_lock); +| ^ + +either we get rid of those or we have to introduce them… + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/md/bcache/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/drivers/md/bcache/Kconfig ++++ b/drivers/md/bcache/Kconfig +@@ -1,6 +1,7 @@ + + config BCACHE + tristate "Block device as cache" ++ depends on !PREEMPT_RT_FULL + ---help--- + Allows a block device to be used as cache for other devices; uses + a btree for indexing and the layout is optimized for SSDs. diff --git a/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch b/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch new file mode 100644 index 000000000..92d286b4c --- /dev/null +++ b/debian/patches/features/all/rt/md-raid5-percpu-handling-rt-aware.patch @@ -0,0 +1,70 @@ +From: Thomas Gleixner +Date: Tue, 6 Apr 2010 16:51:31 +0200 +Subject: md: raid5: Make raid5_percpu handling RT aware +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +__raid_run_ops() disables preemption with get_cpu() around the access +to the raid5_percpu variables. That causes scheduling while atomic +spews on RT. + +Serialize the access to the percpu data with a lock and keep the code +preemptible. + +Reported-by: Udo van den Heuvel +Signed-off-by: Thomas Gleixner +Tested-by: Udo van den Heuvel + +--- + drivers/md/raid5.c | 8 +++++--- + drivers/md/raid5.h | 1 + + 2 files changed, 6 insertions(+), 3 deletions(-) + +--- a/drivers/md/raid5.c ++++ b/drivers/md/raid5.c +@@ -2069,8 +2069,9 @@ static void raid_run_ops(struct stripe_h + struct raid5_percpu *percpu; + unsigned long cpu; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + percpu = per_cpu_ptr(conf->percpu, cpu); ++ spin_lock(&percpu->lock); + if (test_bit(STRIPE_OP_BIOFILL, &ops_request)) { + ops_run_biofill(sh); + overlap_clear++; +@@ -2129,7 +2130,8 @@ static void raid_run_ops(struct stripe_h + if (test_and_clear_bit(R5_Overlap, &dev->flags)) + wake_up(&sh->raid_conf->wait_for_overlap); + } +- put_cpu(); ++ spin_unlock(&percpu->lock); ++ put_cpu_light(); + } + + static void free_stripe(struct kmem_cache *sc, struct stripe_head *sh) +@@ -6793,6 +6795,7 @@ static int raid456_cpu_up_prepare(unsign + __func__, cpu); + return -ENOMEM; + } ++ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock); + return 0; + } + +@@ -6803,7 +6806,6 @@ static int raid5_alloc_percpu(struct r5c + conf->percpu = alloc_percpu(struct raid5_percpu); + if (!conf->percpu) + return -ENOMEM; +- + err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node); + if (!err) { + conf->scribble_disks = max(conf->raid_disks, +--- a/drivers/md/raid5.h ++++ b/drivers/md/raid5.h +@@ -637,6 +637,7 @@ struct r5conf { + int recovery_disabled; + /* per cpu variables */ + struct raid5_percpu { ++ spinlock_t lock; /* Protection for -RT */ + struct page *spare_page; /* Used when checking P/Q in raid6 */ + struct flex_array *scribble; /* space for constructing buffer + * lists and performing address diff --git a/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch b/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch new file mode 100644 index 000000000..cd1a02ed5 --- /dev/null +++ b/debian/patches/features/all/rt/mips-disable-highmem-on-rt.patch @@ -0,0 +1,23 @@ +Subject: mips: Disable highmem on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:10:12 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner +--- + arch/mips/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/mips/Kconfig ++++ b/arch/mips/Kconfig +@@ -2519,7 +2519,7 @@ config MIPS_CRC_SUPPORT + # + config HIGHMEM + bool "High Memory Support" +- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA ++ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL + + config CPU_SUPPORTS_HIGHMEM + bool diff --git a/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch b/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch new file mode 100644 index 000000000..b2769e056 --- /dev/null +++ b/debian/patches/features/all/rt/mm-convert-swap-to-percpu-locked.patch @@ -0,0 +1,200 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:51 -0500 +Subject: mm/swap: Convert to percpu locked +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Replace global locks (get_cpu + local_irq_save) with "local_locks()". +Currently there is one of for "rotate" and one for "swap". + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/swap.h | 2 ++ + mm/compaction.c | 6 ++++-- + mm/page_alloc.c | 3 ++- + mm/swap.c | 38 ++++++++++++++++++++++---------------- + 4 files changed, 30 insertions(+), 19 deletions(-) + +--- a/include/linux/swap.h ++++ b/include/linux/swap.h +@@ -12,6 +12,7 @@ + #include + #include + #include ++#include + #include + + struct notifier_block; +@@ -322,6 +323,7 @@ extern unsigned long nr_free_pagecache_p + + + /* linux/mm/swap.c */ ++DECLARE_LOCAL_IRQ_LOCK(swapvec_lock); + extern void lru_cache_add(struct page *); + extern void lru_cache_add_anon(struct page *page); + extern void lru_cache_add_file(struct page *page); +--- a/mm/compaction.c ++++ b/mm/compaction.c +@@ -1657,10 +1657,12 @@ static enum compact_result compact_zone( + block_start_pfn(cc->migrate_pfn, cc->order); + + if (cc->last_migrated_pfn < current_block_start) { +- cpu = get_cpu(); ++ cpu = get_cpu_light(); ++ local_lock_irq(swapvec_lock); + lru_add_drain_cpu(cpu); ++ local_unlock_irq(swapvec_lock); + drain_local_pages(zone); +- put_cpu(); ++ put_cpu_light(); + /* No more flushing until we migrate again */ + cc->last_migrated_pfn = 0; + } +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -7125,8 +7125,9 @@ void __init free_area_init(unsigned long + + static int page_alloc_cpu_dead(unsigned int cpu) + { +- ++ local_lock_irq_on(swapvec_lock, cpu); + lru_add_drain_cpu(cpu); ++ local_unlock_irq_on(swapvec_lock, cpu); + drain_pages(cpu); + + /* +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -33,6 +33,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -51,6 +52,8 @@ static DEFINE_PER_CPU(struct pagevec, lr + #ifdef CONFIG_SMP + static DEFINE_PER_CPU(struct pagevec, activate_page_pvecs); + #endif ++static DEFINE_LOCAL_IRQ_LOCK(rotate_lock); ++DEFINE_LOCAL_IRQ_LOCK(swapvec_lock); + + /* + * This path almost never happens for VM activity - pages are normally +@@ -253,11 +256,11 @@ void rotate_reclaimable_page(struct page + unsigned long flags; + + get_page(page); +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pvec = this_cpu_ptr(&lru_rotate_pvecs); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + } + +@@ -307,12 +310,13 @@ void activate_page(struct page *page) + { + page = compound_head(page); + if (PageLRU(page) && !PageActive(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(activate_page_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ activate_page_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, __activate_page, NULL); +- put_cpu_var(activate_page_pvecs); ++ put_locked_var(swapvec_lock, activate_page_pvecs); + } + } + +@@ -339,7 +343,7 @@ void activate_page(struct page *page) + + static void __lru_cache_activate_page(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + int i; + + /* +@@ -361,7 +365,7 @@ static void __lru_cache_activate_page(st + } + } + +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /* +@@ -403,12 +407,12 @@ EXPORT_SYMBOL(mark_page_accessed); + + static void __lru_cache_add(struct page *page) + { +- struct pagevec *pvec = &get_cpu_var(lru_add_pvec); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, lru_add_pvec); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + __pagevec_lru_add(pvec); +- put_cpu_var(lru_add_pvec); ++ put_locked_var(swapvec_lock, lru_add_pvec); + } + + /** +@@ -586,9 +590,9 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ +- local_irq_save(flags); ++ local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); +- local_irq_restore(flags); ++ local_unlock_irqrestore(rotate_lock, flags); + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -620,11 +624,12 @@ void deactivate_file_page(struct page *p + return; + + if (likely(get_page_unless_zero(page))) { +- struct pagevec *pvec = &get_cpu_var(lru_deactivate_file_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_deactivate_file_pvecs); + + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_deactivate_file_fn, NULL); +- put_cpu_var(lru_deactivate_file_pvecs); ++ put_locked_var(swapvec_lock, lru_deactivate_file_pvecs); + } + } + +@@ -639,19 +644,20 @@ void mark_page_lazyfree(struct page *pag + { + if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) && + !PageSwapCache(page) && !PageUnevictable(page)) { +- struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs); ++ struct pagevec *pvec = &get_locked_var(swapvec_lock, ++ lru_lazyfree_pvecs); + + get_page(page); + if (!pagevec_add(pvec, page) || PageCompound(page)) + pagevec_lru_move_fn(pvec, lru_lazyfree_fn, NULL); +- put_cpu_var(lru_lazyfree_pvecs); ++ put_locked_var(swapvec_lock, lru_lazyfree_pvecs); + } + } + + void lru_add_drain(void) + { +- lru_add_drain_cpu(get_cpu()); +- put_cpu(); ++ lru_add_drain_cpu(local_lock_cpu(swapvec_lock)); ++ local_unlock_cpu(swapvec_lock); + } + + static void lru_add_drain_per_cpu(struct work_struct *dummy) diff --git a/debian/patches/features/all/rt/mm-disable-sloub-rt.patch b/debian/patches/features/all/rt/mm-disable-sloub-rt.patch new file mode 100644 index 000000000..749e1b16b --- /dev/null +++ b/debian/patches/features/all/rt/mm-disable-sloub-rt.patch @@ -0,0 +1,32 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:44:03 -0500 +Subject: mm: Allow only slub on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Disable SLAB and SLOB on -RT. Only SLUB is adopted to -RT needs. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + init/Kconfig | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1591,6 +1591,7 @@ choice + + config SLAB + bool "SLAB" ++ depends on !PREEMPT_RT_FULL + select HAVE_HARDENED_USERCOPY_ALLOCATOR + help + The regular slab allocator that is established and known to work +@@ -1611,6 +1612,7 @@ config SLUB + config SLOB + depends on EXPERT + bool "SLOB (Simple Allocator)" ++ depends on !PREEMPT_RT_FULL + help + SLOB replaces the stock allocator with a drastically simpler + allocator. SLOB is generally more space efficient but diff --git a/debian/patches/features/all/rt/mm-enable-slub.patch b/debian/patches/features/all/rt/mm-enable-slub.patch new file mode 100644 index 000000000..a8fc47710 --- /dev/null +++ b/debian/patches/features/all/rt/mm-enable-slub.patch @@ -0,0 +1,36 @@ +Subject: mm: Enable SLUB for RT +From: Thomas Gleixner +Date: Thu, 25 Oct 2012 10:32:35 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Avoid the memory allocation in IRQ section + +Signed-off-by: Thomas Gleixner +[bigeasy: factor out everything except the kcalloc() workaorund ] +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/slub.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -3679,6 +3679,11 @@ static void list_slab_objects(struct kme + const char *text) + { + #ifdef CONFIG_SLUB_DEBUG ++#ifdef CONFIG_PREEMPT_RT_BASE ++ /* XXX move out of irq-off section */ ++ slab_err(s, page, text, s->name); ++#else ++ + void *addr = page_address(page); + void *p; + unsigned long *map = kcalloc(BITS_TO_LONGS(page->objects), +@@ -3700,6 +3705,7 @@ static void list_slab_objects(struct kme + slab_unlock(page); + kfree(map); + #endif ++#endif + } + + /* diff --git a/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch b/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch new file mode 100644 index 000000000..83e821699 --- /dev/null +++ b/debian/patches/features/all/rt/mm-make-vmstat-rt-aware.patch @@ -0,0 +1,137 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:30:13 -0500 +Subject: mm/vmstat: Protect per cpu variables with preempt disable on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Disable preemption on -RT for the vmstat code. On vanila the code runs in +IRQ-off regions while on -RT it is not. "preempt_disable" ensures that the +same ressources is not updated in parallel due to preemption. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/vmstat.h | 4 ++++ + mm/vmstat.c | 12 ++++++++++++ + 2 files changed, 16 insertions(+) + +--- a/include/linux/vmstat.h ++++ b/include/linux/vmstat.h +@@ -54,7 +54,9 @@ DECLARE_PER_CPU(struct vm_event_state, v + */ + static inline void __count_vm_event(enum vm_event_item item) + { ++ preempt_disable_rt(); + raw_cpu_inc(vm_event_states.event[item]); ++ preempt_enable_rt(); + } + + static inline void count_vm_event(enum vm_event_item item) +@@ -64,7 +66,9 @@ static inline void count_vm_event(enum v + + static inline void __count_vm_events(enum vm_event_item item, long delta) + { ++ preempt_disable_rt(); + raw_cpu_add(vm_event_states.event[item], delta); ++ preempt_enable_rt(); + } + + static inline void count_vm_events(enum vm_event_item item, long delta) +--- a/mm/vmstat.c ++++ b/mm/vmstat.c +@@ -320,6 +320,7 @@ void __mod_zone_page_state(struct zone * + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -329,6 +330,7 @@ void __mod_zone_page_state(struct zone * + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_zone_page_state); + +@@ -340,6 +342,7 @@ void __mod_node_page_state(struct pglist + long x; + long t; + ++ preempt_disable_rt(); + x = delta + __this_cpu_read(*p); + + t = __this_cpu_read(pcp->stat_threshold); +@@ -349,6 +352,7 @@ void __mod_node_page_state(struct pglist + x = 0; + } + __this_cpu_write(*p, x); ++ preempt_enable_rt(); + } + EXPORT_SYMBOL(__mod_node_page_state); + +@@ -381,6 +385,7 @@ void __inc_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -389,6 +394,7 @@ void __inc_zone_state(struct zone *zone, + zone_page_state_add(v + overstep, zone, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) +@@ -397,6 +403,7 @@ void __inc_node_state(struct pglist_data + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_inc_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v > t)) { +@@ -405,6 +412,7 @@ void __inc_node_state(struct pglist_data + node_page_state_add(v + overstep, pgdat, item); + __this_cpu_write(*p, -overstep); + } ++ preempt_enable_rt(); + } + + void __inc_zone_page_state(struct page *page, enum zone_stat_item item) +@@ -425,6 +433,7 @@ void __dec_zone_state(struct zone *zone, + s8 __percpu *p = pcp->vm_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -433,6 +442,7 @@ void __dec_zone_state(struct zone *zone, + zone_page_state_add(v - overstep, zone, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) +@@ -441,6 +451,7 @@ void __dec_node_state(struct pglist_data + s8 __percpu *p = pcp->vm_node_stat_diff + item; + s8 v, t; + ++ preempt_disable_rt(); + v = __this_cpu_dec_return(*p); + t = __this_cpu_read(pcp->stat_threshold); + if (unlikely(v < - t)) { +@@ -449,6 +460,7 @@ void __dec_node_state(struct pglist_data + node_page_state_add(v - overstep, pgdat, item); + __this_cpu_write(*p, overstep); + } ++ preempt_enable_rt(); + } + + void __dec_zone_page_state(struct page *page, enum zone_stat_item item) diff --git a/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch b/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch new file mode 100644 index 000000000..71bfad058 --- /dev/null +++ b/debian/patches/features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch @@ -0,0 +1,69 @@ +From: Yang Shi +Subject: mm/memcontrol: Don't call schedule_work_on in preemption disabled context +Date: Wed, 30 Oct 2013 11:48:33 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The following trace is triggered when running ltp oom test cases: + +BUG: sleeping function called from invalid context at kernel/rtmutex.c:659 +in_atomic(): 1, irqs_disabled(): 0, pid: 17188, name: oom03 +Preemption disabled at:[] mem_cgroup_reclaim+0x90/0xe0 + +CPU: 2 PID: 17188 Comm: oom03 Not tainted 3.10.10-rt3 #2 +Hardware name: Intel Corporation Calpella platform/MATXM-CORE-411-B, BIOS 4.6.3 08/18/2010 +ffff88007684d730 ffff880070df9b58 ffffffff8169918d ffff880070df9b70 +ffffffff8106db31 ffff88007688b4a0 ffff880070df9b88 ffffffff8169d9c0 +ffff88007688b4a0 ffff880070df9bc8 ffffffff81059da1 0000000170df9bb0 +Call Trace: +[] dump_stack+0x19/0x1b +[] __might_sleep+0xf1/0x170 +[] rt_spin_lock+0x20/0x50 +[] queue_work_on+0x61/0x100 +[] drain_all_stock+0xe1/0x1c0 +[] mem_cgroup_reclaim+0x90/0xe0 +[] __mem_cgroup_try_charge+0x41a/0xc40 +[] ? release_pages+0x1b1/0x1f0 +[] ? sched_exec+0x40/0xb0 +[] mem_cgroup_charge_common+0x37/0x70 +[] mem_cgroup_newpage_charge+0x26/0x30 +[] handle_pte_fault+0x618/0x840 +[] ? unpin_current_cpu+0x16/0x70 +[] ? migrate_enable+0xd4/0x200 +[] handle_mm_fault+0x145/0x1e0 +[] __do_page_fault+0x1a1/0x4c0 +[] ? preempt_schedule_irq+0x4b/0x70 +[] ? retint_kernel+0x37/0x40 +[] do_page_fault+0xe/0x10 +[] page_fault+0x22/0x30 + +So, to prevent schedule_work_on from being called in preempt disabled context, +replace the pair of get/put_cpu() to get/put_cpu_light(). + + +Signed-off-by: Yang Shi +Signed-off-by: Sebastian Andrzej Siewior +--- + + mm/memcontrol.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -1783,7 +1783,7 @@ static void drain_all_stock(struct mem_c + * as well as workers from this path always operate on the local + * per-cpu data. CPU up doesn't touch memcg_stock at all. + */ +- curcpu = get_cpu(); ++ curcpu = get_cpu_light(); + for_each_online_cpu(cpu) { + struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu); + struct mem_cgroup *memcg; +@@ -1803,7 +1803,7 @@ static void drain_all_stock(struct mem_c + } + css_put(&memcg->css); + } +- put_cpu(); ++ put_cpu_light(); + mutex_unlock(&percpu_charge_mutex); + } + diff --git a/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch b/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch new file mode 100644 index 000000000..870e85df7 --- /dev/null +++ b/debian/patches/features/all/rt/mm-memcontrol-do_not_disable_irq.patch @@ -0,0 +1,117 @@ +From: Sebastian Andrzej Siewior +Subject: mm/memcontrol: Replace local_irq_disable with local locks +Date: Wed, 28 Jan 2015 17:14:16 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There are a few local_irq_disable() which then take sleeping locks. This +patch converts them local locks. + +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/memcontrol.c | 24 ++++++++++++++++-------- + 1 file changed, 16 insertions(+), 8 deletions(-) + +--- a/mm/memcontrol.c ++++ b/mm/memcontrol.c +@@ -69,6 +69,7 @@ + #include + #include + #include "slab.h" ++#include + + #include + +@@ -94,6 +95,8 @@ int do_swap_account __read_mostly; + #define do_swap_account 0 + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(event_lock); ++ + /* Whether legacy memory+swap accounting is active */ + static bool do_memsw_account(void) + { +@@ -4558,12 +4561,12 @@ static int mem_cgroup_move_account(struc + + ret = 0; + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(to, page, compound, nr_pages); + memcg_check_events(to, page); + mem_cgroup_charge_statistics(from, page, compound, -nr_pages); + memcg_check_events(from, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + out_unlock: + unlock_page(page); + out: +@@ -5637,10 +5640,10 @@ void mem_cgroup_commit_charge(struct pag + + commit_charge(page, memcg, lrucare); + +- local_irq_disable(); ++ local_lock_irq(event_lock); + mem_cgroup_charge_statistics(memcg, page, compound, nr_pages); + memcg_check_events(memcg, page); +- local_irq_enable(); ++ local_unlock_irq(event_lock); + + if (do_memsw_account() && PageSwapCache(page)) { + swp_entry_t entry = { .val = page_private(page) }; +@@ -5709,7 +5712,7 @@ static void uncharge_batch(const struct + memcg_oom_recover(ug->memcg); + } + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + __mod_memcg_state(ug->memcg, MEMCG_RSS, -ug->nr_anon); + __mod_memcg_state(ug->memcg, MEMCG_CACHE, -ug->nr_file); + __mod_memcg_state(ug->memcg, MEMCG_RSS_HUGE, -ug->nr_huge); +@@ -5717,7 +5720,7 @@ static void uncharge_batch(const struct + __count_memcg_events(ug->memcg, PGPGOUT, ug->pgpgout); + __this_cpu_add(ug->memcg->stat_cpu->nr_page_events, nr_pages); + memcg_check_events(ug->memcg, ug->dummy_page); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + + if (!mem_cgroup_is_root(ug->memcg)) + css_put_many(&ug->memcg->css, nr_pages); +@@ -5880,10 +5883,10 @@ void mem_cgroup_migrate(struct page *old + + commit_charge(newpage, memcg, false); + +- local_irq_save(flags); ++ local_lock_irqsave(event_lock, flags); + mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); + memcg_check_events(memcg, newpage); +- local_irq_restore(flags); ++ local_unlock_irqrestore(event_lock, flags); + } + + DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); +@@ -6075,6 +6078,7 @@ void mem_cgroup_swapout(struct page *pag + struct mem_cgroup *memcg, *swap_memcg; + unsigned int nr_entries; + unsigned short oldid; ++ unsigned long flags; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); +@@ -6120,13 +6124,17 @@ void mem_cgroup_swapout(struct page *pag + * important here to have the interrupts disabled because it is the + * only synchronisation we have for updating the per-CPU variables. + */ ++ local_lock_irqsave(event_lock, flags); ++#ifndef CONFIG_PREEMPT_RT_BASE + VM_BUG_ON(!irqs_disabled()); ++#endif + mem_cgroup_charge_statistics(memcg, page, PageTransHuge(page), + -nr_entries); + memcg_check_events(memcg, page); + + if (!mem_cgroup_is_root(memcg)) + css_put_many(&memcg->css, nr_entries); ++ local_unlock_irqrestore(event_lock, flags); + } + + /** diff --git a/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch b/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch new file mode 100644 index 000000000..2d2ac92c6 --- /dev/null +++ b/debian/patches/features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch @@ -0,0 +1,233 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:37 -0500 +Subject: mm: page_alloc: rt-friendly per-cpu pages +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +rt-friendly per-cpu pages: convert the irqs-off per-cpu locking +method into a preemptible, explicit-per-cpu-locks method. + +Contains fixes from: + Peter Zijlstra + Thomas Gleixner + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +--- + mm/page_alloc.c | 63 ++++++++++++++++++++++++++++++++++++++------------------ + 1 file changed, 43 insertions(+), 20 deletions(-) + +--- a/mm/page_alloc.c ++++ b/mm/page_alloc.c +@@ -61,6 +61,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -291,6 +292,18 @@ EXPORT_SYMBOL(nr_node_ids); + EXPORT_SYMBOL(nr_online_nodes); + #endif + ++static DEFINE_LOCAL_IRQ_LOCK(pa_lock); ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define cpu_lock_irqsave(cpu, flags) \ ++ local_lock_irqsave_on(pa_lock, flags, cpu) ++# define cpu_unlock_irqrestore(cpu, flags) \ ++ local_unlock_irqrestore_on(pa_lock, flags, cpu) ++#else ++# define cpu_lock_irqsave(cpu, flags) local_irq_save(flags) ++# define cpu_unlock_irqrestore(cpu, flags) local_irq_restore(flags) ++#endif ++ + int page_group_by_mobility_disabled __read_mostly; + + #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT +@@ -1268,10 +1281,10 @@ static void __free_pages_ok(struct page + return; + + migratetype = get_pfnblock_migratetype(page, pfn); +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + __count_vm_events(PGFREE, 1 << order); + free_one_page(page_zone(page), page, pfn, order, migratetype); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + static void __init __free_pages_boot_core(struct page *page, unsigned int order) +@@ -2539,13 +2552,13 @@ void drain_zone_pages(struct zone *zone, + int to_drain, batch; + LIST_HEAD(dst); + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + batch = READ_ONCE(pcp->batch); + to_drain = min(pcp->count, batch); + if (to_drain > 0) + isolate_pcp_pages(to_drain, pcp, &dst); + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + if (to_drain > 0) + free_pcppages_bulk(zone, &dst, false); +@@ -2567,7 +2580,7 @@ static void drain_pages_zone(unsigned in + LIST_HEAD(dst); + int count; + +- local_irq_save(flags); ++ cpu_lock_irqsave(cpu, flags); + pset = per_cpu_ptr(zone->pageset, cpu); + + pcp = &pset->pcp; +@@ -2575,7 +2588,7 @@ static void drain_pages_zone(unsigned in + if (count) + isolate_pcp_pages(count, pcp, &dst); + +- local_irq_restore(flags); ++ cpu_unlock_irqrestore(cpu, flags); + + if (count) + free_pcppages_bulk(zone, &dst, false); +@@ -2613,6 +2626,7 @@ void drain_local_pages(struct zone *zone + drain_pages(cpu); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + static void drain_local_pages_wq(struct work_struct *work) + { + /* +@@ -2626,6 +2640,7 @@ static void drain_local_pages_wq(struct + drain_local_pages(NULL); + preempt_enable(); + } ++#endif + + /* + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. +@@ -2692,7 +2707,14 @@ void drain_all_pages(struct zone *zone) + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++ for_each_cpu(cpu, &cpus_with_pcps) { ++ if (zone) ++ drain_pages_zone(cpu, zone); ++ else ++ drain_pages(cpu); ++ } ++#else + for_each_cpu(cpu, &cpus_with_pcps) { + struct work_struct *work = per_cpu_ptr(&pcpu_drain, cpu); + INIT_WORK(work, drain_local_pages_wq); +@@ -2700,6 +2722,7 @@ void drain_all_pages(struct zone *zone) + } + for_each_cpu(cpu, &cpus_with_pcps) + flush_work(per_cpu_ptr(&pcpu_drain, cpu)); ++#endif + + mutex_unlock(&pcpu_drain_mutex); + } +@@ -2819,9 +2842,9 @@ void free_unref_page(struct page *page) + if (!free_unref_page_prepare(page, pfn)) + return; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + free_unref_page_commit(page, pfn, &dst); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + if (!list_empty(&dst)) + free_pcppages_bulk(zone, &dst, false); + } +@@ -2848,7 +2871,7 @@ void free_unref_page_list(struct list_he + set_page_private(page, pfn); + } + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + list_for_each_entry_safe(page, next, list, lru) { + unsigned long pfn = page_private(page); + enum zone_type type; +@@ -2863,12 +2886,12 @@ void free_unref_page_list(struct list_he + * a large list of pages to free. + */ + if (++batch_count == SWAP_CLUSTER_MAX) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + batch_count = 0; +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + } + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + for (i = 0; i < __MAX_NR_ZONES; ) { + struct page *page; +@@ -3017,7 +3040,7 @@ static struct page *rmqueue_pcplist(stru + struct page *page; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + pcp = &this_cpu_ptr(zone->pageset)->pcp; + list = &pcp->lists[migratetype]; + page = __rmqueue_pcplist(zone, migratetype, pcp, list); +@@ -3025,7 +3048,7 @@ static struct page *rmqueue_pcplist(stru + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return page; + } + +@@ -3052,7 +3075,7 @@ struct page *rmqueue(struct zone *prefer + * allocate greater than order-1 page units with __GFP_NOFAIL. + */ + WARN_ON_ONCE((gfp_flags & __GFP_NOFAIL) && (order > 1)); +- spin_lock_irqsave(&zone->lock, flags); ++ local_spin_lock_irqsave(pa_lock, &zone->lock, flags); + + do { + page = NULL; +@@ -3072,14 +3095,14 @@ struct page *rmqueue(struct zone *prefer + + __count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order); + zone_statistics(preferred_zone, zone); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + + out: + VM_BUG_ON_PAGE(page && bad_range(zone, page), page); + return page; + + failed: +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + return NULL; + } + +@@ -7999,7 +8022,7 @@ void zone_pcp_reset(struct zone *zone) + struct per_cpu_pageset *pset; + + /* avoid races with drain_pages() */ +- local_irq_save(flags); ++ local_lock_irqsave(pa_lock, flags); + if (zone->pageset != &boot_pageset) { + for_each_online_cpu(cpu) { + pset = per_cpu_ptr(zone->pageset, cpu); +@@ -8008,7 +8031,7 @@ void zone_pcp_reset(struct zone *zone) + free_percpu(zone->pageset); + zone->pageset = &boot_pageset; + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(pa_lock, flags); + } + + #ifdef CONFIG_MEMORY_HOTREMOVE diff --git a/debian/patches/features/all/rt/mm-perform-lru_add_drain_all-remotely.patch b/debian/patches/features/all/rt/mm-perform-lru_add_drain_all-remotely.patch new file mode 100644 index 000000000..12c74d47b --- /dev/null +++ b/debian/patches/features/all/rt/mm-perform-lru_add_drain_all-remotely.patch @@ -0,0 +1,103 @@ +From: Luiz Capitulino +Date: Fri, 27 May 2016 15:03:28 +0200 +Subject: [PATCH] mm: perform lru_add_drain_all() remotely +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +lru_add_drain_all() works by scheduling lru_add_drain_cpu() to run +on all CPUs that have non-empty LRU pagevecs and then waiting for +the scheduled work to complete. However, workqueue threads may never +have the chance to run on a CPU that's running a SCHED_FIFO task. +This causes lru_add_drain_all() to block forever. + +This commit solves this problem by changing lru_add_drain_all() +to drain the LRU pagevecs of remote CPUs. This is done by grabbing +swapvec_lock and calling lru_add_drain_cpu(). + +PS: This is based on an idea and initial implementation by + Rik van Riel. + +Signed-off-by: Rik van Riel +Signed-off-by: Luiz Capitulino +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/swap.c | 36 ++++++++++++++++++++++++++++++------ + 1 file changed, 30 insertions(+), 6 deletions(-) + +--- a/mm/swap.c ++++ b/mm/swap.c +@@ -590,9 +590,15 @@ void lru_add_drain_cpu(int cpu) + unsigned long flags; + + /* No harm done if a racing interrupt already did this */ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ local_lock_irqsave_on(rotate_lock, flags, cpu); ++ pagevec_move_tail(pvec); ++ local_unlock_irqrestore_on(rotate_lock, flags, cpu); ++#else + local_lock_irqsave(rotate_lock, flags); + pagevec_move_tail(pvec); + local_unlock_irqrestore(rotate_lock, flags); ++#endif + } + + pvec = &per_cpu(lru_deactivate_file_pvecs, cpu); +@@ -660,6 +666,16 @@ void lru_add_drain(void) + local_unlock_cpu(swapvec_lock); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ local_lock_on(swapvec_lock, cpu); ++ lru_add_drain_cpu(cpu); ++ local_unlock_on(swapvec_lock, cpu); ++} ++ ++#else ++ + static void lru_add_drain_per_cpu(struct work_struct *dummy) + { + lru_add_drain(); +@@ -667,6 +683,16 @@ static void lru_add_drain_per_cpu(struct + + static DEFINE_PER_CPU(struct work_struct, lru_add_drain_work); + ++static inline void remote_lru_add_drain(int cpu, struct cpumask *has_work) ++{ ++ struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); ++ ++ INIT_WORK(work, lru_add_drain_per_cpu); ++ queue_work_on(cpu, mm_percpu_wq, work); ++ cpumask_set_cpu(cpu, has_work); ++} ++#endif ++ + /* + * Doesn't need any cpu hotplug locking because we do rely on per-cpu + * kworkers being shut down before our page_alloc_cpu_dead callback is +@@ -691,21 +717,19 @@ void lru_add_drain_all(void) + cpumask_clear(&has_work); + + for_each_online_cpu(cpu) { +- struct work_struct *work = &per_cpu(lru_add_drain_work, cpu); + + if (pagevec_count(&per_cpu(lru_add_pvec, cpu)) || + pagevec_count(&per_cpu(lru_rotate_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_deactivate_file_pvecs, cpu)) || + pagevec_count(&per_cpu(lru_lazyfree_pvecs, cpu)) || +- need_activate_page_drain(cpu)) { +- INIT_WORK(work, lru_add_drain_per_cpu); +- queue_work_on(cpu, mm_percpu_wq, work); +- cpumask_set_cpu(cpu, &has_work); +- } ++ need_activate_page_drain(cpu)) ++ remote_lru_add_drain(cpu, &has_work); + } + ++#ifndef CONFIG_PREEMPT_RT_BASE + for_each_cpu(cpu, &has_work) + flush_work(&per_cpu(lru_add_drain_work, cpu)); ++#endif + + mutex_unlock(&lock); + } diff --git a/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch b/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch new file mode 100644 index 000000000..941ece7f5 --- /dev/null +++ b/debian/patches/features/all/rt/mm-protect-activate-switch-mm.patch @@ -0,0 +1,72 @@ +From: Yong Zhang +Date: Tue, 15 May 2012 13:53:56 +0800 +Subject: mm: Protect activate_mm() by preempt_[disable&enable]_rt() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +User preempt_*_rt instead of local_irq_*_rt or otherwise there will be +warning on ARM like below: + +WARNING: at build/linux/kernel/smp.c:459 smp_call_function_many+0x98/0x264() +Modules linked in: +[] (unwind_backtrace+0x0/0xe4) from [] (warn_slowpath_common+0x4c/0x64) +[] (warn_slowpath_common+0x4c/0x64) from [] (warn_slowpath_null+0x18/0x1c) +[] (warn_slowpath_null+0x18/0x1c) from [](smp_call_function_many+0x98/0x264) +[] (smp_call_function_many+0x98/0x264) from [] (smp_call_function+0x44/0x6c) +[] (smp_call_function+0x44/0x6c) from [] (__new_context+0xbc/0x124) +[] (__new_context+0xbc/0x124) from [] (flush_old_exec+0x460/0x5e4) +[] (flush_old_exec+0x460/0x5e4) from [] (load_elf_binary+0x2e0/0x11ac) +[] (load_elf_binary+0x2e0/0x11ac) from [] (search_binary_handler+0x94/0x2a4) +[] (search_binary_handler+0x94/0x2a4) from [] (do_execve+0x254/0x364) +[] (do_execve+0x254/0x364) from [] (sys_execve+0x34/0x54) +[] (sys_execve+0x34/0x54) from [] (ret_fast_syscall+0x0/0x30) +---[ end trace 0000000000000002 ]--- + +The reason is that ARM need irq enabled when doing activate_mm(). +According to mm-protect-activate-switch-mm.patch, actually +preempt_[disable|enable]_rt() is sufficient. + +Inspired-by: Steven Rostedt +Signed-off-by: Yong Zhang +Cc: Steven Rostedt +Link: http://lkml.kernel.org/r/1337061236-1766-1-git-send-email-yong.zhang0@gmail.com +Signed-off-by: Thomas Gleixner +--- + fs/exec.c | 2 ++ + mm/mmu_context.c | 2 ++ + 2 files changed, 4 insertions(+) + +--- a/fs/exec.c ++++ b/fs/exec.c +@@ -1028,12 +1028,14 @@ static int exec_mmap(struct mm_struct *m + } + } + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + tsk->mm = mm; + tsk->active_mm = mm; + activate_mm(active_mm, mm); + tsk->mm->vmacache_seqnum = 0; + vmacache_flush(tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + if (old_mm) { + up_read(&old_mm->mmap_sem); +--- a/mm/mmu_context.c ++++ b/mm/mmu_context.c +@@ -25,6 +25,7 @@ void use_mm(struct mm_struct *mm) + struct task_struct *tsk = current; + + task_lock(tsk); ++ preempt_disable_rt(); + active_mm = tsk->active_mm; + if (active_mm != mm) { + mmgrab(mm); +@@ -32,6 +33,7 @@ void use_mm(struct mm_struct *mm) + } + tsk->mm = mm; + switch_mm(active_mm, mm, tsk); ++ preempt_enable_rt(); + task_unlock(tsk); + #ifdef finish_arch_post_lock_switch + finish_arch_post_lock_switch(); diff --git a/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch b/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch new file mode 100644 index 000000000..124fcfde3 --- /dev/null +++ b/debian/patches/features/all/rt/mm-rt-kmap-atomic-scheduling.patch @@ -0,0 +1,307 @@ +Subject: mm, rt: kmap_atomic scheduling +From: Peter Zijlstra +Date: Thu, 28 Jul 2011 10:43:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In fact, with migrate_disable() existing one could play games with +kmap_atomic. You could save/restore the kmap_atomic slots on context +switch (if there are any in use of course), this should be esp easy now +that we have a kmap_atomic stack. + +Something like the below.. it wants replacing all the preempt_disable() +stuff with pagefault_disable() && migrate_disable() of course, but then +you can flip kmaps around like below. + +Signed-off-by: Peter Zijlstra +[dvhart@linux.intel.com: build fix] +Link: http://lkml.kernel.org/r/1311842631.5890.208.camel@twins + +[tglx@linutronix.de: Get rid of the per cpu variable and store the idx + and the pte content right away in the task struct. + Shortens the context switch code. ] +--- + arch/x86/kernel/process_32.c | 32 ++++++++++++++++++++++++++++++++ + arch/x86/mm/highmem_32.c | 13 ++++++++++--- + arch/x86/mm/iomap_32.c | 9 ++++++++- + include/linux/highmem.h | 31 +++++++++++++++++++++++++------ + include/linux/sched.h | 7 +++++++ + include/linux/uaccess.h | 2 ++ + mm/highmem.c | 6 ++++-- + 7 files changed, 88 insertions(+), 12 deletions(-) + +--- a/arch/x86/kernel/process_32.c ++++ b/arch/x86/kernel/process_32.c +@@ -38,6 +38,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -196,6 +197,35 @@ start_thread(struct pt_regs *regs, unsig + } + EXPORT_SYMBOL_GPL(start_thread); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) ++{ ++ int i; ++ ++ /* ++ * Clear @prev's kmap_atomic mappings ++ */ ++ for (i = 0; i < prev_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ pte_t *ptep = kmap_pte - idx; ++ ++ kpte_clear_flush(ptep, __fix_to_virt(FIX_KMAP_BEGIN + idx)); ++ } ++ /* ++ * Restore @next_p's kmap_atomic mappings ++ */ ++ for (i = 0; i < next_p->kmap_idx; i++) { ++ int idx = i + KM_TYPE_NR * smp_processor_id(); ++ ++ if (!pte_none(next_p->kmap_pte[i])) ++ set_pte(kmap_pte - idx, next_p->kmap_pte[i]); ++ } ++} ++#else ++static inline void ++switch_kmaps(struct task_struct *prev_p, struct task_struct *next_p) { } ++#endif ++ + + /* + * switch_to(x,y) should switch tasks from x to y. +@@ -271,6 +301,8 @@ EXPORT_SYMBOL_GPL(start_thread); + task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT)) + __switch_to_xtra(prev_p, next_p, tss); + ++ switch_kmaps(prev_p, next_p); ++ + /* + * Leave lazy mode, flushing any hypercalls made here. + * This must be done before restoring TLS segments so +--- a/arch/x86/mm/highmem_32.c ++++ b/arch/x86/mm/highmem_32.c +@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap); + */ + void *kmap_atomic_prot(struct page *page, pgprot_t prot) + { ++ pte_t pte = mk_pte(page, prot); + unsigned long vaddr; + int idx, type; + +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + + if (!PageHighMem(page)) +@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page + idx = type + KM_TYPE_NR*smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + BUG_ON(!pte_none(*(kmap_pte-idx))); +- set_pte(kmap_pte-idx, mk_pte(page, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte-idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -88,6 +92,9 @@ void __kunmap_atomic(void *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + arch_flush_lazy_mmu_mode(); +@@ -100,7 +107,7 @@ void __kunmap_atomic(void *kvaddr) + #endif + + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + EXPORT_SYMBOL(__kunmap_atomic); + +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -59,6 +59,7 @@ EXPORT_SYMBOL_GPL(iomap_free); + + void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot) + { ++ pte_t pte = pfn_pte(pfn, prot); + unsigned long vaddr; + int idx, type; + +@@ -68,7 +69,10 @@ void *kmap_atomic_prot_pfn(unsigned long + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); +- set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = pte; ++#endif ++ set_pte(kmap_pte - idx, pte); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +@@ -119,6 +123,9 @@ iounmap_atomic(void __iomem *kvaddr) + * is a bad idea also, in case the page changes cacheability + * attributes or becomes a protected page in a hypervisor. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ current->kmap_pte[type] = __pte(0); ++#endif + kpte_clear_flush(kmap_pte-idx, vaddr); + kmap_atomic_idx_pop(); + } +--- a/include/linux/highmem.h ++++ b/include/linux/highmem.h +@@ -66,7 +66,7 @@ static inline void kunmap(struct page *p + + static inline void *kmap_atomic(struct page *page) + { +- preempt_disable(); ++ preempt_disable_nort(); + pagefault_disable(); + return page_address(page); + } +@@ -75,7 +75,7 @@ static inline void *kmap_atomic(struct p + static inline void __kunmap_atomic(void *addr) + { + pagefault_enable(); +- preempt_enable(); ++ preempt_enable_nort(); + } + + #define kmap_atomic_pfn(pfn) kmap_atomic(pfn_to_page(pfn)) +@@ -87,32 +87,51 @@ static inline void __kunmap_atomic(void + + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + ++#ifndef CONFIG_PREEMPT_RT_FULL + DECLARE_PER_CPU(int, __kmap_atomic_idx); ++#endif + + static inline int kmap_atomic_idx_push(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1; + +-#ifdef CONFIG_DEBUG_HIGHMEM ++# ifdef CONFIG_DEBUG_HIGHMEM + WARN_ON_ONCE(in_irq() && !irqs_disabled()); + BUG_ON(idx >= KM_TYPE_NR); +-#endif ++# endif + return idx; ++#else ++ current->kmap_idx++; ++ BUG_ON(current->kmap_idx > KM_TYPE_NR); ++ return current->kmap_idx - 1; ++#endif + } + + static inline int kmap_atomic_idx(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + return __this_cpu_read(__kmap_atomic_idx) - 1; ++#else ++ return current->kmap_idx - 1; ++#endif + } + + static inline void kmap_atomic_idx_pop(void) + { +-#ifdef CONFIG_DEBUG_HIGHMEM ++#ifndef CONFIG_PREEMPT_RT_FULL ++# ifdef CONFIG_DEBUG_HIGHMEM + int idx = __this_cpu_dec_return(__kmap_atomic_idx); + + BUG_ON(idx < 0); +-#else ++# else + __this_cpu_dec(__kmap_atomic_idx); ++# endif ++#else ++ current->kmap_idx--; ++# ifdef CONFIG_DEBUG_HIGHMEM ++ BUG_ON(current->kmap_idx < 0); ++# endif + #endif + } + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -28,6 +28,7 @@ + #include + #include + #include ++#include + + /* task_struct member predeclarations (sorted alphabetically): */ + struct audit_context; +@@ -1193,6 +1194,12 @@ struct task_struct { + int softirq_nestcnt; + unsigned int softirqs_raised; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++# if defined CONFIG_HIGHMEM || defined CONFIG_X86_32 ++ int kmap_idx; ++ pte_t kmap_pte[KM_TYPE_NR]; ++# endif ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +--- a/include/linux/uaccess.h ++++ b/include/linux/uaccess.h +@@ -185,6 +185,7 @@ static __always_inline void pagefault_di + */ + static inline void pagefault_disable(void) + { ++ migrate_disable(); + pagefault_disabled_inc(); + /* + * make sure to have issued the store before a pagefault +@@ -201,6 +202,7 @@ static inline void pagefault_enable(void + */ + barrier(); + pagefault_disabled_dec(); ++ migrate_enable(); + } + + /* +--- a/mm/highmem.c ++++ b/mm/highmem.c +@@ -30,10 +30,11 @@ + #include + #include + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + #if defined(CONFIG_HIGHMEM) || defined(CONFIG_X86_32) + DEFINE_PER_CPU(int, __kmap_atomic_idx); + #endif ++#endif + + /* + * Virtual_count is not a pure "count". +@@ -108,8 +109,9 @@ static inline wait_queue_head_t *get_pkm + unsigned long totalhigh_pages __read_mostly; + EXPORT_SYMBOL(totalhigh_pages); + +- ++#ifndef CONFIG_PREEMPT_RT_FULL + EXPORT_PER_CPU_SYMBOL(__kmap_atomic_idx); ++#endif + + unsigned int nr_free_highpages (void) + { diff --git a/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch b/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch new file mode 100644 index 000000000..10d188d28 --- /dev/null +++ b/debian/patches/features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch @@ -0,0 +1,24 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:44:34 -0500 +Subject: mm/scatterlist: Do not disable irqs on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +For -RT it is enough to keep pagefault disabled (which is currently handled by +kmap_atomic()). + +Signed-off-by: Thomas Gleixner +--- + lib/scatterlist.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/lib/scatterlist.c ++++ b/lib/scatterlist.c +@@ -776,7 +776,7 @@ void sg_miter_stop(struct sg_mapping_ite + flush_kernel_dcache_page(miter->page); + + if (miter->__flags & SG_MITER_ATOMIC) { +- WARN_ON_ONCE(preemptible()); ++ WARN_ON_ONCE(!pagefault_disabled()); + kunmap_atomic(miter->addr); + } else + kunmap(miter->page); diff --git a/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch b/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch new file mode 100644 index 000000000..655f4b165 --- /dev/null +++ b/debian/patches/features/all/rt/mm-vmalloc-use-get-cpu-light.patch @@ -0,0 +1,66 @@ +Subject: mm/vmalloc: Another preempt disable region which sucks +From: Thomas Gleixner +Date: Tue, 12 Jul 2011 11:39:36 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Avoid the preempt disable version of get_cpu_var(). The inner-lock should +provide enough serialisation. + +Signed-off-by: Thomas Gleixner +--- + mm/vmalloc.c | 13 ++++++++----- + 1 file changed, 8 insertions(+), 5 deletions(-) + +--- a/mm/vmalloc.c ++++ b/mm/vmalloc.c +@@ -848,7 +848,7 @@ static void *new_vmap_block(unsigned int + struct vmap_block *vb; + struct vmap_area *va; + unsigned long vb_idx; +- int node, err; ++ int node, err, cpu; + void *vaddr; + + node = numa_node_id(); +@@ -891,11 +891,12 @@ static void *new_vmap_block(unsigned int + BUG_ON(err); + radix_tree_preload_end(); + +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + spin_lock(&vbq->lock); + list_add_tail_rcu(&vb->free_list, &vbq->free); + spin_unlock(&vbq->lock); +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + + return vaddr; + } +@@ -964,6 +965,7 @@ static void *vb_alloc(unsigned long size + struct vmap_block *vb; + void *vaddr = NULL; + unsigned int order; ++ int cpu; + + BUG_ON(offset_in_page(size)); + BUG_ON(size > PAGE_SIZE*VMAP_MAX_ALLOC); +@@ -978,7 +980,8 @@ static void *vb_alloc(unsigned long size + order = get_order(size); + + rcu_read_lock(); +- vbq = &get_cpu_var(vmap_block_queue); ++ cpu = get_cpu_light(); ++ vbq = this_cpu_ptr(&vmap_block_queue); + list_for_each_entry_rcu(vb, &vbq->free, free_list) { + unsigned long pages_off; + +@@ -1001,7 +1004,7 @@ static void *vb_alloc(unsigned long size + break; + } + +- put_cpu_var(vmap_block_queue); ++ put_cpu_light(); + rcu_read_unlock(); + + /* Allocate new block if nothing was found */ diff --git a/debian/patches/features/all/rt/mm_zsmalloc_copy_with_get_cpu_var_and_locking.patch b/debian/patches/features/all/rt/mm_zsmalloc_copy_with_get_cpu_var_and_locking.patch new file mode 100644 index 000000000..bb4eb1a9f --- /dev/null +++ b/debian/patches/features/all/rt/mm_zsmalloc_copy_with_get_cpu_var_and_locking.patch @@ -0,0 +1,197 @@ +From: Mike Galbraith +Date: Tue, 22 Mar 2016 11:16:09 +0100 +Subject: [PATCH] mm/zsmalloc: copy with get_cpu_var() and locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +get_cpu_var() disables preemption and triggers a might_sleep() splat later. +This is replaced with get_locked_var(). +This bitspinlocks are replaced with a proper mutex which requires a slightly +larger struct to allocate. + +Signed-off-by: Mike Galbraith +[bigeasy: replace the bitspin_lock() with a mutex, get_locked_var(). Mike then +fixed the size magic] +Signed-off-by: Sebastian Andrzej Siewior +--- + mm/zsmalloc.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++++++----- + 1 file changed, 74 insertions(+), 6 deletions(-) + +--- a/mm/zsmalloc.c ++++ b/mm/zsmalloc.c +@@ -55,6 +55,7 @@ + #include + #include + #include ++#include + + #define ZSPAGE_MAGIC 0x58 + +@@ -72,9 +73,22 @@ + */ + #define ZS_MAX_ZSPAGE_ORDER 2 + #define ZS_MAX_PAGES_PER_ZSPAGE (_AC(1, UL) << ZS_MAX_ZSPAGE_ORDER) +- + #define ZS_HANDLE_SIZE (sizeof(unsigned long)) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct zsmalloc_handle { ++ unsigned long addr; ++ struct mutex lock; ++}; ++ ++#define ZS_HANDLE_ALLOC_SIZE (sizeof(struct zsmalloc_handle)) ++ ++#else ++ ++#define ZS_HANDLE_ALLOC_SIZE (sizeof(unsigned long)) ++#endif ++ + /* + * Object location (, ) is encoded as + * as single (unsigned long) handle value. +@@ -320,7 +334,7 @@ static void SetZsPageMovable(struct zs_p + + static int create_cache(struct zs_pool *pool) + { +- pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_SIZE, ++ pool->handle_cachep = kmem_cache_create("zs_handle", ZS_HANDLE_ALLOC_SIZE, + 0, 0, NULL); + if (!pool->handle_cachep) + return 1; +@@ -344,10 +358,27 @@ static void destroy_cache(struct zs_pool + + static unsigned long cache_alloc_handle(struct zs_pool *pool, gfp_t gfp) + { +- return (unsigned long)kmem_cache_alloc(pool->handle_cachep, +- gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); ++ void *p; ++ ++ p = kmem_cache_alloc(pool->handle_cachep, ++ gfp & ~(__GFP_HIGHMEM|__GFP_MOVABLE)); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (p) { ++ struct zsmalloc_handle *zh = p; ++ ++ mutex_init(&zh->lock); ++ } ++#endif ++ return (unsigned long)p; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct zsmalloc_handle *zs_get_pure_handle(unsigned long handle) ++{ ++ return (void *)(handle &~((1 << OBJ_TAG_BITS) - 1)); ++} ++#endif ++ + static void cache_free_handle(struct zs_pool *pool, unsigned long handle) + { + kmem_cache_free(pool->handle_cachep, (void *)handle); +@@ -366,12 +397,18 @@ static void cache_free_zspage(struct zs_ + + static void record_obj(unsigned long handle, unsigned long obj) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ WRITE_ONCE(zh->addr, obj); ++#else + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); ++#endif + } + + /* zpool driver */ +@@ -453,6 +490,7 @@ MODULE_ALIAS("zpool-zsmalloc"); + + /* per-cpu VM mapping areas for zspage accesses that cross page boundaries */ + static DEFINE_PER_CPU(struct mapping_area, zs_map_area); ++static DEFINE_LOCAL_IRQ_LOCK(zs_map_area_lock); + + static bool is_zspage_isolated(struct zspage *zspage) + { +@@ -882,7 +920,13 @@ static unsigned long location_to_obj(str + + static unsigned long handle_to_obj(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return zh->addr; ++#else + return *(unsigned long *)handle; ++#endif + } + + static unsigned long obj_to_head(struct page *page, void *obj) +@@ -896,22 +940,46 @@ static unsigned long obj_to_head(struct + + static inline int testpin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_is_locked(&zh->lock); ++#else + return bit_spin_is_locked(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static inline int trypin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_trylock(&zh->lock); ++#else + return bit_spin_trylock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void pin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_lock(&zh->lock); ++#else + bit_spin_lock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void unpin_tag(unsigned long handle) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct zsmalloc_handle *zh = zs_get_pure_handle(handle); ++ ++ return mutex_unlock(&zh->lock); ++#else + bit_spin_unlock(HANDLE_PIN_BIT, (unsigned long *)handle); ++#endif + } + + static void reset_page(struct page *page) +@@ -1350,7 +1418,7 @@ void *zs_map_object(struct zs_pool *pool + class = pool->size_class[class_idx]; + off = (class->size * obj_idx) & ~PAGE_MASK; + +- area = &get_cpu_var(zs_map_area); ++ area = &get_locked_var(zs_map_area_lock, zs_map_area); + area->vm_mm = mm; + if (off + class->size <= PAGE_SIZE) { + /* this object is contained entirely within a page */ +@@ -1404,7 +1472,7 @@ void zs_unmap_object(struct zs_pool *poo + + __zs_unmap_object(area, pages, off, class->size); + } +- put_cpu_var(zs_map_area); ++ put_locked_var(zs_map_area_lock, zs_map_area); + + migrate_read_unlock(zspage); + unpin_tag(handle); diff --git a/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch b/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch new file mode 100644 index 000000000..813f87f73 --- /dev/null +++ b/debian/patches/features/all/rt/mutex-no-spin-on-rt.patch @@ -0,0 +1,29 @@ +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:51:45 +0200 +Subject: locking: Disable spin on owner for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Drop spin on owner for mutex / rwsem. We are most likely not using it +but… + +Signed-off-by: Thomas Gleixner +--- + kernel/Kconfig.locks | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/kernel/Kconfig.locks ++++ b/kernel/Kconfig.locks +@@ -225,11 +225,11 @@ config ARCH_SUPPORTS_ATOMIC_RMW + + config MUTEX_SPIN_ON_OWNER + def_bool y +- depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config RWSEM_SPIN_ON_OWNER + def_bool y +- depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW ++ depends on SMP && RWSEM_XCHGADD_ALGORITHM && ARCH_SUPPORTS_ATOMIC_RMW && !PREEMPT_RT_FULL + + config LOCK_SPIN_ON_OWNER + def_bool y diff --git a/debian/patches/features/all/rt/net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch b/debian/patches/features/all/rt/net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch new file mode 100644 index 000000000..487964c2b --- /dev/null +++ b/debian/patches/features/all/rt/net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch @@ -0,0 +1,69 @@ +From: Steven Rostedt +Date: Tue, 6 Dec 2016 17:50:30 -0500 +Subject: [PATCH] net: Have __napi_schedule_irqoff() disable interrupts on + RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +A customer hit a crash where the napi sd->poll_list became corrupted. +The customer had the bnx2x driver, which does a +__napi_schedule_irqoff() in its interrupt handler. Unfortunately, when +running with CONFIG_PREEMPT_RT_FULL, this interrupt handler is run as a +thread and is preemptable. The call to ____napi_schedule() must be done +with interrupts disabled to protect the per cpu softnet_data's +"poll_list, which is protected by disabling interrupts (disabling +preemption is enough when all interrupts are threaded and +local_bh_disable() can't preempt)." + +As bnx2x isn't the only driver that does this, the safest thing to do +is to make __napi_schedule_irqoff() call __napi_schedule() instead when +CONFIG_PREEMPT_RT_FULL is enabled, which will call local_irq_save() +before calling ____napi_schedule(). + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Steven Rostedt (Red Hat) +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/netdevice.h | 12 ++++++++++++ + net/core/dev.c | 2 ++ + 2 files changed, 14 insertions(+) + +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -411,7 +411,19 @@ typedef enum rx_handler_result rx_handle + typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); + + void __napi_schedule(struct napi_struct *n); ++ ++/* ++ * When PREEMPT_RT_FULL is defined, all device interrupt handlers ++ * run as threads, and they can also be preempted (without PREEMPT_RT ++ * interrupt threads can not be preempted). Which means that calling ++ * __napi_schedule_irqoff() from an interrupt handler can be preempted ++ * and can corrupt the napi->poll_list. ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define __napi_schedule_irqoff(n) __napi_schedule(n) ++#else + void __napi_schedule_irqoff(struct napi_struct *n); ++#endif + + static inline bool napi_disable_pending(struct napi_struct *n) + { +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -5470,6 +5470,7 @@ bool napi_schedule_prep(struct napi_stru + } + EXPORT_SYMBOL(napi_schedule_prep); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * __napi_schedule_irqoff - schedule for receive + * @n: entry to schedule +@@ -5481,6 +5482,7 @@ void __napi_schedule_irqoff(struct napi_ + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + } + EXPORT_SYMBOL(__napi_schedule_irqoff); ++#endif + + bool napi_complete_done(struct napi_struct *n, int work_done) + { diff --git a/debian/patches/features/all/rt/net-Qdisc-use-a-seqlock-instead-seqcount.patch b/debian/patches/features/all/rt/net-Qdisc-use-a-seqlock-instead-seqcount.patch new file mode 100644 index 000000000..1f5986774 --- /dev/null +++ b/debian/patches/features/all/rt/net-Qdisc-use-a-seqlock-instead-seqcount.patch @@ -0,0 +1,272 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 14 Sep 2016 17:36:35 +0200 +Subject: [PATCH] net/Qdisc: use a seqlock instead seqcount +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The seqcount disables preemption on -RT while it is held which can't +remove. Also we don't want the reader to spin for ages if the writer is +scheduled out. The seqlock on the other hand will serialize / sleep on +the lock while writer is active. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/seqlock.h | 9 +++++++++ + include/net/gen_stats.h | 9 +++++---- + include/net/net_seq_lock.h | 15 +++++++++++++++ + include/net/sch_generic.h | 19 +++++++++++++++++-- + net/core/gen_estimator.c | 6 +++--- + net/core/gen_stats.c | 8 ++++---- + net/sched/sch_api.c | 2 +- + net/sched/sch_generic.c | 12 ++++++++++++ + 8 files changed, 66 insertions(+), 14 deletions(-) + create mode 100644 include/net/net_seq_lock.h + +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -482,6 +482,15 @@ static inline void write_seqlock(seqlock + __raw_write_seqcount_begin(&sl->seqcount); + } + ++static inline int try_write_seqlock(seqlock_t *sl) ++{ ++ if (spin_trylock(&sl->lock)) { ++ __raw_write_seqcount_begin(&sl->seqcount); ++ return 1; ++ } ++ return 0; ++} ++ + static inline void write_sequnlock(seqlock_t *sl) + { + __raw_write_seqcount_end(&sl->seqcount); +--- a/include/net/gen_stats.h ++++ b/include/net/gen_stats.h +@@ -6,6 +6,7 @@ + #include + #include + #include ++#include + + struct gnet_stats_basic_cpu { + struct gnet_stats_basic_packed bstats; +@@ -36,11 +37,11 @@ int gnet_stats_start_copy_compat(struct + spinlock_t *lock, struct gnet_dump *d, + int padattr); + +-int gnet_stats_copy_basic(const seqcount_t *running, ++int gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); +-void __gnet_stats_copy_basic(const seqcount_t *running, ++void __gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b); +@@ -60,13 +61,13 @@ int gen_new_estimator(struct gnet_stats_ + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *stats_lock, +- seqcount_t *running, struct nlattr *opt); ++ net_seqlock_t *running, struct nlattr *opt); + void gen_kill_estimator(struct net_rate_estimator __rcu **ptr); + int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **ptr, + spinlock_t *stats_lock, +- seqcount_t *running, struct nlattr *opt); ++ net_seqlock_t *running, struct nlattr *opt); + bool gen_estimator_active(struct net_rate_estimator __rcu **ptr); + bool gen_estimator_read(struct net_rate_estimator __rcu **ptr, + struct gnet_stats_rate_est64 *sample); +--- /dev/null ++++ b/include/net/net_seq_lock.h +@@ -0,0 +1,15 @@ ++#ifndef __NET_NET_SEQ_LOCK_H__ ++#define __NET_NET_SEQ_LOCK_H__ ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define net_seqlock_t seqlock_t ++# define net_seq_begin(__r) read_seqbegin(__r) ++# define net_seq_retry(__r, __s) read_seqretry(__r, __s) ++ ++#else ++# define net_seqlock_t seqcount_t ++# define net_seq_begin(__r) read_seqcount_begin(__r) ++# define net_seq_retry(__r, __s) read_seqcount_retry(__r, __s) ++#endif ++ ++#endif +--- a/include/net/sch_generic.h ++++ b/include/net/sch_generic.h +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -94,7 +95,7 @@ struct Qdisc { + struct sk_buff_head gso_skb ____cacheline_aligned_in_smp; + struct qdisc_skb_head q; + struct gnet_stats_basic_packed bstats; +- seqcount_t running; ++ net_seqlock_t running; + struct gnet_stats_queue qstats; + unsigned long state; + struct Qdisc *next_sched; +@@ -115,7 +116,11 @@ static inline bool qdisc_is_running(stru + { + if (qdisc->flags & TCQ_F_NOLOCK) + return spin_is_locked(&qdisc->seqlock); ++#ifdef CONFIG_PREEMPT_RT_BASE ++ return spin_is_locked(&qdisc->running.lock) ? true : false; ++#else + return (raw_read_seqcount(&qdisc->running) & 1) ? true : false; ++#endif + } + + static inline bool qdisc_run_begin(struct Qdisc *qdisc) +@@ -126,17 +131,27 @@ static inline bool qdisc_run_begin(struc + } else if (qdisc_is_running(qdisc)) { + return false; + } ++#ifdef CONFIG_PREEMPT_RT_BASE ++ if (try_write_seqlock(&qdisc->running)) ++ return true; ++ return false; ++#else + /* Variant of write_seqcount_begin() telling lockdep a trylock + * was attempted. + */ + raw_write_seqcount_begin(&qdisc->running); + seqcount_acquire(&qdisc->running.dep_map, 0, 1, _RET_IP_); + return true; ++#endif + } + + static inline void qdisc_run_end(struct Qdisc *qdisc) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ write_sequnlock(&qdisc->running); ++#else + write_seqcount_end(&qdisc->running); ++#endif + if (qdisc->flags & TCQ_F_NOLOCK) + spin_unlock(&qdisc->seqlock); + } +@@ -412,7 +427,7 @@ static inline spinlock_t *qdisc_root_sle + return qdisc_lock(root); + } + +-static inline seqcount_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) ++static inline net_seqlock_t *qdisc_root_sleeping_running(const struct Qdisc *qdisc) + { + struct Qdisc *root = qdisc_root_sleeping(qdisc); + +--- a/net/core/gen_estimator.c ++++ b/net/core/gen_estimator.c +@@ -46,7 +46,7 @@ + struct net_rate_estimator { + struct gnet_stats_basic_packed *bstats; + spinlock_t *stats_lock; +- seqcount_t *running; ++ net_seqlock_t *running; + struct gnet_stats_basic_cpu __percpu *cpu_bstats; + u8 ewma_log; + u8 intvl_log; /* period : (250ms << intvl_log) */ +@@ -129,7 +129,7 @@ int gen_new_estimator(struct gnet_stats_ + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *stats_lock, +- seqcount_t *running, ++ net_seqlock_t *running, + struct nlattr *opt) + { + struct gnet_estimator *parm = nla_data(opt); +@@ -222,7 +222,7 @@ int gen_replace_estimator(struct gnet_st + struct gnet_stats_basic_cpu __percpu *cpu_bstats, + struct net_rate_estimator __rcu **rate_est, + spinlock_t *stats_lock, +- seqcount_t *running, struct nlattr *opt) ++ net_seqlock_t *running, struct nlattr *opt) + { + return gen_new_estimator(bstats, cpu_bstats, rate_est, + stats_lock, running, opt); +--- a/net/core/gen_stats.c ++++ b/net/core/gen_stats.c +@@ -142,7 +142,7 @@ static void + } + + void +-__gnet_stats_copy_basic(const seqcount_t *running, ++__gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_stats_basic_packed *bstats, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +@@ -155,10 +155,10 @@ void + } + do { + if (running) +- seq = read_seqcount_begin(running); ++ seq = net_seq_begin(running); + bstats->bytes = b->bytes; + bstats->packets = b->packets; +- } while (running && read_seqcount_retry(running, seq)); ++ } while (running && net_seq_retry(running, seq)); + } + EXPORT_SYMBOL(__gnet_stats_copy_basic); + +@@ -176,7 +176,7 @@ EXPORT_SYMBOL(__gnet_stats_copy_basic); + * if the room in the socket buffer was not sufficient. + */ + int +-gnet_stats_copy_basic(const seqcount_t *running, ++gnet_stats_copy_basic(net_seqlock_t *running, + struct gnet_dump *d, + struct gnet_stats_basic_cpu __percpu *cpu, + struct gnet_stats_basic_packed *b) +--- a/net/sched/sch_api.c ++++ b/net/sched/sch_api.c +@@ -1159,7 +1159,7 @@ static struct Qdisc *qdisc_create(struct + rcu_assign_pointer(sch->stab, stab); + } + if (tca[TCA_RATE]) { +- seqcount_t *running; ++ net_seqlock_t *running; + + err = -EOPNOTSUPP; + if (sch->flags & TCQ_F_MQROOT) { +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -570,7 +570,11 @@ struct Qdisc noop_qdisc = { + .ops = &noop_qdisc_ops, + .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), + .dev_queue = &noop_netdev_queue, ++#ifdef CONFIG_PREEMPT_RT_BASE ++ .running = __SEQLOCK_UNLOCKED(noop_qdisc.running), ++#else + .running = SEQCNT_ZERO(noop_qdisc.running), ++#endif + .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), + }; + EXPORT_SYMBOL(noop_qdisc); +@@ -860,9 +864,17 @@ struct Qdisc *qdisc_alloc(struct netdev_ + lockdep_set_class(&sch->busylock, + dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++ seqlock_init(&sch->running); ++ lockdep_set_class(&sch->running.seqcount, ++ dev->qdisc_running_key ?: &qdisc_running_key); ++ lockdep_set_class(&sch->running.lock, ++ dev->qdisc_running_key ?: &qdisc_running_key); ++#else + seqcount_init(&sch->running); + lockdep_set_class(&sch->running, + dev->qdisc_running_key ?: &qdisc_running_key); ++#endif + + sch->ops = ops; + sch->flags = ops->static_flags; diff --git a/debian/patches/features/all/rt/net-add-a-lock-around-icmp_sk.patch b/debian/patches/features/all/rt/net-add-a-lock-around-icmp_sk.patch new file mode 100644 index 000000000..57aa15772 --- /dev/null +++ b/debian/patches/features/all/rt/net-add-a-lock-around-icmp_sk.patch @@ -0,0 +1,59 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 31 Aug 2016 17:54:09 +0200 +Subject: [PATCH] net: add a lock around icmp_sk() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +It looks like the this_cpu_ptr() access in icmp_sk() is protected with +local_bh_disable(). To avoid missing serialization in -RT I am adding +here a local lock. No crash has been observed, this is just precaution. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + net/ipv4/icmp.c | 8 ++++++++ + 1 file changed, 8 insertions(+) + +--- a/net/ipv4/icmp.c ++++ b/net/ipv4/icmp.c +@@ -77,6 +77,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -204,6 +205,8 @@ static const struct icmp_control icmp_po + * + * On SMP we have one ICMP socket per-cpu. + */ ++static DEFINE_LOCAL_IRQ_LOCK(icmp_sk_lock); ++ + static struct sock *icmp_sk(struct net *net) + { + return *this_cpu_ptr(net->ipv4.icmp_sk); +@@ -214,12 +217,16 @@ static inline struct sock *icmp_xmit_loc + { + struct sock *sk; + ++ if (!local_trylock(icmp_sk_lock)) ++ return NULL; ++ + sk = icmp_sk(net); + + if (unlikely(!spin_trylock(&sk->sk_lock.slock))) { + /* This can happen if the output path signals a + * dst_link_failure() for an outgoing ICMP packet. + */ ++ local_unlock(icmp_sk_lock); + return NULL; + } + return sk; +@@ -228,6 +235,7 @@ static inline struct sock *icmp_xmit_loc + static inline void icmp_xmit_unlock(struct sock *sk) + { + spin_unlock(&sk->sk_lock.slock); ++ local_unlock(icmp_sk_lock); + } + + int sysctl_icmp_msgs_per_sec __read_mostly = 1000; diff --git a/debian/patches/features/all/rt/net-add-back-the-missing-serialization-in-ip_send_un.patch b/debian/patches/features/all/rt/net-add-back-the-missing-serialization-in-ip_send_un.patch new file mode 100644 index 000000000..6c0cf3916 --- /dev/null +++ b/debian/patches/features/all/rt/net-add-back-the-missing-serialization-in-ip_send_un.patch @@ -0,0 +1,93 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 31 Aug 2016 17:21:56 +0200 +Subject: [PATCH] net: add back the missing serialization in + ip_send_unicast_reply() +MIME-Version: 1.0 +Content-Type: text/plain; charset=UTF-8 +Content-Transfer-Encoding: 8bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Some time ago Sami Pietikäinen reported a crash on -RT in +ip_send_unicast_reply() which was later fixed by Nicholas Mc Guire +(v3.12.8-rt11). Later (v3.18.8) the code was reworked and I dropped the +patch. As it turns out it was mistake. +I have reports that the same crash is possible with a similar backtrace. +It seems that vanilla protects access to this_cpu_ptr() via +local_bh_disable(). This does not work the on -RT since we can have +NET_RX and NET_TX running in parallel on the same CPU. +This is brings back the old locks. + +|Unable to handle kernel NULL pointer dereference at virtual address 00000010 +|PC is at __ip_make_skb+0x198/0x3e8 +|[] (__ip_make_skb) from [] (ip_push_pending_frames+0x20/0x40) +|[] (ip_push_pending_frames) from [] (ip_send_unicast_reply+0x210/0x22c) +|[] (ip_send_unicast_reply) from [] (tcp_v4_send_reset+0x190/0x1c0) +|[] (tcp_v4_send_reset) from [] (tcp_v4_do_rcv+0x22c/0x288) +|[] (tcp_v4_do_rcv) from [] (release_sock+0xb4/0x150) +|[] (release_sock) from [] (tcp_close+0x240/0x454) +|[] (tcp_close) from [] (inet_release+0x74/0x7c) +|[] (inet_release) from [] (sock_release+0x30/0xb0) +|[] (sock_release) from [] (sock_close+0x1c/0x24) +|[] (sock_close) from [] (__fput+0xe8/0x20c) +|[] (__fput) from [] (____fput+0x18/0x1c) +|[] (____fput) from [] (task_work_run+0xa4/0xb8) +|[] (task_work_run) from [] (do_work_pending+0xd0/0xe4) +|[] (do_work_pending) from [] (work_pending+0xc/0x20) +|Code: e3530001 8a000001 e3a00040 ea000011 (e5973010) + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + net/ipv4/tcp_ipv4.c | 6 ++++++ + 1 file changed, 6 insertions(+) + +--- a/net/ipv4/tcp_ipv4.c ++++ b/net/ipv4/tcp_ipv4.c +@@ -62,6 +62,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -632,6 +633,7 @@ void tcp_v4_send_check(struct sock *sk, + } + EXPORT_SYMBOL(tcp_v4_send_check); + ++static DEFINE_LOCAL_IRQ_LOCK(tcp_sk_lock); + /* + * This routine will send an RST to the other tcp. + * +@@ -766,6 +768,7 @@ static void tcp_v4_send_reset(const stru + arg.tos = ip_hdr(skb)->tos; + arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); ++ local_lock(tcp_sk_lock); + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? +@@ -778,6 +781,7 @@ static void tcp_v4_send_reset(const stru + ctl_sk->sk_mark = 0; + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); + __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); ++ local_unlock(tcp_sk_lock); + local_bh_enable(); + + #ifdef CONFIG_TCP_MD5SIG +@@ -858,6 +862,7 @@ static void tcp_v4_send_ack(const struct + arg.tos = tos; + arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); + local_bh_disable(); ++ local_lock(tcp_sk_lock); + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? +@@ -869,6 +874,7 @@ static void tcp_v4_send_ack(const struct + + ctl_sk->sk_mark = 0; + __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); ++ local_unlock(tcp_sk_lock); + local_bh_enable(); + } + diff --git a/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch b/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch new file mode 100644 index 000000000..257b09459 --- /dev/null +++ b/debian/patches/features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch @@ -0,0 +1,59 @@ +From: Thomas Gleixner +Date: Wed, 26 Sep 2012 16:21:08 +0200 +Subject: net: Another local_irq_disable/kmalloc headache +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Replace it by a local lock. Though that's pretty inefficient :( + +Signed-off-by: Thomas Gleixner +--- + net/core/skbuff.c | 10 ++++++---- + 1 file changed, 6 insertions(+), 4 deletions(-) + +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -330,6 +331,7 @@ struct napi_alloc_cache { + + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); ++static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); + + static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +@@ -337,10 +339,10 @@ static void *__netdev_alloc_frag(unsigne + unsigned long flags; + void *data; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc(nc, fragsz, gfp_mask); +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + return data; + } + +@@ -408,13 +410,13 @@ struct sk_buff *__netdev_alloc_skb(struc + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + +- local_irq_save(flags); ++ local_lock_irqsave(netdev_alloc_lock, flags); + + nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc(nc, len, gfp_mask); + pfmemalloc = nc->pfmemalloc; + +- local_irq_restore(flags); ++ local_unlock_irqrestore(netdev_alloc_lock, flags); + + if (unlikely(!data)) + return NULL; diff --git a/debian/patches/features/all/rt/net-core-protect-users-of-napi_alloc_cache-against-r.patch b/debian/patches/features/all/rt/net-core-protect-users-of-napi_alloc_cache-against-r.patch new file mode 100644 index 000000000..5154fba66 --- /dev/null +++ b/debian/patches/features/all/rt/net-core-protect-users-of-napi_alloc_cache-against-r.patch @@ -0,0 +1,113 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 15 Jan 2016 16:33:34 +0100 +Subject: net/core: protect users of napi_alloc_cache against + reentrance +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On -RT the code running in BH can not be moved to another CPU so CPU +local variable remain local. However the code can be preempted +and another task may enter BH accessing the same CPU using the same +napi_alloc_cache variable. +This patch ensures that each user of napi_alloc_cache uses a local lock. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + net/core/skbuff.c | 25 +++++++++++++++++++------ + 1 file changed, 19 insertions(+), 6 deletions(-) + +--- a/net/core/skbuff.c ++++ b/net/core/skbuff.c +@@ -332,6 +332,7 @@ struct napi_alloc_cache { + static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); + static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); + static DEFINE_LOCAL_IRQ_LOCK(netdev_alloc_lock); ++static DEFINE_LOCAL_IRQ_LOCK(napi_alloc_cache_lock); + + static void *__netdev_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +@@ -361,9 +362,13 @@ EXPORT_SYMBOL(netdev_alloc_frag); + + static void *__napi_alloc_frag(unsigned int fragsz, gfp_t gfp_mask) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; ++ void *data; + +- return page_frag_alloc(&nc->page, fragsz, gfp_mask); ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ data = page_frag_alloc(&nc->page, fragsz, gfp_mask); ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); ++ return data; + } + + void *napi_alloc_frag(unsigned int fragsz) +@@ -457,9 +462,10 @@ EXPORT_SYMBOL(__netdev_alloc_skb); + struct sk_buff *__napi_alloc_skb(struct napi_struct *napi, unsigned int len, + gfp_t gfp_mask) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; + struct sk_buff *skb; + void *data; ++ bool pfmemalloc; + + len += NET_SKB_PAD + NET_IP_ALIGN; + +@@ -477,7 +483,10 @@ struct sk_buff *__napi_alloc_skb(struct + if (sk_memalloc_socks()) + gfp_mask |= __GFP_MEMALLOC; + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + data = page_frag_alloc(&nc->page, len, gfp_mask); ++ pfmemalloc = nc->page.pfmemalloc; ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + if (unlikely(!data)) + return NULL; + +@@ -488,7 +497,7 @@ struct sk_buff *__napi_alloc_skb(struct + } + + /* use OR instead of assignment to avoid clearing of bits in mask */ +- if (nc->page.pfmemalloc) ++ if (pfmemalloc) + skb->pfmemalloc = 1; + skb->head_frag = 1; + +@@ -720,23 +729,26 @@ void __consume_stateless_skb(struct sk_b + + void __kfree_skb_flush(void) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + /* flush skb_cache if containing objects */ + if (nc->skb_count) { + kmem_cache_free_bulk(skbuff_head_cache, nc->skb_count, + nc->skb_cache); + nc->skb_count = 0; + } ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + } + + static inline void _kfree_skb_defer(struct sk_buff *skb) + { +- struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); ++ struct napi_alloc_cache *nc; + + /* drop skb->head and call any destructors for packet */ + skb_release_all(skb); + ++ nc = &get_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + /* record skb to CPU local list */ + nc->skb_cache[nc->skb_count++] = skb; + +@@ -751,6 +763,7 @@ static inline void _kfree_skb_defer(stru + nc->skb_cache); + nc->skb_count = 0; + } ++ put_locked_var(napi_alloc_cache_lock, napi_alloc_cache); + } + void __kfree_skb_defer(struct sk_buff *skb) + { diff --git a/debian/patches/features/all/rt/net-core-use-local_bh_disable-in-netif_rx_ni.patch b/debian/patches/features/all/rt/net-core-use-local_bh_disable-in-netif_rx_ni.patch new file mode 100644 index 000000000..4821ef806 --- /dev/null +++ b/debian/patches/features/all/rt/net-core-use-local_bh_disable-in-netif_rx_ni.patch @@ -0,0 +1,35 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 16 Jun 2017 19:03:16 +0200 +Subject: [PATCH] net/core: use local_bh_disable() in netif_rx_ni() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In 2004 netif_rx_ni() gained a preempt_disable() section around +netif_rx() and its do_softirq() + testing for it. The do_softirq() part +is required because netif_rx() raises the softirq but does not invoke +it. The preempt_disable() is required to remain on the same CPU which added the +skb to the per-CPU list. +All this can be avoided be putting this into a local_bh_disable()ed +section. The local_bh_enable() part will invoke do_softirq() if +required. + +Signed-off-by: Sebastian Andrzej Siewior +--- + net/core/dev.c | 6 ++---- + 1 file changed, 2 insertions(+), 4 deletions(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4252,11 +4252,9 @@ int netif_rx_ni(struct sk_buff *skb) + + trace_netif_rx_ni_entry(skb); + +- preempt_disable(); ++ local_bh_disable(); + err = netif_rx_internal(skb); +- if (local_softirq_pending()) +- do_softirq(); +- preempt_enable(); ++ local_bh_enable(); + + return err; + } diff --git a/debian/patches/features/all/rt/net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch b/debian/patches/features/all/rt/net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch new file mode 100644 index 000000000..4b2fef840 --- /dev/null +++ b/debian/patches/features/all/rt/net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch @@ -0,0 +1,35 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 30 Mar 2016 13:36:29 +0200 +Subject: [PATCH] net: dev: always take qdisc's busylock in __dev_xmit_skb() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The root-lock is dropped before dev_hard_start_xmit() is invoked and after +setting the __QDISC___STATE_RUNNING bit. If this task is now pushed away +by a task with a higher priority then the task with the higher priority +won't be able to submit packets to the NIC directly instead they will be +enqueued into the Qdisc. The NIC will remain idle until the task(s) with +higher priority leave the CPU and the task with lower priority gets back +and finishes the job. + +If we take always the busylock we ensure that the RT task can boost the +low-prio task and submit the packet. + +Signed-off-by: Sebastian Andrzej Siewior +--- + net/core/dev.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3242,7 +3242,11 @@ static inline int __dev_xmit_skb(struct + * This permits qdisc->running owner to get the lock more + * often and dequeue packets faster. + */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ contended = true; ++#else + contended = qdisc_is_running(q); ++#endif + if (unlikely(contended)) + spin_lock(&q->busylock); + diff --git a/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch b/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch new file mode 100644 index 000000000..312d85dbc --- /dev/null +++ b/debian/patches/features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch @@ -0,0 +1,76 @@ +Subject: net: netfilter: Serialize xt_write_recseq sections on RT +From: Thomas Gleixner +Date: Sun, 28 Oct 2012 11:18:08 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The netfilter code relies only on the implicit semantics of +local_bh_disable() for serializing wt_write_recseq sections. RT breaks +that and needs explicit serialization here. + +Reported-by: Peter LaDow +Signed-off-by: Thomas Gleixner + +--- + include/linux/netfilter/x_tables.h | 7 +++++++ + net/netfilter/core.c | 6 ++++++ + 2 files changed, 13 insertions(+) + +--- a/include/linux/netfilter/x_tables.h ++++ b/include/linux/netfilter/x_tables.h +@@ -6,6 +6,7 @@ + #include + #include + #include ++#include + #include + + /* Test a struct->invflags and a boolean for inequality */ +@@ -345,6 +346,8 @@ void xt_free_table_info(struct xt_table_ + */ + DECLARE_PER_CPU(seqcount_t, xt_recseq); + ++DECLARE_LOCAL_IRQ_LOCK(xt_write_lock); ++ + /* xt_tee_enabled - true if x_tables needs to handle reentrancy + * + * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. +@@ -365,6 +368,9 @@ static inline unsigned int xt_write_recs + { + unsigned int addend; + ++ /* RT protection */ ++ local_lock(xt_write_lock); ++ + /* + * Low order bit of sequence is set if we already + * called xt_write_recseq_begin(). +@@ -395,6 +401,7 @@ static inline void xt_write_recseq_end(u + /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ + smp_wmb(); + __this_cpu_add(xt_recseq.sequence, addend); ++ local_unlock(xt_write_lock); + } + + /* +--- a/net/netfilter/core.c ++++ b/net/netfilter/core.c +@@ -20,6 +20,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -27,6 +28,11 @@ + + #include "nf_internals.h" + ++#ifdef CONFIG_PREEMPT_RT_BASE ++DEFINE_LOCAL_IRQ_LOCK(xt_write_lock); ++EXPORT_PER_CPU_SYMBOL(xt_write_lock); ++#endif ++ + const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; + EXPORT_SYMBOL_GPL(nf_ipv6_ops); + diff --git a/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch b/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch new file mode 100644 index 000000000..8f8e2ea9b --- /dev/null +++ b/debian/patches/features/all/rt/net-make-devnet_rename_seq-a-mutex.patch @@ -0,0 +1,107 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 20 Mar 2013 18:06:20 +0100 +Subject: net: Add a mutex around devnet_rename_seq +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On RT write_seqcount_begin() disables preemption and device_rename() +allocates memory with GFP_KERNEL and grabs later the sysfs_mutex +mutex. Serialize with a mutex and add use the non preemption disabling +__write_seqcount_begin(). + +To avoid writer starvation, let the reader grab the mutex and release +it when it detects a writer in progress. This keeps the normal case +(no reader on the fly) fast. + +[ tglx: Instead of replacing the seqcount by a mutex, add the mutex ] + +Signed-off-by: Sebastian Andrzej Siewior +Signed-off-by: Thomas Gleixner +--- + net/core/dev.c | 34 ++++++++++++++++++++-------------- + 1 file changed, 20 insertions(+), 14 deletions(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -197,6 +197,7 @@ static unsigned int napi_gen_id = NR_CPU + static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); + + static seqcount_t devnet_rename_seq; ++static DEFINE_MUTEX(devnet_rename_mutex); + + static inline void dev_base_seq_inc(struct net *net) + { +@@ -922,7 +923,8 @@ int netdev_get_name(struct net *net, cha + strcpy(name, dev->name); + rcu_read_unlock(); + if (read_seqcount_retry(&devnet_rename_seq, seq)) { +- cond_resched(); ++ mutex_lock(&devnet_rename_mutex); ++ mutex_unlock(&devnet_rename_mutex); + goto retry; + } + +@@ -1185,20 +1187,17 @@ int dev_change_name(struct net_device *d + if (dev->flags & IFF_UP) + return -EBUSY; + +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + +- if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { +- write_seqcount_end(&devnet_rename_seq); +- return 0; +- } ++ if (strncmp(newname, dev->name, IFNAMSIZ) == 0) ++ goto outunlock; + + memcpy(oldname, dev->name, IFNAMSIZ); + + err = dev_get_valid_name(net, dev, newname); +- if (err < 0) { +- write_seqcount_end(&devnet_rename_seq); +- return err; +- } ++ if (err < 0) ++ goto outunlock; + + if (oldname[0] && !strchr(oldname, '%')) + netdev_info(dev, "renamed from %s\n", oldname); +@@ -1211,11 +1210,12 @@ int dev_change_name(struct net_device *d + if (ret) { + memcpy(dev->name, oldname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +- write_seqcount_end(&devnet_rename_seq); +- return ret; ++ err = ret; ++ goto outunlock; + } + +- write_seqcount_end(&devnet_rename_seq); ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); + + netdev_adjacent_rename_links(dev, oldname); + +@@ -1236,7 +1236,8 @@ int dev_change_name(struct net_device *d + /* err >= 0 after dev_alloc_name() or stores the first errno */ + if (err >= 0) { + err = ret; +- write_seqcount_begin(&devnet_rename_seq); ++ mutex_lock(&devnet_rename_mutex); ++ __raw_write_seqcount_begin(&devnet_rename_seq); + memcpy(dev->name, oldname, IFNAMSIZ); + memcpy(oldname, newname, IFNAMSIZ); + dev->name_assign_type = old_assign_type; +@@ -1249,6 +1250,11 @@ int dev_change_name(struct net_device *d + } + + return err; ++ ++outunlock: ++ __raw_write_seqcount_end(&devnet_rename_seq); ++ mutex_unlock(&devnet_rename_mutex); ++ return err; + } + + /** diff --git a/debian/patches/features/all/rt/net-move-xmit_recursion-to-per-task-variable-on-RT.patch b/debian/patches/features/all/rt/net-move-xmit_recursion-to-per-task-variable-on-RT.patch new file mode 100644 index 000000000..6ec25a174 --- /dev/null +++ b/debian/patches/features/all/rt/net-move-xmit_recursion-to-per-task-variable-on-RT.patch @@ -0,0 +1,266 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 13 Jan 2016 15:55:02 +0100 +Subject: net: move xmit_recursion to per-task variable on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +A softirq on -RT can be preempted. That means one task is in +__dev_queue_xmit(), gets preempted and another task may enter +__dev_queue_xmit() aw well. netperf together with a bridge device +will then trigger the `recursion alert` because each task increments +the xmit_recursion variable which is per-CPU. +A virtual device like br0 is required to trigger this warning. + +This patch moves the lock owner and counter to be per task instead per-CPU so +it counts the recursion properly on -RT. The owner is also a task now and not a +CPU number. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/netdevice.h | 95 ++++++++++++++++++++++++++++++++++++++++++---- + include/linux/sched.h | 3 + + net/core/dev.c | 15 ++++--- + net/core/filter.c | 6 +- + 4 files changed, 104 insertions(+), 15 deletions(-) + +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -573,7 +573,11 @@ struct netdev_queue { + * write-mostly part + */ + spinlock_t _xmit_lock ____cacheline_aligned_in_smp; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct task_struct *xmit_lock_owner; ++#else + int xmit_lock_owner; ++#endif + /* + * Time (in jiffies) of last Tx + */ +@@ -2554,14 +2558,53 @@ void netdev_freemem(struct net_device *d + void synchronize_net(void); + int init_dummy_netdev(struct net_device *dev); + +-DECLARE_PER_CPU(int, xmit_recursion); + #define XMIT_RECURSION_LIMIT 10 ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int dev_recursion_level(void) ++{ ++ return current->xmit_recursion; ++} ++ ++static inline int xmit_rec_read(void) ++{ ++ return current->xmit_recursion; ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ current->xmit_recursion++; ++} ++ ++static inline void xmit_rec_dec(void) ++{ ++ current->xmit_recursion--; ++} ++ ++#else ++ ++DECLARE_PER_CPU(int, xmit_recursion); + + static inline int dev_recursion_level(void) + { + return this_cpu_read(xmit_recursion); + } + ++static inline int xmit_rec_read(void) ++{ ++ return __this_cpu_read(xmit_recursion); ++} ++ ++static inline void xmit_rec_inc(void) ++{ ++ __this_cpu_inc(xmit_recursion); ++} ++ ++static inline void xmit_rec_dec(void) ++{ ++ __this_cpu_dec(xmit_recursion); ++} ++#endif ++ + struct net_device *dev_get_by_index(struct net *net, int ifindex); + struct net_device *__dev_get_by_index(struct net *net, int ifindex); + struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); +@@ -3639,10 +3682,48 @@ static inline u32 netif_msg_init(int deb + return (1 << debug_value) - 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) ++{ ++ txq->xmit_lock_owner = current; ++} ++ ++static inline void netdev_queue_clear_owner(struct netdev_queue *txq) ++{ ++ txq->xmit_lock_owner = NULL; ++} ++ ++static inline bool netdev_queue_has_owner(struct netdev_queue *txq) ++{ ++ if (txq->xmit_lock_owner != NULL) ++ return true; ++ return false; ++} ++ ++#else ++ ++static inline void netdev_queue_set_owner(struct netdev_queue *txq, int cpu) ++{ ++ txq->xmit_lock_owner = cpu; ++} ++ ++static inline void netdev_queue_clear_owner(struct netdev_queue *txq) ++{ ++ txq->xmit_lock_owner = -1; ++} ++ ++static inline bool netdev_queue_has_owner(struct netdev_queue *txq) ++{ ++ if (txq->xmit_lock_owner != -1) ++ return true; ++ return false; ++} ++#endif ++ + static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) + { + spin_lock(&txq->_xmit_lock); +- txq->xmit_lock_owner = cpu; ++ netdev_queue_set_owner(txq, cpu); + } + + static inline bool __netif_tx_acquire(struct netdev_queue *txq) +@@ -3659,32 +3740,32 @@ static inline void __netif_tx_release(st + static inline void __netif_tx_lock_bh(struct netdev_queue *txq) + { + spin_lock_bh(&txq->_xmit_lock); +- txq->xmit_lock_owner = smp_processor_id(); ++ netdev_queue_set_owner(txq, smp_processor_id()); + } + + static inline bool __netif_tx_trylock(struct netdev_queue *txq) + { + bool ok = spin_trylock(&txq->_xmit_lock); + if (likely(ok)) +- txq->xmit_lock_owner = smp_processor_id(); ++ netdev_queue_set_owner(txq, smp_processor_id()); + return ok; + } + + static inline void __netif_tx_unlock(struct netdev_queue *txq) + { +- txq->xmit_lock_owner = -1; ++ netdev_queue_clear_owner(txq); + spin_unlock(&txq->_xmit_lock); + } + + static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) + { +- txq->xmit_lock_owner = -1; ++ netdev_queue_clear_owner(txq); + spin_unlock_bh(&txq->_xmit_lock); + } + + static inline void txq_trans_update(struct netdev_queue *txq) + { +- if (txq->xmit_lock_owner != -1) ++ if (netdev_queue_has_owner(txq)) + txq->trans_start = jiffies; + } + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1196,6 +1196,9 @@ struct task_struct { + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int xmit_recursion; ++#endif + int pagefault_disabled; + #ifdef CONFIG_MMU + struct task_struct *oom_reaper_list; +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -3314,8 +3314,10 @@ static void skb_update_prio(struct sk_bu + #define skb_update_prio(skb) + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL + DEFINE_PER_CPU(int, xmit_recursion); + EXPORT_SYMBOL(xmit_recursion); ++#endif + + /** + * dev_loopback_xmit - loop back @skb +@@ -3555,9 +3557,12 @@ static int __dev_queue_xmit(struct sk_bu + if (dev->flags & IFF_UP) { + int cpu = smp_processor_id(); /* ok because BHs are off */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (txq->xmit_lock_owner != current) { ++#else + if (txq->xmit_lock_owner != cpu) { +- if (unlikely(__this_cpu_read(xmit_recursion) > +- XMIT_RECURSION_LIMIT)) ++#endif ++ if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT)) + goto recursion_alert; + + skb = validate_xmit_skb(skb, dev, &again); +@@ -3567,9 +3572,9 @@ static int __dev_queue_xmit(struct sk_bu + HARD_TX_LOCK(dev, txq, cpu); + + if (!netif_xmit_stopped(txq)) { +- __this_cpu_inc(xmit_recursion); ++ xmit_rec_inc(); + skb = dev_hard_start_xmit(skb, dev, txq, &rc); +- __this_cpu_dec(xmit_recursion); ++ xmit_rec_dec(); + if (dev_xmit_complete(rc)) { + HARD_TX_UNLOCK(dev, txq); + goto out; +@@ -7858,7 +7863,7 @@ static void netdev_init_one_queue(struct + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); +- queue->xmit_lock_owner = -1; ++ netdev_queue_clear_owner(queue); + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); + queue->dev = dev; + #ifdef CONFIG_BQL +--- a/net/core/filter.c ++++ b/net/core/filter.c +@@ -1983,7 +1983,7 @@ static inline int __bpf_tx_skb(struct ne + { + int ret; + +- if (unlikely(__this_cpu_read(xmit_recursion) > XMIT_RECURSION_LIMIT)) { ++ if (unlikely(xmit_rec_read() > XMIT_RECURSION_LIMIT)) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + kfree_skb(skb); + return -ENETDOWN; +@@ -1991,9 +1991,9 @@ static inline int __bpf_tx_skb(struct ne + + skb->dev = dev; + +- __this_cpu_inc(xmit_recursion); ++ xmit_rec_inc(); + ret = dev_queue_xmit(skb); +- __this_cpu_dec(xmit_recursion); ++ xmit_rec_dec(); + + return ret; + } diff --git a/debian/patches/features/all/rt/net-provide-a-way-to-delegate-processing-a-softirq-t.patch b/debian/patches/features/all/rt/net-provide-a-way-to-delegate-processing-a-softirq-t.patch new file mode 100644 index 000000000..4ec112d8a --- /dev/null +++ b/debian/patches/features/all/rt/net-provide-a-way-to-delegate-processing-a-softirq-t.patch @@ -0,0 +1,79 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 20 Jan 2016 15:39:05 +0100 +Subject: net: provide a way to delegate processing a softirq to + ksoftirqd +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +If the NET_RX uses up all of his budget it moves the following NAPI +invocations into the `ksoftirqd`. On -RT it does not do so. Instead it +rises the NET_RX softirq in its current context again. + +In order to get closer to mainline's behaviour this patch provides +__raise_softirq_irqoff_ksoft() which raises the softirq in the ksoftird. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/interrupt.h | 8 ++++++++ + kernel/softirq.c | 21 +++++++++++++++++++++ + net/core/dev.c | 2 +- + 3 files changed, 30 insertions(+), 1 deletion(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -524,6 +524,14 @@ extern void thread_do_softirq(void); + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); + extern void __raise_softirq_irqoff(unsigned int nr); ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void __raise_softirq_irqoff_ksoft(unsigned int nr); ++#else ++static inline void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++} ++#endif + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -694,6 +694,27 @@ void __raise_softirq_irqoff(unsigned int + } + + /* ++ * Same as __raise_softirq_irqoff() but will process them in ksoftirqd ++ */ ++void __raise_softirq_irqoff_ksoft(unsigned int nr) ++{ ++ unsigned int mask; ++ ++ if (WARN_ON_ONCE(!__this_cpu_read(ksoftirqd) || ++ !__this_cpu_read(ktimer_softirqd))) ++ return; ++ mask = 1UL << nr; ++ ++ trace_softirq_raise(nr); ++ or_softirq_pending(mask); ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++ wakeup_proper_softirq(nr); ++} ++ ++/* + * This function must run with irqs disabled! + */ + void raise_softirq_irqoff(unsigned int nr) +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -5875,7 +5875,7 @@ static __latent_entropy void net_rx_acti + list_splice_tail(&repoll, &list); + list_splice(&list, &sd->poll_list); + if (!list_empty(&sd->poll_list)) +- __raise_softirq_irqoff(NET_RX_SOFTIRQ); ++ __raise_softirq_irqoff_ksoft(NET_RX_SOFTIRQ); + + net_rps_action_and_irq_enable(sd); + out: diff --git a/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch b/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch new file mode 100644 index 000000000..577fdcefe --- /dev/null +++ b/debian/patches/features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch @@ -0,0 +1,58 @@ +From: Marc Kleine-Budde +Date: Wed, 5 Mar 2014 00:49:47 +0100 +Subject: net: sched: Use msleep() instead of yield() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On PREEMPT_RT enabled systems the interrupt handler run as threads at prio 50 +(by default). If a high priority userspace process tries to shut down a busy +network interface it might spin in a yield loop waiting for the device to +become idle. With the interrupt thread having a lower priority than the +looping process it might never be scheduled and so result in a deadlock on UP +systems. + +With Magic SysRq the following backtrace can be produced: + +> test_app R running 0 174 168 0x00000000 +> [] (__schedule+0x220/0x3fc) from [] (preempt_schedule_irq+0x48/0x80) +> [] (preempt_schedule_irq+0x48/0x80) from [] (svc_preempt+0x8/0x20) +> [] (svc_preempt+0x8/0x20) from [] (local_bh_enable+0x18/0x88) +> [] (local_bh_enable+0x18/0x88) from [] (dev_deactivate_many+0x220/0x264) +> [] (dev_deactivate_many+0x220/0x264) from [] (__dev_close_many+0x64/0xd4) +> [] (__dev_close_many+0x64/0xd4) from [] (__dev_close+0x28/0x3c) +> [] (__dev_close+0x28/0x3c) from [] (__dev_change_flags+0x88/0x130) +> [] (__dev_change_flags+0x88/0x130) from [] (dev_change_flags+0x10/0x48) +> [] (dev_change_flags+0x10/0x48) from [] (do_setlink+0x370/0x7ec) +> [] (do_setlink+0x370/0x7ec) from [] (rtnl_newlink+0x2b4/0x450) +> [] (rtnl_newlink+0x2b4/0x450) from [] (rtnetlink_rcv_msg+0x158/0x1f4) +> [] (rtnetlink_rcv_msg+0x158/0x1f4) from [] (netlink_rcv_skb+0xac/0xc0) +> [] (netlink_rcv_skb+0xac/0xc0) from [] (rtnetlink_rcv+0x18/0x24) +> [] (rtnetlink_rcv+0x18/0x24) from [] (netlink_unicast+0x13c/0x198) +> [] (netlink_unicast+0x13c/0x198) from [] (netlink_sendmsg+0x264/0x2e0) +> [] (netlink_sendmsg+0x264/0x2e0) from [] (sock_sendmsg+0x78/0x98) +> [] (sock_sendmsg+0x78/0x98) from [] (___sys_sendmsg.part.25+0x268/0x278) +> [] (___sys_sendmsg.part.25+0x268/0x278) from [] (__sys_sendmsg+0x48/0x78) +> [] (__sys_sendmsg+0x48/0x78) from [] (ret_fast_syscall+0x0/0x2c) + +This patch works around the problem by replacing yield() by msleep(1), giving +the interrupt thread time to finish, similar to other changes contained in the +rt patch set. Using wait_for_completion() instead would probably be a better +solution. + + +Signed-off-by: Marc Kleine-Budde +Signed-off-by: Sebastian Andrzej Siewior +--- + net/sched/sch_generic.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/sched/sch_generic.c ++++ b/net/sched/sch_generic.c +@@ -1184,7 +1184,7 @@ void dev_deactivate_many(struct list_hea + /* Wait for outstanding qdisc_run calls. */ + list_for_each_entry(dev, head, close_list) { + while (some_qdisc_is_busy(dev)) +- yield(); ++ msleep(1); + /* The new qdisc is assigned at this point so we can safely + * unwind stale skb lists and qdisc statistics + */ diff --git a/debian/patches/features/all/rt/net-use-cpu-chill.patch b/debian/patches/features/all/rt/net-use-cpu-chill.patch new file mode 100644 index 000000000..38c1ab4a1 --- /dev/null +++ b/debian/patches/features/all/rt/net-use-cpu-chill.patch @@ -0,0 +1,63 @@ +Subject: net: Use cpu_chill() instead of cpu_relax() +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 21:10:04 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Use cpu_chill() instead of cpu_relax() to let the system +make progress. + +Signed-off-by: Thomas Gleixner + +--- + net/packet/af_packet.c | 5 +++-- + net/rds/ib_rdma.c | 3 ++- + 2 files changed, 5 insertions(+), 3 deletions(-) + +--- a/net/packet/af_packet.c ++++ b/net/packet/af_packet.c +@@ -63,6 +63,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -666,7 +667,7 @@ static void prb_retire_rx_blk_timer_expi + if (BLOCK_NUM_PKTS(pbd)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + +@@ -928,7 +929,7 @@ static void prb_retire_current_block(str + if (!(status & TP_STATUS_BLK_TMO)) { + while (atomic_read(&pkc->blk_fill_in_prog)) { + /* Waiting for skb_copy_bits to finish... */ +- cpu_relax(); ++ cpu_chill(); + } + } + prb_close_block(pkc, pbd, po, status); +--- a/net/rds/ib_rdma.c ++++ b/net/rds/ib_rdma.c +@@ -34,6 +34,7 @@ + #include + #include + #include ++#include + + #include "rds_single_path.h" + #include "ib_mr.h" +@@ -210,7 +211,7 @@ static inline void wait_clean_list_grace + for_each_online_cpu(cpu) { + flag = &per_cpu(clean_list_grace, cpu); + while (test_bit(CLEAN_LIST_BUSY_BIT, flag)) +- cpu_relax(); ++ cpu_chill(); + } + } + diff --git a/debian/patches/features/all/rt/net_disable_NET_RX_BUSY_POLL.patch b/debian/patches/features/all/rt/net_disable_NET_RX_BUSY_POLL.patch new file mode 100644 index 000000000..d3ea37c16 --- /dev/null +++ b/debian/patches/features/all/rt/net_disable_NET_RX_BUSY_POLL.patch @@ -0,0 +1,29 @@ +From: Sebastian Andrzej Siewior +Date: Sat, 27 May 2017 19:02:06 +0200 +Subject: net/core: disable NET_RX_BUSY_POLL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +sk_busy_loop() does preempt_disable() followed by a few operations which can +take sleeping locks and may get long. +I _think_ that we could use preempt_disable_nort() (in sk_busy_loop()) instead +but after a successfull cmpxchg(&napi->state, …) we would gain the ressource +and could be scheduled out. At this point nobody knows who (which context) owns +it and so it could take a while until the state is realeased and napi_poll() +could be invoked again. + +Signed-off-by: Sebastian Andrzej Siewior +--- + net/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/net/Kconfig ++++ b/net/Kconfig +@@ -275,7 +275,7 @@ config CGROUP_NET_CLASSID + + config NET_RX_BUSY_POLL + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config BQL + bool diff --git a/debian/patches/features/all/rt/ntfs-avoid-disabling-interrupts-during-kmap_atomic.patch b/debian/patches/features/all/rt/ntfs-avoid-disabling-interrupts-during-kmap_atomic.patch new file mode 100644 index 000000000..59f117f68 --- /dev/null +++ b/debian/patches/features/all/rt/ntfs-avoid-disabling-interrupts-during-kmap_atomic.patch @@ -0,0 +1,52 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 10 Apr 2018 17:54:32 +0200 +Subject: [PATCH] ntfs: don't disable interrupts during kmap_atomic() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +ntfs_end_buffer_async_read() disables interrupts around kmap_atomic(). This is +a leftover from the old kmap_atomic() implementation which relied on fixed +mapping slots, so the caller had to make sure that the same slot could not be +reused from an interrupting context. + +kmap_atomic() was changed to dynamic slots long ago and commit 1ec9c5ddc17a +("include/linux/highmem.h: remove the second argument of k[un]map_atomic()") +removed the slot assignements, but the callers were not checked for now +redundant interrupt disabling. + +Remove the conditional interrupt disable. + +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/ntfs/aops.c | 4 ---- + 1 file changed, 4 deletions(-) + +--- a/fs/ntfs/aops.c ++++ b/fs/ntfs/aops.c +@@ -93,13 +93,11 @@ static void ntfs_end_buffer_async_read(s + ofs = 0; + if (file_ofs < init_size) + ofs = init_size - file_ofs; +- local_irq_save(flags); + kaddr = kmap_atomic(page); + memset(kaddr + bh_offset(bh) + ofs, 0, + bh->b_size - ofs); + flush_dcache_page(page); + kunmap_atomic(kaddr); +- local_irq_restore(flags); + } + } else { + clear_buffer_uptodate(bh); +@@ -146,13 +144,11 @@ static void ntfs_end_buffer_async_read(s + recs = PAGE_SIZE / rec_size; + /* Should have been verified before we got here... */ + BUG_ON(!recs); +- local_irq_save(flags); + kaddr = kmap_atomic(page); + for (i = 0; i < recs; i++) + post_read_mst_fixup((NTFS_RECORD*)(kaddr + + i * rec_size), rec_size); + kunmap_atomic(kaddr); +- local_irq_restore(flags); + flush_dcache_page(page); + if (likely(page_uptodate && !PageError(page))) + SetPageUptodate(page); diff --git a/debian/patches/features/all/rt/oleg-signal-rt-fix.patch b/debian/patches/features/all/rt/oleg-signal-rt-fix.patch new file mode 100644 index 000000000..daef77780 --- /dev/null +++ b/debian/patches/features/all/rt/oleg-signal-rt-fix.patch @@ -0,0 +1,143 @@ +From: Oleg Nesterov +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: signal/x86: Delay calling signals in atomic +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On x86_64 we must disable preemption before we enable interrupts +for stack faults, int3 and debugging, because the current task is using +a per CPU debug stack defined by the IST. If we schedule out, another task +can come in and use the same stack and cause the stack to be corrupted +and crash the kernel on return. + +When CONFIG_PREEMPT_RT_FULL is enabled, spin_locks become mutexes, and +one of these is the spin lock used in signal handling. + +Some of the debug code (int3) causes do_trap() to send a signal. +This function calls a spin lock that has been converted to a mutex +and has the possibility to sleep. If this happens, the above issues with +the corrupted stack is possible. + +Instead of calling the signal right away, for PREEMPT_RT and x86_64, +the signal information is stored on the stacks task_struct and +TIF_NOTIFY_RESUME is set. Then on exit of the trap, the signal resume +code will send the signal when preemption is enabled. + +[ rostedt: Switched from #ifdef CONFIG_PREEMPT_RT_FULL to + ARCH_RT_DELAYS_SIGNAL_SEND and added comments to the code. ] + + +Signed-off-by: Oleg Nesterov +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner +--- + + arch/x86/entry/common.c | 7 +++++++ + arch/x86/include/asm/signal.h | 13 +++++++++++++ + include/linux/sched.h | 4 ++++ + kernel/signal.c | 37 +++++++++++++++++++++++++++++++++++-- + 4 files changed, 59 insertions(+), 2 deletions(-) + +--- a/arch/x86/entry/common.c ++++ b/arch/x86/entry/common.c +@@ -151,6 +151,13 @@ static void exit_to_usermode_loop(struct + if (cached_flags & _TIF_NEED_RESCHED) + schedule(); + ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (unlikely(current->forced_info.si_signo)) { ++ struct task_struct *t = current; ++ force_sig_info(t->forced_info.si_signo, &t->forced_info, t); ++ t->forced_info.si_signo = 0; ++ } ++#endif + if (cached_flags & _TIF_UPROBE) + uprobe_notify_resume(regs); + +--- a/arch/x86/include/asm/signal.h ++++ b/arch/x86/include/asm/signal.h +@@ -28,6 +28,19 @@ typedef struct { + #define SA_IA32_ABI 0x02000000u + #define SA_X32_ABI 0x01000000u + ++/* ++ * Because some traps use the IST stack, we must keep preemption ++ * disabled while calling do_trap(), but do_trap() may call ++ * force_sig_info() which will grab the signal spin_locks for the ++ * task, which in PREEMPT_RT_FULL are mutexes. By defining ++ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set ++ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the ++ * trap. ++ */ ++#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#define ARCH_RT_DELAYS_SIGNAL_SEND ++#endif ++ + #ifndef CONFIG_COMPAT + typedef sigset_t compat_sigset_t; + #endif +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -875,6 +875,10 @@ struct task_struct { + /* Restored if set_restore_sigmask() was used: */ + sigset_t saved_sigmask; + struct sigpending pending; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* TODO: move me into ->restart_block ? */ ++ struct siginfo forced_info; ++#endif + unsigned long sas_ss_sp; + size_t sas_ss_size; + unsigned int sas_ss_flags; +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -1185,8 +1185,8 @@ int do_send_sig_info(int sig, struct sig + * We don't want to have recursive SIGSEGV's etc, for example, + * that is why we also clear SIGNAL_UNKILLABLE. + */ +-int +-force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++static int ++do_force_sig_info(int sig, struct siginfo *info, struct task_struct *t) + { + unsigned long int flags; + int ret, blocked, ignored; +@@ -1215,6 +1215,39 @@ force_sig_info(int sig, struct siginfo * + return ret; + } + ++int force_sig_info(int sig, struct siginfo *info, struct task_struct *t) ++{ ++/* ++ * On some archs, PREEMPT_RT has to delay sending a signal from a trap ++ * since it can not enable preemption, and the signal code's spin_locks ++ * turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME which will ++ * send the signal on exit of the trap. ++ */ ++#ifdef ARCH_RT_DELAYS_SIGNAL_SEND ++ if (in_atomic()) { ++ if (WARN_ON_ONCE(t != current)) ++ return 0; ++ if (WARN_ON_ONCE(t->forced_info.si_signo)) ++ return 0; ++ ++ if (is_si_special(info)) { ++ WARN_ON_ONCE(info != SEND_SIG_PRIV); ++ t->forced_info.si_signo = sig; ++ t->forced_info.si_errno = 0; ++ t->forced_info.si_code = SI_KERNEL; ++ t->forced_info.si_pid = 0; ++ t->forced_info.si_uid = 0; ++ } else { ++ t->forced_info = *info; ++ } ++ ++ set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); ++ return 0; ++ } ++#endif ++ return do_force_sig_info(sig, info, t); ++} ++ + /* + * Nuke all other threads in the group. + */ diff --git a/debian/patches/features/all/rt/panic-disable-random-on-rt.patch b/debian/patches/features/all/rt/panic-disable-random-on-rt.patch new file mode 100644 index 000000000..51cee3c2b --- /dev/null +++ b/debian/patches/features/all/rt/panic-disable-random-on-rt.patch @@ -0,0 +1,27 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: panic: skip get_random_bytes for RT_FULL in init_oops_id +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Disable on -RT. If this is invoked from irq-context we will have problems +to acquire the sleeping lock. + +Signed-off-by: Thomas Gleixner +--- + kernel/panic.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/kernel/panic.c ++++ b/kernel/panic.c +@@ -475,9 +475,11 @@ static u64 oops_id; + + static int init_oops_id(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (!oops_id) + get_random_bytes(&oops_id, sizeof(oops_id)); + else ++#endif + oops_id++; + + return 0; diff --git a/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch b/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch new file mode 100644 index 000000000..4fa63b421 --- /dev/null +++ b/debian/patches/features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch @@ -0,0 +1,99 @@ +Subject: rcu: Make ksoftirqd do RCU quiescent states +From: "Paul E. McKenney" +Date: Wed, 5 Oct 2011 11:45:18 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Implementing RCU-bh in terms of RCU-preempt makes the system vulnerable +to network-based denial-of-service attacks. This patch therefore +makes __do_softirq() invoke rcu_bh_qs(), but only when __do_softirq() +is running in ksoftirqd context. A wrapper layer in interposed so that +other calls to __do_softirq() avoid invoking rcu_bh_qs(). The underlying +function __do_softirq_common() does the actual work. + +The reason that rcu_bh_qs() is bad in these non-ksoftirqd contexts is +that there might be a local_bh_enable() inside an RCU-preempt read-side +critical section. This local_bh_enable() can invoke __do_softirq() +directly, so if __do_softirq() were to invoke rcu_bh_qs() (which just +calls rcu_preempt_qs() in the PREEMPT_RT_FULL case), there would be +an illegal RCU-preempt quiescent state in the middle of an RCU-preempt +read-side critical section. Therefore, quiescent states can only happen +in cases where __do_softirq() is invoked directly from ksoftirqd. + +Signed-off-by: Paul E. McKenney +Link: http://lkml.kernel.org/r/20111005184518.GA21601@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner + +--- + kernel/rcu/tree.c | 14 +++++++++++++- + kernel/rcu/tree_plugin.h | 8 +++++++- + 2 files changed, 20 insertions(+), 2 deletions(-) + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -243,7 +243,19 @@ void rcu_sched_qs(void) + this_cpu_ptr(&rcu_sched_data), true); + } + +-#ifndef CONFIG_PREEMPT_RT_FULL ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void rcu_preempt_qs(void); ++ ++void rcu_bh_qs(void) ++{ ++ unsigned long flags; ++ ++ /* Callers to this function, rcu_preempt_qs(), must disable irqs. */ ++ local_irq_save(flags); ++ rcu_preempt_qs(); ++ local_irq_restore(flags); ++} ++#else + void rcu_bh_qs(void) + { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -29,6 +29,7 @@ + #include + #include + #include ++#include + #include + #include + #include "../time/tick-internal.h" +@@ -1336,7 +1337,7 @@ static void rcu_prepare_kthreads(int cpu + + #endif /* #else #ifdef CONFIG_RCU_BOOST */ + +-#if !defined(CONFIG_RCU_FAST_NO_HZ) ++#if !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) + + /* + * Check to see if any future RCU-related work will need to be done +@@ -1352,7 +1353,9 @@ int rcu_needs_cpu(u64 basemono, u64 *nex + *nextevt = KTIME_MAX; + return rcu_cpu_has_callbacks(NULL); + } ++#endif /* !defined(CONFIG_RCU_FAST_NO_HZ) || defined(CONFIG_PREEMPT_RT_FULL) */ + ++#if !defined(CONFIG_RCU_FAST_NO_HZ) + /* + * Because we do not have RCU_FAST_NO_HZ, don't bother cleaning up + * after it. +@@ -1448,6 +1451,8 @@ static bool __maybe_unused rcu_try_advan + return cbs_ready; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + /* + * Allow the CPU to enter dyntick-idle mode unless it has callbacks ready + * to invoke. If the CPU has callbacks, try to advance them. Tell the +@@ -1490,6 +1495,7 @@ int rcu_needs_cpu(u64 basemono, u64 *nex + *nextevt = basemono + dj * TICK_NSEC; + return 0; + } ++#endif /* #ifndef CONFIG_PREEMPT_RT_FULL */ + + /* + * Prepare a CPU for idle from an RCU perspective. The first major task diff --git a/debian/patches/features/all/rt/pci-switchtec-Don-t-use-completion-s-wait-queue.patch b/debian/patches/features/all/rt/pci-switchtec-Don-t-use-completion-s-wait-queue.patch new file mode 100644 index 000000000..bbf7a1413 --- /dev/null +++ b/debian/patches/features/all/rt/pci-switchtec-Don-t-use-completion-s-wait-queue.patch @@ -0,0 +1,109 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 4 Oct 2017 10:24:23 +0200 +Subject: [PATCH] pci/switchtec: Don't use completion's wait queue +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The poll callback is using completion's wait_queue_head_t member and +puts it in poll_wait() so the poll() caller gets a wakeup after command +completed. This does not work on RT because we don't have a +wait_queue_head_t in our completion implementation. Nobody in tree does +like that in tree so this is the only driver that breaks. + +Instead of using the completion here is waitqueue with a status flag as +suggested by Logan. + +I don't have the HW so I have no idea if it works as expected, so please +test it. + +Cc: Kurt Schwemmer +Cc: Logan Gunthorpe +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/pci/switch/switchtec.c | 22 +++++++++++++--------- + 1 file changed, 13 insertions(+), 9 deletions(-) + +--- a/drivers/pci/switch/switchtec.c ++++ b/drivers/pci/switch/switchtec.c +@@ -41,10 +41,11 @@ struct switchtec_user { + + enum mrpc_state state; + +- struct completion comp; ++ wait_queue_head_t cmd_comp; + struct kref kref; + struct list_head list; + ++ bool cmd_done; + u32 cmd; + u32 status; + u32 return_code; +@@ -66,7 +67,7 @@ static struct switchtec_user *stuser_cre + stuser->stdev = stdev; + kref_init(&stuser->kref); + INIT_LIST_HEAD(&stuser->list); +- init_completion(&stuser->comp); ++ init_waitqueue_head(&stuser->cmd_comp); + stuser->event_cnt = atomic_read(&stdev->event_cnt); + + dev_dbg(&stdev->dev, "%s: %p\n", __func__, stuser); +@@ -149,7 +150,7 @@ static int mrpc_queue_cmd(struct switcht + kref_get(&stuser->kref); + stuser->read_len = sizeof(stuser->data); + stuser_set_state(stuser, MRPC_QUEUED); +- init_completion(&stuser->comp); ++ stuser->cmd_done = false; + list_add_tail(&stuser->list, &stdev->mrpc_queue); + + mrpc_cmd_submit(stdev); +@@ -186,7 +187,8 @@ static void mrpc_complete_cmd(struct swi + stuser->read_len); + + out: +- complete_all(&stuser->comp); ++ stuser->cmd_done = true; ++ wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + stdev->mrpc_busy = 0; +@@ -456,10 +458,11 @@ static ssize_t switchtec_dev_read(struct + mutex_unlock(&stdev->mrpc_mutex); + + if (filp->f_flags & O_NONBLOCK) { +- if (!try_wait_for_completion(&stuser->comp)) ++ if (!READ_ONCE(stuser->cmd_done)) + return -EAGAIN; + } else { +- rc = wait_for_completion_interruptible(&stuser->comp); ++ rc = wait_event_interruptible(stuser->cmd_comp, ++ stuser->cmd_done); + if (rc < 0) + return rc; + } +@@ -507,7 +510,7 @@ static __poll_t switchtec_dev_poll(struc + struct switchtec_dev *stdev = stuser->stdev; + __poll_t ret = 0; + +- poll_wait(filp, &stuser->comp.wait, wait); ++ poll_wait(filp, &stuser->cmd_comp, wait); + poll_wait(filp, &stdev->event_wq, wait); + + if (lock_mutex_and_test_alive(stdev)) +@@ -515,7 +518,7 @@ static __poll_t switchtec_dev_poll(struc + + mutex_unlock(&stdev->mrpc_mutex); + +- if (try_wait_for_completion(&stuser->comp)) ++ if (READ_ONCE(stuser->cmd_done)) + ret |= EPOLLIN | EPOLLRDNORM; + + if (stuser->event_cnt != atomic_read(&stdev->event_cnt)) +@@ -1034,7 +1037,8 @@ static void stdev_kill(struct switchtec_ + + /* Wake up and kill any users waiting on an MRPC request */ + list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) { +- complete_all(&stuser->comp); ++ stuser->cmd_done = true; ++ wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + } diff --git a/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch b/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch new file mode 100644 index 000000000..04e453a20 --- /dev/null +++ b/debian/patches/features/all/rt/peter_zijlstra-frob-rcu.patch @@ -0,0 +1,167 @@ +Subject: rcu: Frob softirq test +From: Peter Zijlstra +Date: Sat Aug 13 00:23:17 CEST 2011 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +With RT_FULL we get the below wreckage: + +[ 126.060484] ======================================================= +[ 126.060486] [ INFO: possible circular locking dependency detected ] +[ 126.060489] 3.0.1-rt10+ #30 +[ 126.060490] ------------------------------------------------------- +[ 126.060492] irq/24-eth0/1235 is trying to acquire lock: +[ 126.060495] (&(lock)->wait_lock#2){+.+...}, at: [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060503] +[ 126.060504] but task is already holding lock: +[ 126.060506] (&p->pi_lock){-...-.}, at: [] try_to_wake_up+0x35/0x429 +[ 126.060511] +[ 126.060511] which lock already depends on the new lock. +[ 126.060513] +[ 126.060514] +[ 126.060514] the existing dependency chain (in reverse order) is: +[ 126.060516] +[ 126.060516] -> #1 (&p->pi_lock){-...-.}: +[ 126.060519] [] lock_acquire+0x145/0x18a +[ 126.060524] [] _raw_spin_lock_irqsave+0x4b/0x85 +[ 126.060527] [] task_blocks_on_rt_mutex+0x36/0x20f +[ 126.060531] [] rt_mutex_slowlock+0xd1/0x15a +[ 126.060534] [] rt_mutex_lock+0x2d/0x2f +[ 126.060537] [] rcu_boost+0xad/0xde +[ 126.060541] [] rcu_boost_kthread+0x7d/0x9b +[ 126.060544] [] kthread+0x99/0xa1 +[ 126.060547] [] kernel_thread_helper+0x4/0x10 +[ 126.060551] +[ 126.060552] -> #0 (&(lock)->wait_lock#2){+.+...}: +[ 126.060555] [] __lock_acquire+0x1157/0x1816 +[ 126.060558] [] lock_acquire+0x145/0x18a +[ 126.060561] [] _raw_spin_lock+0x40/0x73 +[ 126.060564] [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060566] [] rt_mutex_unlock+0x27/0x29 +[ 126.060569] [] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060573] [] __rcu_read_unlock+0x48/0x89 +[ 126.060576] [] select_task_rq_rt+0xc7/0xd5 +[ 126.060580] [] try_to_wake_up+0x175/0x429 +[ 126.060583] [] wake_up_process+0x15/0x17 +[ 126.060585] [] wakeup_softirqd+0x24/0x26 +[ 126.060590] [] irq_exit+0x49/0x55 +[ 126.060593] [] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060597] [] apic_timer_interrupt+0x13/0x20 +[ 126.060600] [] irq_forced_thread_fn+0x1b/0x44 +[ 126.060603] [] irq_thread+0xde/0x1af +[ 126.060606] [] kthread+0x99/0xa1 +[ 126.060608] [] kernel_thread_helper+0x4/0x10 +[ 126.060611] +[ 126.060612] other info that might help us debug this: +[ 126.060614] +[ 126.060615] Possible unsafe locking scenario: +[ 126.060616] +[ 126.060617] CPU0 CPU1 +[ 126.060619] ---- ---- +[ 126.060620] lock(&p->pi_lock); +[ 126.060623] lock(&(lock)->wait_lock); +[ 126.060625] lock(&p->pi_lock); +[ 126.060627] lock(&(lock)->wait_lock); +[ 126.060629] +[ 126.060629] *** DEADLOCK *** +[ 126.060630] +[ 126.060632] 1 lock held by irq/24-eth0/1235: +[ 126.060633] #0: (&p->pi_lock){-...-.}, at: [] try_to_wake_up+0x35/0x429 +[ 126.060638] +[ 126.060638] stack backtrace: +[ 126.060641] Pid: 1235, comm: irq/24-eth0 Not tainted 3.0.1-rt10+ #30 +[ 126.060643] Call Trace: +[ 126.060644] [] print_circular_bug+0x289/0x29a +[ 126.060651] [] __lock_acquire+0x1157/0x1816 +[ 126.060655] [] ? trace_hardirqs_off_caller+0x1f/0x99 +[ 126.060658] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060661] [] lock_acquire+0x145/0x18a +[ 126.060664] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060668] [] _raw_spin_lock+0x40/0x73 +[ 126.060671] [] ? rt_mutex_slowunlock+0x16/0x55 +[ 126.060674] [] ? rcu_report_qs_rsp+0x87/0x8c +[ 126.060677] [] rt_mutex_slowunlock+0x16/0x55 +[ 126.060680] [] ? rcu_read_unlock_special+0x9b/0x1c4 +[ 126.060683] [] rt_mutex_unlock+0x27/0x29 +[ 126.060687] [] rcu_read_unlock_special+0x17e/0x1c4 +[ 126.060690] [] __rcu_read_unlock+0x48/0x89 +[ 126.060693] [] select_task_rq_rt+0xc7/0xd5 +[ 126.060696] [] ? select_task_rq_rt+0x27/0xd5 +[ 126.060701] [] ? clockevents_program_event+0x8e/0x90 +[ 126.060704] [] try_to_wake_up+0x175/0x429 +[ 126.060708] [] ? tick_program_event+0x1f/0x21 +[ 126.060711] [] wake_up_process+0x15/0x17 +[ 126.060715] [] wakeup_softirqd+0x24/0x26 +[ 126.060718] [] irq_exit+0x49/0x55 +[ 126.060721] [] smp_apic_timer_interrupt+0x8a/0x98 +[ 126.060724] [] apic_timer_interrupt+0x13/0x20 +[ 126.060726] [] ? migrate_disable+0x75/0x12d +[ 126.060733] [] ? local_bh_disable+0xe/0x1f +[ 126.060736] [] ? local_bh_disable+0x1d/0x1f +[ 126.060739] [] irq_forced_thread_fn+0x1b/0x44 +[ 126.060742] [] ? _raw_spin_unlock_irq+0x3b/0x59 +[ 126.060745] [] irq_thread+0xde/0x1af +[ 126.060748] [] ? irq_thread_fn+0x3a/0x3a +[ 126.060751] [] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060754] [] ? irq_finalize_oneshot+0xd1/0xd1 +[ 126.060757] [] kthread+0x99/0xa1 +[ 126.060761] [] kernel_thread_helper+0x4/0x10 +[ 126.060764] [] ? finish_task_switch+0x87/0x10a +[ 126.060768] [] ? retint_restore_args+0xe/0xe +[ 126.060771] [] ? __init_kthread_worker+0x8c/0x8c +[ 126.060774] [] ? gs_change+0xb/0xb + +Because irq_exit() does: + +void irq_exit(void) +{ + account_system_vtime(current); + trace_hardirq_exit(); + sub_preempt_count(IRQ_EXIT_OFFSET); + if (!in_interrupt() && local_softirq_pending()) + invoke_softirq(); + + ... +} + +Which triggers a wakeup, which uses RCU, now if the interrupted task has +t->rcu_read_unlock_special set, the rcu usage from the wakeup will end +up in rcu_read_unlock_special(). rcu_read_unlock_special() will test +for in_irq(), which will fail as we just decremented preempt_count +with IRQ_EXIT_OFFSET, and in_sering_softirq(), which for +PREEMPT_RT_FULL reads: + +int in_serving_softirq(void) +{ + int res; + + preempt_disable(); + res = __get_cpu_var(local_softirq_runner) == current; + preempt_enable(); + return res; +} + +Which will thus also fail, resulting in the above wreckage. + +The 'somewhat' ugly solution is to open-code the preempt_count() test +in rcu_read_unlock_special(). + +Also, we're not at all sure how ->rcu_read_unlock_special gets set +here... so this is very likely a bandaid and more thought is required. + +Cc: Paul E. McKenney +Signed-off-by: Peter Zijlstra +--- + kernel/rcu/tree_plugin.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -512,7 +512,7 @@ void rcu_read_unlock_special(struct task + } + + /* Hardware IRQ handlers cannot block, complain if they get here. */ +- if (in_irq() || in_serving_softirq()) { ++ if (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_OFFSET)) { + lockdep_rcu_suspicious(__FILE__, __LINE__, + "rcu_read_unlock() from irq or softirq with blocking in critical section!!!\n"); + pr_alert("->rcu_read_unlock_special: %#x (b: %d, enq: %d nq: %d)\n", diff --git a/debian/patches/features/all/rt/peterz-percpu-rwsem-rt.patch b/debian/patches/features/all/rt/peterz-percpu-rwsem-rt.patch new file mode 100644 index 000000000..c1f1f475f --- /dev/null +++ b/debian/patches/features/all/rt/peterz-percpu-rwsem-rt.patch @@ -0,0 +1,219 @@ +Subject: locking/percpu-rwsem: Remove preempt_disable variants +From: Peter Zijlstra +Date: Wed Nov 23 16:29:32 CET 2016 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Effective revert commit: + + 87709e28dc7c ("fs/locks: Use percpu_down_read_preempt_disable()") + +This is causing major pain for PREEMPT_RT and is only a very small +performance issue for PREEMPT=y. + +Signed-off-by: Peter Zijlstra (Intel) +--- +--- + fs/locks.c | 32 ++++++++++++++++---------------- + include/linux/percpu-rwsem.h | 24 ++++-------------------- + 2 files changed, 20 insertions(+), 36 deletions(-) + +--- a/fs/locks.c ++++ b/fs/locks.c +@@ -945,7 +945,7 @@ static int flock_lock_inode(struct inode + return -ENOMEM; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + if (request->fl_flags & FL_ACCESS) + goto find_conflict; +@@ -986,7 +986,7 @@ static int flock_lock_inode(struct inode + + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + if (new_fl) + locks_free_lock(new_fl); + locks_dispose_list(&dispose); +@@ -1023,7 +1023,7 @@ static int posix_lock_inode(struct inode + new_fl2 = locks_alloc_lock(); + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + /* + * New lock request. Walk all POSIX locks and look for conflicts. If +@@ -1195,7 +1195,7 @@ static int posix_lock_inode(struct inode + } + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + /* + * Free any unused locks. + */ +@@ -1470,7 +1470,7 @@ int __break_lease(struct inode *inode, u + return error; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + + time_out_leases(inode, &dispose); +@@ -1522,13 +1522,13 @@ int __break_lease(struct inode *inode, u + locks_insert_block(fl, new_fl); + trace_break_lease_block(inode, new_fl); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + error = wait_event_interruptible_timeout(new_fl->fl_wait, + !new_fl->fl_next, break_time); + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + trace_break_lease_unblock(inode, new_fl); + locks_delete_block(new_fl); +@@ -1545,7 +1545,7 @@ int __break_lease(struct inode *inode, u + } + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + locks_free_lock(new_fl); + return error; +@@ -1617,7 +1617,7 @@ int fcntl_getlease(struct file *filp) + + ctx = smp_load_acquire(&inode->i_flctx); + if (ctx && !list_empty_careful(&ctx->flc_lease)) { +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + time_out_leases(inode, &dispose); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { +@@ -1627,7 +1627,7 @@ int fcntl_getlease(struct file *filp) + break; + } + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + } +@@ -1702,7 +1702,7 @@ generic_add_lease(struct file *filp, lon + return -EINVAL; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + time_out_leases(inode, &dispose); + error = check_conflicting_open(dentry, arg, lease->fl_flags); +@@ -1773,7 +1773,7 @@ generic_add_lease(struct file *filp, lon + lease->fl_lmops->lm_setup(lease, priv); + out: + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + if (is_deleg) + inode_unlock(inode); +@@ -1796,7 +1796,7 @@ static int generic_delete_lease(struct f + return error; + } + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + list_for_each_entry(fl, &ctx->flc_lease, fl_list) { + if (fl->fl_file == filp && +@@ -1809,7 +1809,7 @@ static int generic_delete_lease(struct f + if (victim) + error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + locks_dispose_list(&dispose); + return error; + } +@@ -2533,13 +2533,13 @@ locks_remove_lease(struct file *filp, st + if (list_empty(&ctx->flc_lease)) + return; + +- percpu_down_read_preempt_disable(&file_rwsem); ++ percpu_down_read(&file_rwsem); + spin_lock(&ctx->flc_lock); + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) + if (filp == fl->fl_file) + lease_modify(fl, F_UNLCK, &dispose); + spin_unlock(&ctx->flc_lock); +- percpu_up_read_preempt_enable(&file_rwsem); ++ percpu_up_read(&file_rwsem); + + locks_dispose_list(&dispose); + } +--- a/include/linux/percpu-rwsem.h ++++ b/include/linux/percpu-rwsem.h +@@ -29,7 +29,7 @@ static struct percpu_rw_semaphore name = + extern int __percpu_down_read(struct percpu_rw_semaphore *, int); + extern void __percpu_up_read(struct percpu_rw_semaphore *); + +-static inline void percpu_down_read_preempt_disable(struct percpu_rw_semaphore *sem) ++static inline void percpu_down_read(struct percpu_rw_semaphore *sem) + { + might_sleep(); + +@@ -47,16 +47,10 @@ static inline void percpu_down_read_pree + __this_cpu_inc(*sem->read_count); + if (unlikely(!rcu_sync_is_idle(&sem->rss))) + __percpu_down_read(sem, false); /* Unconditional memory barrier */ +- barrier(); + /* +- * The barrier() prevents the compiler from ++ * The preempt_enable() prevents the compiler from + * bleeding the critical section out. + */ +-} +- +-static inline void percpu_down_read(struct percpu_rw_semaphore *sem) +-{ +- percpu_down_read_preempt_disable(sem); + preempt_enable(); + } + +@@ -83,13 +77,9 @@ static inline int percpu_down_read_trylo + return ret; + } + +-static inline void percpu_up_read_preempt_enable(struct percpu_rw_semaphore *sem) ++static inline void percpu_up_read(struct percpu_rw_semaphore *sem) + { +- /* +- * The barrier() prevents the compiler from +- * bleeding the critical section out. +- */ +- barrier(); ++ preempt_disable(); + /* + * Same as in percpu_down_read(). + */ +@@ -102,12 +92,6 @@ static inline void percpu_up_read_preemp + rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); + } + +-static inline void percpu_up_read(struct percpu_rw_semaphore *sem) +-{ +- preempt_disable(); +- percpu_up_read_preempt_enable(sem); +-} +- + extern void percpu_down_write(struct percpu_rw_semaphore *); + extern void percpu_up_write(struct percpu_rw_semaphore *); + diff --git a/debian/patches/features/all/rt/pid.h-include-atomic.h.patch b/debian/patches/features/all/rt/pid.h-include-atomic.h.patch new file mode 100644 index 000000000..c1621b3b3 --- /dev/null +++ b/debian/patches/features/all/rt/pid.h-include-atomic.h.patch @@ -0,0 +1,37 @@ +From: Grygorii Strashko +Date: Tue, 21 Jul 2015 19:43:56 +0300 +Subject: pid.h: include atomic.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This patch fixes build error: + CC kernel/pid_namespace.o +In file included from kernel/pid_namespace.c:11:0: +include/linux/pid.h: In function 'get_pid': +include/linux/pid.h:78:3: error: implicit declaration of function 'atomic_inc' [-Werror=implicit-function-declaration] + atomic_inc(&pid->count); + ^ +which happens when + CONFIG_PROVE_LOCKING=n + CONFIG_DEBUG_SPINLOCK=n + CONFIG_DEBUG_MUTEXES=n + CONFIG_DEBUG_LOCK_ALLOC=n + CONFIG_PID_NS=y + +Vanilla gets this via spinlock.h. + +Signed-off-by: Grygorii Strashko +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/pid.h | 1 + + 1 file changed, 1 insertion(+) + +--- a/include/linux/pid.h ++++ b/include/linux/pid.h +@@ -3,6 +3,7 @@ + #define _LINUX_PID_H + + #include ++#include + + enum pid_type + { diff --git a/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch b/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch new file mode 100644 index 000000000..2e0e8ad47 --- /dev/null +++ b/debian/patches/features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch @@ -0,0 +1,258 @@ +From: John Stultz +Date: Fri, 3 Jul 2009 08:29:58 -0500 +Subject: posix-timers: Thread posix-cpu-timers on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +posix-cpu-timer code takes non -rt safe locks in hard irq +context. Move it to a thread. + +[ 3.0 fixes from Peter Zijlstra ] + +Signed-off-by: John Stultz +Signed-off-by: Thomas Gleixner + +--- + include/linux/sched.h | 3 + init/init_task.c | 7 + + kernel/fork.c | 3 + kernel/time/posix-cpu-timers.c | 154 ++++++++++++++++++++++++++++++++++++++++- + 4 files changed, 164 insertions(+), 3 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -827,6 +827,9 @@ struct task_struct { + #ifdef CONFIG_POSIX_TIMERS + struct task_cputime cputime_expires; + struct list_head cpu_timers[3]; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct task_struct *posix_timer_list; ++#endif + #endif + + /* Process credentials: */ +--- a/init/init_task.c ++++ b/init/init_task.c +@@ -43,6 +43,12 @@ static struct sighand_struct init_sighan + .signalfd_wqh = __WAIT_QUEUE_HEAD_INITIALIZER(init_sighand.signalfd_wqh), + }; + ++#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE) ++# define INIT_TIMER_LIST .posix_timer_list = NULL, ++#else ++# define INIT_TIMER_LIST ++#endif ++ + /* + * Set up the first task table, touch at your own risk!. Base=0, + * limit=0x1fffff (=2MB) +@@ -112,6 +118,7 @@ struct task_struct init_task + INIT_CPU_TIMERS(init_task) + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock), + .timer_slack_ns = 50000, /* 50 usec default slack */ ++ INIT_TIMER_LIST + .pids = { + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1563,6 +1563,9 @@ static void rt_mutex_init_task(struct ta + */ + static void posix_cpu_timers_init(struct task_struct *tsk) + { ++#ifdef CONFIG_PREEMPT_RT_BASE ++ tsk->posix_timer_list = NULL; ++#endif + tsk->cputime_expires.prof_exp = 0; + tsk->cputime_expires.virt_exp = 0; + tsk->cputime_expires.sched_exp = 0; +--- a/kernel/time/posix-cpu-timers.c ++++ b/kernel/time/posix-cpu-timers.c +@@ -3,8 +3,10 @@ + * Implement CPU time clocks for the POSIX clock interface. + */ + ++#include + #include + #include ++#include + #include + #include + #include +@@ -15,6 +17,7 @@ + #include + #include + #include ++#include + + #include "posix-timers.h" + +@@ -1135,14 +1138,12 @@ static inline int fastpath_timer_check(s + * already updated our counts. We need to check if any timers fire now. + * Interrupts are disabled. + */ +-void run_posix_cpu_timers(struct task_struct *tsk) ++static void __run_posix_cpu_timers(struct task_struct *tsk) + { + LIST_HEAD(firing); + struct k_itimer *timer, *next; + unsigned long flags; + +- lockdep_assert_irqs_disabled(); +- + /* + * The fast path checks that there are no expired thread or thread + * group timers. If that's so, just return. +@@ -1195,6 +1196,153 @@ void run_posix_cpu_timers(struct task_st + } + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++#include ++#include ++DEFINE_PER_CPU(struct task_struct *, posix_timer_task); ++DEFINE_PER_CPU(struct task_struct *, posix_timer_tasklist); ++DEFINE_PER_CPU(bool, posix_timer_th_active); ++ ++static void posix_cpu_kthread_fn(unsigned int cpu) ++{ ++ struct task_struct *tsk = NULL; ++ struct task_struct *next = NULL; ++ ++ BUG_ON(per_cpu(posix_timer_task, cpu) != current); ++ ++ /* grab task list */ ++ raw_local_irq_disable(); ++ tsk = per_cpu(posix_timer_tasklist, cpu); ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ raw_local_irq_enable(); ++ ++ /* its possible the list is empty, just return */ ++ if (!tsk) ++ return; ++ ++ /* Process task list */ ++ while (1) { ++ /* save next */ ++ next = tsk->posix_timer_list; ++ ++ /* run the task timers, clear its ptr and ++ * unreference it ++ */ ++ __run_posix_cpu_timers(tsk); ++ tsk->posix_timer_list = NULL; ++ put_task_struct(tsk); ++ ++ /* check if this is the last on the list */ ++ if (next == tsk) ++ break; ++ tsk = next; ++ } ++} ++ ++static inline int __fastpath_timer_check(struct task_struct *tsk) ++{ ++ /* tsk == current, ensure it is safe to use ->signal/sighand */ ++ if (unlikely(tsk->exit_state)) ++ return 0; ++ ++ if (!task_cputime_zero(&tsk->cputime_expires)) ++ return 1; ++ ++ if (!task_cputime_zero(&tsk->signal->cputime_expires)) ++ return 1; ++ ++ return 0; ++} ++ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ unsigned int cpu = smp_processor_id(); ++ struct task_struct *tasklist; ++ ++ BUG_ON(!irqs_disabled()); ++ ++ if (per_cpu(posix_timer_th_active, cpu) != true) ++ return; ++ ++ /* get per-cpu references */ ++ tasklist = per_cpu(posix_timer_tasklist, cpu); ++ ++ /* check to see if we're already queued */ ++ if (!tsk->posix_timer_list && __fastpath_timer_check(tsk)) { ++ get_task_struct(tsk); ++ if (tasklist) { ++ tsk->posix_timer_list = tasklist; ++ } else { ++ /* ++ * The list is terminated by a self-pointing ++ * task_struct ++ */ ++ tsk->posix_timer_list = tsk; ++ } ++ per_cpu(posix_timer_tasklist, cpu) = tsk; ++ ++ wake_up_process(per_cpu(posix_timer_task, cpu)); ++ } ++} ++ ++static int posix_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(posix_timer_tasklist) != NULL; ++} ++ ++static void posix_cpu_kthread_park(unsigned int cpu) ++{ ++ this_cpu_write(posix_timer_th_active, false); ++} ++ ++static void posix_cpu_kthread_unpark(unsigned int cpu) ++{ ++ this_cpu_write(posix_timer_th_active, true); ++} ++ ++static void posix_cpu_kthread_setup(unsigned int cpu) ++{ ++ struct sched_param sp; ++ ++ sp.sched_priority = MAX_RT_PRIO - 1; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++ posix_cpu_kthread_unpark(cpu); ++} ++ ++static struct smp_hotplug_thread posix_cpu_thread = { ++ .store = &posix_timer_task, ++ .thread_should_run = posix_cpu_kthread_should_run, ++ .thread_fn = posix_cpu_kthread_fn, ++ .thread_comm = "posixcputmr/%u", ++ .setup = posix_cpu_kthread_setup, ++ .park = posix_cpu_kthread_park, ++ .unpark = posix_cpu_kthread_unpark, ++}; ++ ++static int __init posix_cpu_thread_init(void) ++{ ++ /* Start one for boot CPU. */ ++ unsigned long cpu; ++ int ret; ++ ++ /* init the per-cpu posix_timer_tasklets */ ++ for_each_possible_cpu(cpu) ++ per_cpu(posix_timer_tasklist, cpu) = NULL; ++ ++ ret = smpboot_register_percpu_thread(&posix_cpu_thread); ++ WARN_ON(ret); ++ ++ return 0; ++} ++early_initcall(posix_cpu_thread_init); ++#else /* CONFIG_PREEMPT_RT_BASE */ ++void run_posix_cpu_timers(struct task_struct *tsk) ++{ ++ lockdep_assert_irqs_disabled(); ++ __run_posix_cpu_timers(tsk); ++} ++#endif /* CONFIG_PREEMPT_RT_BASE */ ++ + /* + * Set one of the process-wide special case CPU timers or RLIMIT_CPU. + * The tsk->sighand->siglock must be held by the caller. diff --git a/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch b/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch new file mode 100644 index 000000000..fab96ab80 --- /dev/null +++ b/debian/patches/features/all/rt/power-disable-highmem-on-rt.patch @@ -0,0 +1,23 @@ +Subject: powerpc: Disable highmem on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:08:34 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The current highmem handling on -RT is not compatible and needs fixups. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -395,7 +395,7 @@ menu "Kernel options" + + config HIGHMEM + bool "High memory support" +- depends on PPC32 ++ depends on PPC32 && !PREEMPT_RT_FULL + + source kernel/Kconfig.hz + source kernel/Kconfig.preempt diff --git a/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch b/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch new file mode 100644 index 000000000..6efc827da --- /dev/null +++ b/debian/patches/features/all/rt/power-use-generic-rwsem-on-rt.patch @@ -0,0 +1,27 @@ +From: Thomas Gleixner +Date: Tue, 14 Jul 2015 14:26:34 +0200 +Subject: powerpc: Use generic rwsem on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Use generic code which uses rtmutex + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -105,10 +105,11 @@ config LOCKDEP_SUPPORT + + config RWSEM_GENERIC_SPINLOCK + bool ++ default y if PREEMPT_RT_FULL + + config RWSEM_XCHGADD_ALGORITHM + bool +- default y ++ default y if !PREEMPT_RT_FULL + + config GENERIC_LOCKBREAK + bool diff --git a/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch b/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch new file mode 100644 index 000000000..06349503e --- /dev/null +++ b/debian/patches/features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch @@ -0,0 +1,38 @@ +From: Bogdan Purcareata +Date: Fri, 24 Apr 2015 15:53:13 +0000 +Subject: powerpc/kvm: Disable in-kernel MPIC emulation for PREEMPT_RT_FULL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +While converting the openpic emulation code to use a raw_spinlock_t enables +guests to run on RT, there's still a performance issue. For interrupts sent in +directed delivery mode with a multiple CPU mask, the emulated openpic will loop +through all of the VCPUs, and for each VCPUs, it call IRQ_check, which will loop +through all the pending interrupts for that VCPU. This is done while holding the +raw_lock, meaning that in all this time the interrupts and preemption are +disabled on the host Linux. A malicious user app can max both these number and +cause a DoS. + +This temporary fix is sent for two reasons. First is so that users who want to +use the in-kernel MPIC emulation are aware of the potential latencies, thus +making sure that the hardware MPIC and their usage scenario does not involve +interrupts sent in directed delivery mode, and the number of possible pending +interrupts is kept small. Secondly, this should incentivize the development of a +proper openpic emulation that would be better suited for RT. + +Acked-by: Scott Wood +Signed-off-by: Bogdan Purcareata +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/powerpc/kvm/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/arch/powerpc/kvm/Kconfig ++++ b/arch/powerpc/kvm/Kconfig +@@ -178,6 +178,7 @@ config KVM_E500MC + config KVM_MPIC + bool "KVM in-kernel MPIC emulation" + depends on KVM && E500 ++ depends on !PREEMPT_RT_FULL + select HAVE_KVM_IRQCHIP + select HAVE_KVM_IRQFD + select HAVE_KVM_IRQ_ROUTING diff --git a/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch b/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch new file mode 100644 index 000000000..23fd39813 --- /dev/null +++ b/debian/patches/features/all/rt/powerpc-preempt-lazy-support.patch @@ -0,0 +1,164 @@ +From: Thomas Gleixner +Date: Thu, 1 Nov 2012 10:14:11 +0100 +Subject: powerpc: Add support for lazy preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Implement the powerpc pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/Kconfig | 1 + + arch/powerpc/include/asm/thread_info.h | 7 ++++++- + arch/powerpc/kernel/asm-offsets.c | 1 + + arch/powerpc/kernel/entry_32.S | 17 ++++++++++++----- + arch/powerpc/kernel/entry_64.S | 14 +++++++++++--- + 5 files changed, 31 insertions(+), 9 deletions(-) + +--- a/arch/powerpc/Kconfig ++++ b/arch/powerpc/Kconfig +@@ -215,6 +215,7 @@ config PPC + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI && !HAVE_HARDLOCKUP_DETECTOR_ARCH + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE if SMP + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE if PPC64 && CPU_LITTLE_ENDIAN +--- a/arch/powerpc/include/asm/thread_info.h ++++ b/arch/powerpc/include/asm/thread_info.h +@@ -36,6 +36,8 @@ struct thread_info { + int cpu; /* cpu we're on */ + int preempt_count; /* 0 => preemptable, + <0 => BUG */ ++ int preempt_lazy_count; /* 0 => preemptable, ++ <0 => BUG */ + unsigned long local_flags; /* private flags for thread */ + #ifdef CONFIG_LIVEPATCH + unsigned long *livepatch_sp; +@@ -99,6 +101,7 @@ extern int arch_dup_task_struct(struct t + #define TIF_ELF2ABI 18 /* function descriptors must die! */ + #endif + #define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling TIF_NEED_RESCHED */ ++#define TIF_NEED_RESCHED_LAZY 20 /* lazy rescheduling necessary */ + + /* as above, but as bit values */ + #define _TIF_SYSCALL_TRACE (1< +Date: Sun, 31 May 2015 14:44:42 -0400 +Subject: powerpc: ps3/device-init.c - adapt to completions using swait vs wait +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +To fix: + + cc1: warnings being treated as errors + arch/powerpc/platforms/ps3/device-init.c: In function 'ps3_notification_read_write': + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'prepare_to_wait_event' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'abort_exclusive_wait' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.c:755:2: error: passing argument 1 of 'finish_wait' from incompatible pointer type + arch/powerpc/platforms/ps3/device-init.o] Error 1 + make[3]: *** Waiting for unfinished jobs.... + +Signed-off-by: Paul Gortmaker +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/powerpc/platforms/ps3/device-init.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/powerpc/platforms/ps3/device-init.c ++++ b/arch/powerpc/platforms/ps3/device-init.c +@@ -752,7 +752,7 @@ static int ps3_notification_read_write(s + } + pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op); + +- res = wait_event_interruptible(dev->done.wait, ++ res = swait_event_interruptible(dev->done.wait, + dev->done.done || kthread_should_stop()); + if (kthread_should_stop()) + res = -EINTR; diff --git a/debian/patches/features/all/rt/preempt-lazy-support.patch b/debian/patches/features/all/rt/preempt-lazy-support.patch new file mode 100644 index 000000000..f97eb5daf --- /dev/null +++ b/debian/patches/features/all/rt/preempt-lazy-support.patch @@ -0,0 +1,624 @@ +Subject: sched: Add support for lazy preemption +From: Thomas Gleixner +Date: Fri, 26 Oct 2012 18:50:54 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +It has become an obsession to mitigate the determinism vs. throughput +loss of RT. Looking at the mainline semantics of preemption points +gives a hint why RT sucks throughput wise for ordinary SCHED_OTHER +tasks. One major issue is the wakeup of tasks which are right away +preempting the waking task while the waking task holds a lock on which +the woken task will block right after having preempted the wakee. In +mainline this is prevented due to the implicit preemption disable of +spin/rw_lock held regions. On RT this is not possible due to the fully +preemptible nature of sleeping spinlocks. + +Though for a SCHED_OTHER task preempting another SCHED_OTHER task this +is really not a correctness issue. RT folks are concerned about +SCHED_FIFO/RR tasks preemption and not about the purely fairness +driven SCHED_OTHER preemption latencies. + +So I introduced a lazy preemption mechanism which only applies to +SCHED_OTHER tasks preempting another SCHED_OTHER task. Aside of the +existing preempt_count each tasks sports now a preempt_lazy_count +which is manipulated on lock acquiry and release. This is slightly +incorrect as for lazyness reasons I coupled this on +migrate_disable/enable so some other mechanisms get the same treatment +(e.g. get_cpu_light). + +Now on the scheduler side instead of setting NEED_RESCHED this sets +NEED_RESCHED_LAZY in case of a SCHED_OTHER/SCHED_OTHER preemption and +therefor allows to exit the waking task the lock held region before +the woken task preempts. That also works better for cross CPU wakeups +as the other side can stay in the adaptive spinning loop. + +For RT class preemption there is no change. This simply sets +NEED_RESCHED and forgoes the lazy preemption counter. + + Initial test do not expose any observable latency increasement, but +history shows that I've been proven wrong before :) + +The lazy preemption mode is per default on, but with +CONFIG_SCHED_DEBUG enabled it can be disabled via: + + # echo NO_PREEMPT_LAZY >/sys/kernel/debug/sched_features + +and reenabled via + + # echo PREEMPT_LAZY >/sys/kernel/debug/sched_features + +The test results so far are very machine and workload dependent, but +there is a clear trend that it enhances the non RT workload +performance. + +Signed-off-by: Thomas Gleixner +--- + include/linux/preempt.h | 35 +++++++++++++++++- + include/linux/sched.h | 38 +++++++++++++++++++ + include/linux/thread_info.h | 12 +++++- + include/linux/trace_events.h | 1 + kernel/Kconfig.preempt | 6 +++ + kernel/sched/core.c | 83 +++++++++++++++++++++++++++++++++++++++++-- + kernel/sched/fair.c | 16 ++++---- + kernel/sched/features.h | 3 + + kernel/sched/sched.h | 9 ++++ + kernel/trace/trace.c | 36 ++++++++++-------- + kernel/trace/trace.h | 2 + + kernel/trace/trace_output.c | 14 ++++++- + 12 files changed, 226 insertions(+), 29 deletions(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -180,6 +180,20 @@ extern void preempt_count_sub(int val); + #define preempt_count_inc() preempt_count_add(1) + #define preempt_count_dec() preempt_count_sub(1) + ++#ifdef CONFIG_PREEMPT_LAZY ++#define add_preempt_lazy_count(val) do { preempt_lazy_count() += (val); } while (0) ++#define sub_preempt_lazy_count(val) do { preempt_lazy_count() -= (val); } while (0) ++#define inc_preempt_lazy_count() add_preempt_lazy_count(1) ++#define dec_preempt_lazy_count() sub_preempt_lazy_count(1) ++#define preempt_lazy_count() (current_thread_info()->preempt_lazy_count) ++#else ++#define add_preempt_lazy_count(val) do { } while (0) ++#define sub_preempt_lazy_count(val) do { } while (0) ++#define inc_preempt_lazy_count() do { } while (0) ++#define dec_preempt_lazy_count() do { } while (0) ++#define preempt_lazy_count() (0) ++#endif ++ + #ifdef CONFIG_PREEMPT_COUNT + + #define preempt_disable() \ +@@ -188,6 +202,12 @@ do { \ + barrier(); \ + } while (0) + ++#define preempt_lazy_disable() \ ++do { \ ++ inc_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define sched_preempt_enable_no_resched() \ + do { \ + barrier(); \ +@@ -250,6 +270,13 @@ do { \ + __preempt_schedule(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++ preempt_check_resched(); \ ++} while (0) ++ + #else /* !CONFIG_PREEMPT */ + #define preempt_enable() \ + do { \ +@@ -257,6 +284,12 @@ do { \ + preempt_count_dec(); \ + } while (0) + ++#define preempt_lazy_enable() \ ++do { \ ++ dec_preempt_lazy_count(); \ ++ barrier(); \ ++} while (0) ++ + #define preempt_enable_notrace() \ + do { \ + barrier(); \ +@@ -323,7 +356,7 @@ do { \ + } while (0) + #define preempt_fold_need_resched() \ + do { \ +- if (tif_need_resched()) \ ++ if (tif_need_resched_now()) \ + set_preempt_need_resched(); \ + } while (0) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1723,6 +1723,44 @@ static inline int test_tsk_need_resched( + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++static inline void set_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ set_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ clear_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int test_tsk_need_resched_lazy(struct task_struct *tsk) ++{ ++ return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED_LAZY)); ++} ++ ++static inline int need_resched_lazy(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++} ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#else ++static inline void clear_tsk_need_resched_lazy(struct task_struct *tsk) { } ++static inline int need_resched_lazy(void) { return 0; } ++ ++static inline int need_resched_now(void) ++{ ++ return test_thread_flag(TIF_NEED_RESCHED); ++} ++ ++#endif ++ ++ + static inline bool __task_is_stopped_or_traced(struct task_struct *task) + { + if (task->state & (__TASK_STOPPED | __TASK_TRACED)) +--- a/include/linux/thread_info.h ++++ b/include/linux/thread_info.h +@@ -97,7 +97,17 @@ static inline int test_ti_thread_flag(st + #define test_thread_flag(flag) \ + test_ti_thread_flag(current_thread_info(), flag) + +-#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#ifdef CONFIG_PREEMPT_LAZY ++#define tif_need_resched() (test_thread_flag(TIF_NEED_RESCHED) || \ ++ test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++#define tif_need_resched_now() (test_thread_flag(TIF_NEED_RESCHED)) ++#define tif_need_resched_lazy() test_thread_flag(TIF_NEED_RESCHED_LAZY)) ++ ++#else ++#define tif_need_resched() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_now() test_thread_flag(TIF_NEED_RESCHED) ++#define tif_need_resched_lazy() 0 ++#endif + + #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES + static inline int arch_within_stack_frames(const void * const stack, +--- a/include/linux/trace_events.h ++++ b/include/linux/trace_events.h +@@ -64,6 +64,7 @@ struct trace_entry { + int pid; + unsigned short migrate_disable; + unsigned short padding; ++ unsigned char preempt_lazy_count; + }; + + #define TRACE_EVENT_TYPE_MAX \ +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -6,6 +6,12 @@ config PREEMPT_RT_BASE + bool + select PREEMPT + ++config HAVE_PREEMPT_LAZY ++ bool ++ ++config PREEMPT_LAZY ++ def_bool y if HAVE_PREEMPT_LAZY && PREEMPT_RT_FULL ++ + choice + prompt "Preemption Model" + default PREEMPT_NONE +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -498,6 +498,48 @@ void resched_curr(struct rq *rq) + trace_sched_wake_idle_without_ipi(cpu); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++ ++static int tsk_is_polling(struct task_struct *p) ++{ ++#ifdef TIF_POLLING_NRFLAG ++ return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG); ++#else ++ return 0; ++#endif ++} ++ ++void resched_curr_lazy(struct rq *rq) ++{ ++ struct task_struct *curr = rq->curr; ++ int cpu; ++ ++ if (!sched_feat(PREEMPT_LAZY)) { ++ resched_curr(rq); ++ return; ++ } ++ ++ lockdep_assert_held(&rq->lock); ++ ++ if (test_tsk_need_resched(curr)) ++ return; ++ ++ if (test_tsk_need_resched_lazy(curr)) ++ return; ++ ++ set_tsk_need_resched_lazy(curr); ++ ++ cpu = cpu_of(rq); ++ if (cpu == smp_processor_id()) ++ return; ++ ++ /* NEED_RESCHED_LAZY must be visible before we test polling */ ++ smp_mb(); ++ if (!tsk_is_polling(curr)) ++ smp_send_reschedule(cpu); ++} ++#endif ++ + void resched_cpu(int cpu) + { + struct rq *rq = cpu_rq(cpu); +@@ -2428,6 +2470,9 @@ int sched_fork(unsigned long clone_flags + p->on_cpu = 0; + #endif + init_task_preempt_count(p); ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(p)->preempt_lazy_count = 0; ++#endif + #ifdef CONFIG_SMP + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); +@@ -3493,6 +3538,7 @@ static void __sched notrace __schedule(b + + next = pick_next_task(rq, prev, &rf); + clear_tsk_need_resched(prev); ++ clear_tsk_need_resched_lazy(prev); + clear_preempt_need_resched(); + + if (likely(prev != next)) { +@@ -3673,6 +3719,30 @@ static void __sched notrace preempt_sche + } while (need_resched()); + } + ++#ifdef CONFIG_PREEMPT_LAZY ++/* ++ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is ++ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as ++ * preempt_lazy_count counter >0. ++ */ ++static __always_inline int preemptible_lazy(void) ++{ ++ if (test_thread_flag(TIF_NEED_RESCHED)) ++ return 1; ++ if (current_thread_info()->preempt_lazy_count) ++ return 0; ++ return 1; ++} ++ ++#else ++ ++static inline int preemptible_lazy(void) ++{ ++ return 1; ++} ++ ++#endif ++ + #ifdef CONFIG_PREEMPT + /* + * this is the entry point to schedule() from in-kernel preemption +@@ -3687,7 +3757,8 @@ asmlinkage __visible void __sched notrac + */ + if (likely(!preemptible())) + return; +- ++ if (!preemptible_lazy()) ++ return; + preempt_schedule_common(); + } + NOKPROBE_SYMBOL(preempt_schedule); +@@ -3714,6 +3785,9 @@ asmlinkage __visible void __sched notrac + if (likely(!preemptible())) + return; + ++ if (!preemptible_lazy()) ++ return; ++ + do { + /* + * Because the function tracer can trace preempt_count_sub() +@@ -5482,7 +5556,9 @@ void init_idle(struct task_struct *idle, + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); +- ++#ifdef CONFIG_HAVE_PREEMPT_LAZY ++ task_thread_info(idle)->preempt_lazy_count = 0; ++#endif + /* + * The idle tasks have their own, simple scheduling class: + */ +@@ -7204,6 +7280,7 @@ void migrate_disable(void) + } + + preempt_disable(); ++ preempt_lazy_disable(); + pin_current_cpu(); + + migrate_disable_update_cpus_allowed(p); +@@ -7271,6 +7348,7 @@ void migrate_enable(void) + arg.dest_cpu = dest_cpu; + + unpin_current_cpu(); ++ preempt_lazy_enable(); + preempt_enable(); + stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg); + tlb_migrate_finish(p->mm); +@@ -7279,6 +7357,7 @@ void migrate_enable(void) + } + } + unpin_current_cpu(); ++ preempt_lazy_enable(); + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); +--- a/kernel/sched/fair.c ++++ b/kernel/sched/fair.c +@@ -4336,7 +4336,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq + ideal_runtime = sched_slice(cfs_rq, curr); + delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; + if (delta_exec > ideal_runtime) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + /* + * The current task ran long enough, ensure it doesn't get + * re-elected due to buddy favours. +@@ -4360,7 +4360,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq + return; + + if (delta > ideal_runtime) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static void +@@ -4502,7 +4502,7 @@ entity_tick(struct cfs_rq *cfs_rq, struc + * validating it and just reschedule. + */ + if (queued) { +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + return; + } + /* +@@ -4686,7 +4686,7 @@ static void __account_cfs_rq_runtime(str + * hierarchy can be throttled + */ + if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr)) +- resched_curr(rq_of(cfs_rq)); ++ resched_curr_lazy(rq_of(cfs_rq)); + } + + static __always_inline +@@ -5340,7 +5340,7 @@ static void hrtick_start_fair(struct rq + + if (delta < 0) { + if (rq->curr == p) +- resched_curr(rq); ++ resched_curr_lazy(rq); + return; + } + hrtick_start(rq, delta); +@@ -6880,7 +6880,7 @@ static void check_preempt_wakeup(struct + return; + + preempt: +- resched_curr(rq); ++ resched_curr_lazy(rq); + /* + * Only set the backward buddy when the current task is still + * on the rq. This can happen when a wakeup gets interleaved +@@ -9966,7 +9966,7 @@ static void task_fork_fair(struct task_s + * 'current' within the tree based on its new key value. + */ + swap(curr->vruntime, se->vruntime); +- resched_curr(rq); ++ resched_curr_lazy(rq); + } + + se->vruntime -= cfs_rq->min_vruntime; +@@ -9990,7 +9990,7 @@ prio_changed_fair(struct rq *rq, struct + */ + if (rq->curr == p) { + if (p->prio > oldprio) +- resched_curr(rq); ++ resched_curr_lazy(rq); + } else + check_preempt_curr(rq, p, 0); + } +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -48,6 +48,9 @@ SCHED_FEAT(NONTASK_CAPACITY, true) + + #ifdef CONFIG_PREEMPT_RT_FULL + SCHED_FEAT(TTWU_QUEUE, false) ++# ifdef CONFIG_PREEMPT_LAZY ++SCHED_FEAT(PREEMPT_LAZY, true) ++# endif + #else + + /* +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1613,6 +1613,15 @@ extern void reweight_task(struct task_st + extern void resched_curr(struct rq *rq); + extern void resched_cpu(int cpu); + ++#ifdef CONFIG_PREEMPT_LAZY ++extern void resched_curr_lazy(struct rq *rq); ++#else ++static inline void resched_curr_lazy(struct rq *rq) ++{ ++ resched_curr(rq); ++} ++#endif ++ + extern struct rt_bandwidth def_rt_bandwidth; + extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime); + +--- a/kernel/trace/trace.c ++++ b/kernel/trace/trace.c +@@ -2133,6 +2133,7 @@ tracing_generic_entry_update(struct trac + struct task_struct *tsk = current; + + entry->preempt_count = pc & 0xff; ++ entry->preempt_lazy_count = preempt_lazy_count(); + entry->pid = (tsk) ? tsk->pid : 0; + entry->flags = + #ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT +@@ -2143,7 +2144,8 @@ tracing_generic_entry_update(struct trac + ((pc & NMI_MASK ) ? TRACE_FLAG_NMI : 0) | + ((pc & HARDIRQ_MASK) ? TRACE_FLAG_HARDIRQ : 0) | + ((pc & SOFTIRQ_OFFSET) ? TRACE_FLAG_SOFTIRQ : 0) | +- (tif_need_resched() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (tif_need_resched_now() ? TRACE_FLAG_NEED_RESCHED : 0) | ++ (need_resched_lazy() ? TRACE_FLAG_NEED_RESCHED_LAZY : 0) | + (test_preempt_need_resched() ? TRACE_FLAG_PREEMPT_RESCHED : 0); + + entry->migrate_disable = (tsk) ? __migrate_disabled(tsk) & 0xFF : 0; +@@ -3345,15 +3347,17 @@ get_total_entries(struct trace_buffer *b + + static void print_lat_help_header(struct seq_file *m) + { +- seq_puts(m, "# _------=> CPU# \n" +- "# / _-----=> irqs-off \n" +- "# | / _----=> need-resched \n" +- "# || / _---=> hardirq/softirq \n" +- "# ||| / _--=> preempt-depth \n" +- "# |||| / _--=> migrate-disable\n" +- "# ||||| / delay \n" +- "# cmd pid |||||| time | caller \n" +- "# \\ / ||||| \\ | / \n"); ++ seq_puts(m, "# _--------=> CPU# \n" ++ "# / _-------=> irqs-off \n" ++ "# | / _------=> need-resched \n" ++ "# || / _-----=> need-resched_lazy \n" ++ "# ||| / _----=> hardirq/softirq \n" ++ "# |||| / _---=> preempt-depth \n" ++ "# ||||| / _--=> preempt-lazy-depth\n" ++ "# |||||| / _-=> migrate-disable \n" ++ "# ||||||| / delay \n" ++ "# cmd pid |||||||| time | caller \n" ++ "# \\ / |||||||| \\ | / \n"); + } + + static void print_event_info(struct trace_buffer *buf, struct seq_file *m) +@@ -3389,15 +3393,17 @@ static void print_func_help_header_irq(s + tgid ? tgid_space : space); + seq_printf(m, "# %s / _----=> need-resched\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s| / _---=> hardirq/softirq\n", ++ seq_printf(m, "# %s| / _---=> need-resched_lazy\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s|| / _--=> preempt-depth\n", ++ seq_printf(m, "# %s|| / _--=> hardirq/softirq\n", + tgid ? tgid_space : space); +- seq_printf(m, "# %s||| / delay\n", ++ seq_printf(m, "# %s||| / preempt-depth\n", + tgid ? tgid_space : space); +- seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n", ++ seq_printf(m, "# %s|||| / delay\n", ++ tgid ? tgid_space : space); ++ seq_printf(m, "# TASK-PID %sCPU# ||||| TIMESTAMP FUNCTION\n", + tgid ? " TGID " : space); +- seq_printf(m, "# | | %s | |||| | |\n", ++ seq_printf(m, "# | | %s | ||||| | |\n", + tgid ? " | " : space); + } + +--- a/kernel/trace/trace.h ++++ b/kernel/trace/trace.h +@@ -127,6 +127,7 @@ struct kretprobe_trace_entry_head { + * NEED_RESCHED - reschedule is requested + * HARDIRQ - inside an interrupt handler + * SOFTIRQ - inside a softirq handler ++ * NEED_RESCHED_LAZY - lazy reschedule is requested + */ + enum trace_flag_type { + TRACE_FLAG_IRQS_OFF = 0x01, +@@ -136,6 +137,7 @@ enum trace_flag_type { + TRACE_FLAG_SOFTIRQ = 0x10, + TRACE_FLAG_PREEMPT_RESCHED = 0x20, + TRACE_FLAG_NMI = 0x40, ++ TRACE_FLAG_NEED_RESCHED_LAZY = 0x80, + }; + + #define TRACE_BUF_SIZE 1024 +--- a/kernel/trace/trace_output.c ++++ b/kernel/trace/trace_output.c +@@ -447,6 +447,7 @@ int trace_print_lat_fmt(struct trace_seq + { + char hardsoft_irq; + char need_resched; ++ char need_resched_lazy; + char irqs_off; + int hardirq; + int softirq; +@@ -477,6 +478,9 @@ int trace_print_lat_fmt(struct trace_seq + break; + } + ++ need_resched_lazy = ++ (entry->flags & TRACE_FLAG_NEED_RESCHED_LAZY) ? 'L' : '.'; ++ + hardsoft_irq = + (nmi && hardirq) ? 'Z' : + nmi ? 'z' : +@@ -485,14 +489,20 @@ int trace_print_lat_fmt(struct trace_seq + softirq ? 's' : + '.' ; + +- trace_seq_printf(s, "%c%c%c", +- irqs_off, need_resched, hardsoft_irq); ++ trace_seq_printf(s, "%c%c%c%c", ++ irqs_off, need_resched, need_resched_lazy, ++ hardsoft_irq); + + if (entry->preempt_count) + trace_seq_printf(s, "%x", entry->preempt_count); + else + trace_seq_putc(s, '.'); + ++ if (entry->preempt_lazy_count) ++ trace_seq_printf(s, "%x", entry->preempt_lazy_count); ++ else ++ trace_seq_putc(s, '.'); ++ + if (entry->migrate_disable) + trace_seq_printf(s, "%x", entry->migrate_disable); + else diff --git a/debian/patches/features/all/rt/preempt-nort-rt-variants.patch b/debian/patches/features/all/rt/preempt-nort-rt-variants.patch new file mode 100644 index 000000000..71ce1df3a --- /dev/null +++ b/debian/patches/features/all/rt/preempt-nort-rt-variants.patch @@ -0,0 +1,48 @@ +From: Thomas Gleixner +Date: Fri, 24 Jul 2009 12:38:56 +0200 +Subject: preempt: Provide preempt_*_(no)rt variants +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +RT needs a few preempt_disable/enable points which are not necessary +otherwise. Implement variants to avoid #ifdeffery. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/preempt.h | 18 +++++++++++++++++- + 1 file changed, 17 insertions(+), 1 deletion(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -181,7 +181,11 @@ do { \ + preempt_count_dec(); \ + } while (0) + +-#define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#ifdef CONFIG_PREEMPT_RT_BASE ++# define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++#else ++# define preempt_enable_no_resched() preempt_enable() ++#endif + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + +@@ -298,6 +302,18 @@ do { \ + set_preempt_need_resched(); \ + } while (0) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define preempt_disable_rt() preempt_disable() ++# define preempt_enable_rt() preempt_enable() ++# define preempt_disable_nort() barrier() ++# define preempt_enable_nort() barrier() ++#else ++# define preempt_disable_rt() barrier() ++# define preempt_enable_rt() barrier() ++# define preempt_disable_nort() preempt_disable() ++# define preempt_enable_nort() preempt_enable() ++#endif ++ + #ifdef CONFIG_PREEMPT_NOTIFIERS + + struct preempt_notifier; diff --git a/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch b/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch new file mode 100644 index 000000000..cbf415c2d --- /dev/null +++ b/debian/patches/features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch @@ -0,0 +1,32 @@ +Subject: printk: Add "force_early_printk" boot param to help with debugging +From: Peter Zijlstra +Date: Fri, 02 Sep 2011 14:41:29 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Gives me an option to screw printk and actually see what the machine +says. + +Signed-off-by: Peter Zijlstra +Link: http://lkml.kernel.org/r/1314967289.1301.11.camel@twins +Signed-off-by: Thomas Gleixner +Link: http://lkml.kernel.org/n/tip-ykb97nsfmobq44xketrxs977@git.kernel.org +--- + kernel/printk/printk.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -434,6 +434,13 @@ asmlinkage void early_printk(const char + */ + static bool __read_mostly printk_killswitch; + ++static int __init force_early_printk_setup(char *str) ++{ ++ printk_killswitch = true; ++ return 0; ++} ++early_param("force_early_printk", force_early_printk_setup); ++ + void printk_kill(void) + { + printk_killswitch = true; diff --git a/debian/patches/features/all/rt/printk-kill.patch b/debian/patches/features/all/rt/printk-kill.patch new file mode 100644 index 000000000..2e3b0eac2 --- /dev/null +++ b/debian/patches/features/all/rt/printk-kill.patch @@ -0,0 +1,164 @@ +Subject: printk: Add a printk kill switch +From: Ingo Molnar +Date: Fri, 22 Jul 2011 17:58:40 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Add a prinkt-kill-switch. This is used from (NMI) watchdog to ensure that +it does not dead-lock with the early printk code. + +Signed-off-by: Thomas Gleixner +--- + include/linux/printk.h | 2 + + kernel/printk/printk.c | 79 ++++++++++++++++++++++++++++++++++++------------- + kernel/watchdog_hld.c | 10 ++++++ + 3 files changed, 71 insertions(+), 20 deletions(-) + +--- a/include/linux/printk.h ++++ b/include/linux/printk.h +@@ -140,9 +140,11 @@ struct va_format { + #ifdef CONFIG_EARLY_PRINTK + extern asmlinkage __printf(1, 2) + void early_printk(const char *fmt, ...); ++extern void printk_kill(void); + #else + static inline __printf(1, 2) __cold + void early_printk(const char *s, ...) { } ++static inline void printk_kill(void) { } + #endif + + #ifdef CONFIG_PRINTK_NMI +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -404,6 +404,58 @@ DEFINE_RAW_SPINLOCK(logbuf_lock); + printk_safe_exit_irqrestore(flags); \ + } while (0) + ++#ifdef CONFIG_EARLY_PRINTK ++struct console *early_console; ++ ++static void early_vprintk(const char *fmt, va_list ap) ++{ ++ if (early_console) { ++ char buf[512]; ++ int n = vscnprintf(buf, sizeof(buf), fmt, ap); ++ ++ early_console->write(early_console, buf, n); ++ } ++} ++ ++asmlinkage void early_printk(const char *fmt, ...) ++{ ++ va_list ap; ++ ++ va_start(ap, fmt); ++ early_vprintk(fmt, ap); ++ va_end(ap); ++} ++ ++/* ++ * This is independent of any log levels - a global ++ * kill switch that turns off all of printk. ++ * ++ * Used by the NMI watchdog if early-printk is enabled. ++ */ ++static bool __read_mostly printk_killswitch; ++ ++void printk_kill(void) ++{ ++ printk_killswitch = true; ++} ++ ++#ifdef CONFIG_PRINTK ++static int forced_early_printk(const char *fmt, va_list ap) ++{ ++ if (!printk_killswitch) ++ return 0; ++ early_vprintk(fmt, ap); ++ return 1; ++} ++#endif ++ ++#else ++static inline int forced_early_printk(const char *fmt, va_list ap) ++{ ++ return 0; ++} ++#endif ++ + #ifdef CONFIG_PRINTK + DECLARE_WAIT_QUEUE_HEAD(log_wait); + /* the next printk record to read by syslog(READ) or /proc/kmsg */ +@@ -1836,6 +1888,13 @@ asmlinkage int vprintk_emit(int facility + int printed_len; + bool in_sched = false; + ++ /* ++ * Fall back to early_printk if a debugging subsystem has ++ * killed printk output ++ */ ++ if (unlikely(forced_early_printk(fmt, args))) ++ return 1; ++ + if (level == LOGLEVEL_SCHED) { + level = LOGLEVEL_DEFAULT; + in_sched = true; +@@ -2017,26 +2076,6 @@ static bool suppress_message_printing(in + + #endif /* CONFIG_PRINTK */ + +-#ifdef CONFIG_EARLY_PRINTK +-struct console *early_console; +- +-asmlinkage __visible void early_printk(const char *fmt, ...) +-{ +- va_list ap; +- char buf[512]; +- int n; +- +- if (!early_console) +- return; +- +- va_start(ap, fmt); +- n = vscnprintf(buf, sizeof(buf), fmt, ap); +- va_end(ap); +- +- early_console->write(early_console, buf, n); +-} +-#endif +- + static int __add_preferred_console(char *name, int idx, char *options, + char *brl_options) + { +--- a/kernel/watchdog_hld.c ++++ b/kernel/watchdog_hld.c +@@ -24,6 +24,8 @@ static DEFINE_PER_CPU(bool, hard_watchdo + static DEFINE_PER_CPU(bool, watchdog_nmi_touch); + static DEFINE_PER_CPU(struct perf_event *, watchdog_ev); + static DEFINE_PER_CPU(struct perf_event *, dead_event); ++static DEFINE_RAW_SPINLOCK(watchdog_output_lock); ++ + static struct cpumask dead_events_mask; + + static unsigned long hardlockup_allcpu_dumped; +@@ -134,6 +136,13 @@ static void watchdog_overflow_callback(s + /* only print hardlockups once */ + if (__this_cpu_read(hard_watchdog_warn) == true) + return; ++ /* ++ * If early-printk is enabled then make sure we do not ++ * lock up in printk() and kill console logging: ++ */ ++ printk_kill(); ++ ++ raw_spin_lock(&watchdog_output_lock); + + pr_emerg("Watchdog detected hard LOCKUP on cpu %d", this_cpu); + print_modules(); +@@ -151,6 +160,7 @@ static void watchdog_overflow_callback(s + !test_and_set_bit(0, &hardlockup_allcpu_dumped)) + trigger_allbutself_cpu_backtrace(); + ++ raw_spin_unlock(&watchdog_output_lock); + if (hardlockup_panic) + nmi_panic(regs, "Hard LOCKUP"); + diff --git a/debian/patches/features/all/rt/printk-rt-aware.patch b/debian/patches/features/all/rt/printk-rt-aware.patch new file mode 100644 index 000000000..5294a6d9e --- /dev/null +++ b/debian/patches/features/all/rt/printk-rt-aware.patch @@ -0,0 +1,108 @@ +Subject: printk: Make rt aware +From: Thomas Gleixner +Date: Wed, 19 Sep 2012 14:50:37 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Drop the lock before calling the console driver and do not disable +interrupts while printing to a serial console. + +Signed-off-by: Thomas Gleixner +--- + kernel/printk/printk.c | 33 ++++++++++++++++++++++++++++++--- + 1 file changed, 30 insertions(+), 3 deletions(-) + +--- a/kernel/printk/printk.c ++++ b/kernel/printk/printk.c +@@ -1606,6 +1606,7 @@ SYSCALL_DEFINE3(syslog, int, type, char + return do_syslog(type, buf, len, SYSLOG_FROM_READER); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Special console_lock variants that help to reduce the risk of soft-lockups. + * They allow to pass console_lock to another printk() call using a busy wait. +@@ -1746,6 +1747,15 @@ static int console_trylock_spinning(void + return 1; + } + ++#else ++ ++static int console_trylock_spinning(void) ++{ ++ return console_trylock(); ++} ++ ++#endif ++ + /* + * Call the console drivers, asking them to write out + * log_buf[start] to log_buf[end - 1]. +@@ -1761,6 +1771,7 @@ static void call_console_drivers(const c + if (!console_drivers) + return; + ++ migrate_disable(); + for_each_console(con) { + if (exclusive_console && con != exclusive_console) + continue; +@@ -1776,6 +1787,7 @@ static void call_console_drivers(const c + else + con->write(con, text, len); + } ++ migrate_enable(); + } + + int printk_delay_msec __read_mostly; +@@ -1958,20 +1970,30 @@ asmlinkage int vprintk_emit(int facility + + /* If called from the scheduler, we can not call up(). */ + if (!in_sched) { ++ int may_trylock = 1; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* ++ * we can't take a sleeping lock with IRQs or preeption disabled ++ * so we can't print in these contexts ++ */ ++ if (!(preempt_count() == 0 && !irqs_disabled())) ++ may_trylock = 0; ++#endif + /* + * Disable preemption to avoid being preempted while holding + * console_sem which would prevent anyone from printing to + * console + */ +- preempt_disable(); ++ migrate_disable(); + /* + * Try to acquire and then immediately release the console + * semaphore. The release will print out buffers and wake up + * /dev/kmsg and syslog() users. + */ +- if (console_trylock_spinning()) ++ if (may_trylock && console_trylock_spinning()) + console_unlock(); +- preempt_enable(); ++ migrate_enable(); + } + + wake_up_klogd(); +@@ -2423,6 +2445,10 @@ void console_unlock(void) + console_seq++; + raw_spin_unlock(&logbuf_lock); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ printk_safe_exit_irqrestore(flags); ++ call_console_drivers(ext_text, ext_len, text, len); ++#else + /* + * While actively printing out messages, if another printk() + * were to occur on another CPU, it may wait for this one to +@@ -2441,6 +2467,7 @@ void console_unlock(void) + } + + printk_safe_exit_irqrestore(flags); ++#endif + + if (do_cond_resched) + cond_resched(); diff --git a/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch b/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch new file mode 100644 index 000000000..59f8813bd --- /dev/null +++ b/debian/patches/features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch @@ -0,0 +1,156 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 29 Aug 2013 18:21:04 +0200 +Subject: ptrace: fix ptrace vs tasklist_lock race +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +As explained by Alexander Fyodorov : + +|read_lock(&tasklist_lock) in ptrace_stop() is converted to mutex on RT kernel, +|and it can remove __TASK_TRACED from task->state (by moving it to +|task->saved_state). If parent does wait() on child followed by a sys_ptrace +|call, the following race can happen: +| +|- child sets __TASK_TRACED in ptrace_stop() +|- parent does wait() which eventually calls wait_task_stopped() and returns +| child's pid +|- child blocks on read_lock(&tasklist_lock) in ptrace_stop() and moves +| __TASK_TRACED flag to saved_state +|- parent calls sys_ptrace, which calls ptrace_check_attach() and wait_task_inactive() + +The patch is based on his initial patch where an additional check is +added in case the __TASK_TRACED moved to ->saved_state. The pi_lock is +taken in case the caller is interrupted between looking into ->state and +->saved_state. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/sched.h | 49 +++++++++++++++++++++++++++++++++++++++++++++---- + kernel/ptrace.c | 9 ++++++++- + kernel/sched/core.c | 17 +++++++++++++++-- + 3 files changed, 68 insertions(+), 7 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -101,12 +101,8 @@ struct task_group; + __TASK_TRACED | EXIT_DEAD | EXIT_ZOMBIE | \ + TASK_PARKED) + +-#define task_is_traced(task) ((task->state & __TASK_TRACED) != 0) +- + #define task_is_stopped(task) ((task->state & __TASK_STOPPED) != 0) + +-#define task_is_stopped_or_traced(task) ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0) +- + #define task_contributes_to_load(task) ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \ + (task->flags & PF_FROZEN) == 0 && \ + (task->state & TASK_NOLOAD) == 0) +@@ -1707,6 +1703,51 @@ static inline int test_tsk_need_resched( + return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); + } + ++static inline bool __task_is_stopped_or_traced(struct task_struct *task) ++{ ++ if (task->state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (task->saved_state & (__TASK_STOPPED | __TASK_TRACED)) ++ return true; ++#endif ++ return false; ++} ++ ++static inline bool task_is_stopped_or_traced(struct task_struct *task) ++{ ++ bool traced_stopped; ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ traced_stopped = __task_is_stopped_or_traced(task); ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); ++#else ++ traced_stopped = __task_is_stopped_or_traced(task); ++#endif ++ return traced_stopped; ++} ++ ++static inline bool task_is_traced(struct task_struct *task) ++{ ++ bool traced = false; ++ ++ if (task->state & __TASK_TRACED) ++ return true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ /* in case the task is sleeping on tasklist_lock */ ++ raw_spin_lock_irq(&task->pi_lock); ++ if (task->state & __TASK_TRACED) ++ traced = true; ++ else if (task->saved_state & __TASK_TRACED) ++ traced = true; ++ raw_spin_unlock_irq(&task->pi_lock); ++#endif ++ return traced; ++} ++ + /* + * cond_resched() and cond_resched_lock(): latency reduction via + * explicit rescheduling in places that are safe. The return +--- a/kernel/ptrace.c ++++ b/kernel/ptrace.c +@@ -175,7 +175,14 @@ static bool ptrace_freeze_traced(struct + + spin_lock_irq(&task->sighand->siglock); + if (task_is_traced(task) && !__fatal_signal_pending(task)) { +- task->state = __TASK_TRACED; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&task->pi_lock, flags); ++ if (task->state & __TASK_TRACED) ++ task->state = __TASK_TRACED; ++ else ++ task->saved_state = __TASK_TRACED; ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + ret = true; + } + spin_unlock_irq(&task->sighand->siglock); +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1367,6 +1367,18 @@ int migrate_swap(struct task_struct *cur + return ret; + } + ++static bool check_task_state(struct task_struct *p, long match_state) ++{ ++ bool match = false; ++ ++ raw_spin_lock_irq(&p->pi_lock); ++ if (p->state == match_state || p->saved_state == match_state) ++ match = true; ++ raw_spin_unlock_irq(&p->pi_lock); ++ ++ return match; ++} ++ + /* + * wait_task_inactive - wait for a thread to unschedule. + * +@@ -1411,7 +1423,7 @@ unsigned long wait_task_inactive(struct + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { +- if (match_state && unlikely(p->state != match_state)) ++ if (match_state && !check_task_state(p, match_state)) + return 0; + cpu_relax(); + } +@@ -1426,7 +1438,8 @@ unsigned long wait_task_inactive(struct + running = task_running(rq, p); + queued = task_on_rq_queued(p); + ncsw = 0; +- if (!match_state || p->state == match_state) ++ if (!match_state || p->state == match_state || ++ p->saved_state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_rq_unlock(rq, p, &rf); + diff --git a/debian/patches/features/all/rt/radix-tree-use-local-locks.patch b/debian/patches/features/all/rt/radix-tree-use-local-locks.patch new file mode 100644 index 000000000..57b130974 --- /dev/null +++ b/debian/patches/features/all/rt/radix-tree-use-local-locks.patch @@ -0,0 +1,166 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 25 Jan 2017 16:34:27 +0100 +Subject: [PATCH] radix-tree: use local locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The preload functionality uses per-CPU variables and preempt-disable to +ensure that it does not switch CPUs during its usage. This patch adds +local_locks() instead preempt_disable() for the same purpose and to +remain preemptible on -RT. + +Cc: stable-rt@vger.kernel.org +Reported-and-debugged-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/idr.h | 5 +---- + include/linux/radix-tree.h | 7 ++----- + lib/radix-tree.c | 32 +++++++++++++++++++++++--------- + 3 files changed, 26 insertions(+), 18 deletions(-) + +--- a/include/linux/idr.h ++++ b/include/linux/idr.h +@@ -158,10 +158,7 @@ static inline bool idr_is_empty(const st + * Each idr_preload() should be matched with an invocation of this + * function. See idr_preload() for details. + */ +-static inline void idr_preload_end(void) +-{ +- preempt_enable(); +-} ++void idr_preload_end(void); + + /** + * idr_for_each_entry() - Iterate over an IDR's elements of a given type. +--- a/include/linux/radix-tree.h ++++ b/include/linux/radix-tree.h +@@ -330,6 +330,8 @@ unsigned int radix_tree_gang_lookup_slot + int radix_tree_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload(gfp_t gfp_mask); + int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); ++void radix_tree_preload_end(void); ++ + void radix_tree_init(void); + void *radix_tree_tag_set(struct radix_tree_root *, + unsigned long index, unsigned int tag); +@@ -349,11 +351,6 @@ unsigned int radix_tree_gang_lookup_tag_ + unsigned int max_items, unsigned int tag); + int radix_tree_tagged(const struct radix_tree_root *, unsigned int tag); + +-static inline void radix_tree_preload_end(void) +-{ +- preempt_enable(); +-} +- + int radix_tree_split_preload(unsigned old_order, unsigned new_order, gfp_t); + int radix_tree_split(struct radix_tree_root *, unsigned long index, + unsigned new_order); +--- a/lib/radix-tree.c ++++ b/lib/radix-tree.c +@@ -38,7 +38,7 @@ + #include + #include + #include +- ++#include + + /* Number of nodes in fully populated tree of given height */ + static unsigned long height_to_maxnodes[RADIX_TREE_MAX_PATH + 1] __read_mostly; +@@ -87,6 +87,7 @@ struct radix_tree_preload { + struct radix_tree_node *nodes; + }; + static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, }; ++static DEFINE_LOCAL_IRQ_LOCK(radix_tree_preloads_lock); + + static inline struct radix_tree_node *entry_to_node(void *ptr) + { +@@ -405,12 +406,13 @@ radix_tree_node_alloc(gfp_t gfp_mask, st + * succeed in getting a node here (and never reach + * kmem_cache_alloc) + */ +- rtp = this_cpu_ptr(&radix_tree_preloads); ++ rtp = &get_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + if (rtp->nr) { + ret = rtp->nodes; + rtp->nodes = ret->parent; + rtp->nr--; + } ++ put_locked_var(radix_tree_preloads_lock, radix_tree_preloads); + /* + * Update the allocation stack trace as this is more useful + * for debugging. +@@ -476,14 +478,14 @@ static __must_check int __radix_tree_pre + */ + gfp_mask &= ~__GFP_ACCOUNT; + +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + while (rtp->nr < nr) { +- preempt_enable(); ++ local_unlock(radix_tree_preloads_lock); + node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); + if (node == NULL) + goto out; +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + rtp = this_cpu_ptr(&radix_tree_preloads); + if (rtp->nr < nr) { + node->parent = rtp->nodes; +@@ -525,7 +527,7 @@ int radix_tree_maybe_preload(gfp_t gfp_m + if (gfpflags_allow_blocking(gfp_mask)) + return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); + /* Preloading doesn't help anything with this gfp mask, skip it */ +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + return 0; + } + EXPORT_SYMBOL(radix_tree_maybe_preload); +@@ -563,7 +565,7 @@ int radix_tree_maybe_preload_order(gfp_t + + /* Preloading doesn't help anything with this gfp mask, skip it */ + if (!gfpflags_allow_blocking(gfp_mask)) { +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + return 0; + } + +@@ -597,6 +599,12 @@ int radix_tree_maybe_preload_order(gfp_t + return __radix_tree_preload(gfp_mask, nr_nodes); + } + ++void radix_tree_preload_end(void) ++{ ++ local_unlock(radix_tree_preloads_lock); ++} ++EXPORT_SYMBOL(radix_tree_preload_end); ++ + static unsigned radix_tree_load_root(const struct radix_tree_root *root, + struct radix_tree_node **nodep, unsigned long *maxindex) + { +@@ -2102,10 +2110,16 @@ EXPORT_SYMBOL(radix_tree_tagged); + void idr_preload(gfp_t gfp_mask) + { + if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) +- preempt_disable(); ++ local_lock(radix_tree_preloads_lock); + } + EXPORT_SYMBOL(idr_preload); + ++void idr_preload_end(void) ++{ ++ local_unlock(radix_tree_preloads_lock); ++} ++EXPORT_SYMBOL(idr_preload_end); ++ + /** + * ida_pre_get - reserve resources for ida allocation + * @ida: ida handle +@@ -2122,7 +2136,7 @@ int ida_pre_get(struct ida *ida, gfp_t g + * to return to the ida_pre_get() step. + */ + if (!__radix_tree_preload(gfp, IDA_PRELOAD_SIZE)) +- preempt_enable(); ++ local_unlock(radix_tree_preloads_lock); + + if (!this_cpu_read(ida_bitmap)) { + struct ida_bitmap *bitmap = kzalloc(sizeof(*bitmap), gfp); diff --git a/debian/patches/features/all/rt/random-Remove-preempt-disabled-region.patch b/debian/patches/features/all/rt/random-Remove-preempt-disabled-region.patch new file mode 100644 index 000000000..74a296fc5 --- /dev/null +++ b/debian/patches/features/all/rt/random-Remove-preempt-disabled-region.patch @@ -0,0 +1,49 @@ +From 20690515ca3fd9baa92a3c915c74b14290fef13c Mon Sep 17 00:00:00 2001 +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:30 -0500 +Subject: [PATCH] random: Remove preempt disabled region +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +No need to keep preemption disabled across the whole function. + +mix_pool_bytes() uses a spin_lock() to protect the pool and there are +other places like write_pool() whhich invoke mix_pool_bytes() without +disabling preemption. +credit_entropy_bits() is invoked from other places like +add_hwgenerator_randomness() without disabling preemption. + +Before commit 95b709b6be49 ("random: drop trickle mode") the function +used __this_cpu_inc_return() which would require disabled preemption. +The preempt_disable() section was added in commit 43d5d3018c37 ("[PATCH] +random driver preempt robustness", history tree). It was claimed that +the code relied on "vt_ioctl() being called under BKL". + +Cc: "Theodore Ts'o" +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +[bigeasy: enhance the commit message] +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/char/random.c | 4 ---- + 1 file changed, 4 deletions(-) + +--- a/drivers/char/random.c ++++ b/drivers/char/random.c +@@ -1122,8 +1122,6 @@ static void add_timer_randomness(struct + } sample; + long delta, delta2, delta3; + +- preempt_disable(); +- + sample.jiffies = jiffies; + sample.cycles = random_get_entropy(); + sample.num = num; +@@ -1161,8 +1159,6 @@ static void add_timer_randomness(struct + * and limit entropy entimate to 12 bits. + */ + credit_entropy_bits(r, min_t(int, fls(delta>>1), 11)); +- +- preempt_enable(); + } + + void add_input_randomness(unsigned int type, unsigned int code, diff --git a/debian/patches/features/all/rt/random-avoid-preempt_disable-ed-section.patch b/debian/patches/features/all/rt/random-avoid-preempt_disable-ed-section.patch new file mode 100644 index 000000000..3b7b705c7 --- /dev/null +++ b/debian/patches/features/all/rt/random-avoid-preempt_disable-ed-section.patch @@ -0,0 +1,75 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 12 May 2017 15:46:17 +0200 +Subject: [PATCH] random: avoid preempt_disable()ed section +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +extract_crng() will use sleeping locks while in a preempt_disable() +section due to get_cpu_var(). +Work around it with local_locks. + +Cc: stable-rt@vger.kernel.org # where it applies to +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/char/random.c | 11 +++++++---- + 1 file changed, 7 insertions(+), 4 deletions(-) + +--- a/drivers/char/random.c ++++ b/drivers/char/random.c +@@ -265,6 +265,7 @@ + #include + #include + #include ++#include + #include + + #include +@@ -2193,6 +2194,7 @@ static rwlock_t batched_entropy_reset_lo + * at any point prior. + */ + static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u64); ++static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_u64_lock); + u64 get_random_u64(void) + { + u64 ret; +@@ -2213,7 +2215,7 @@ u64 get_random_u64(void) + warn_unseeded_randomness(&previous); + + use_lock = READ_ONCE(crng_init) < 2; +- batch = &get_cpu_var(batched_entropy_u64); ++ batch = &get_locked_var(batched_entropy_u64_lock, batched_entropy_u64); + if (use_lock) + read_lock_irqsave(&batched_entropy_reset_lock, flags); + if (batch->position % ARRAY_SIZE(batch->entropy_u64) == 0) { +@@ -2223,12 +2225,13 @@ u64 get_random_u64(void) + ret = batch->entropy_u64[batch->position++]; + if (use_lock) + read_unlock_irqrestore(&batched_entropy_reset_lock, flags); +- put_cpu_var(batched_entropy_u64); ++ put_locked_var(batched_entropy_u64_lock, batched_entropy_u64); + return ret; + } + EXPORT_SYMBOL(get_random_u64); + + static DEFINE_PER_CPU(struct batched_entropy, batched_entropy_u32); ++static DEFINE_LOCAL_IRQ_LOCK(batched_entropy_u32_lock); + u32 get_random_u32(void) + { + u32 ret; +@@ -2243,7 +2246,7 @@ u32 get_random_u32(void) + warn_unseeded_randomness(&previous); + + use_lock = READ_ONCE(crng_init) < 2; +- batch = &get_cpu_var(batched_entropy_u32); ++ batch = &get_locked_var(batched_entropy_u32_lock, batched_entropy_u32); + if (use_lock) + read_lock_irqsave(&batched_entropy_reset_lock, flags); + if (batch->position % ARRAY_SIZE(batch->entropy_u32) == 0) { +@@ -2253,7 +2256,7 @@ u32 get_random_u32(void) + ret = batch->entropy_u32[batch->position++]; + if (use_lock) + read_unlock_irqrestore(&batched_entropy_reset_lock, flags); +- put_cpu_var(batched_entropy_u32); ++ put_locked_var(batched_entropy_u32_lock, batched_entropy_u32); + return ret; + } + EXPORT_SYMBOL(get_random_u32); diff --git a/debian/patches/features/all/rt/random-make-it-work-on-rt.patch b/debian/patches/features/all/rt/random-make-it-work-on-rt.patch new file mode 100644 index 000000000..0fd0605f6 --- /dev/null +++ b/debian/patches/features/all/rt/random-make-it-work-on-rt.patch @@ -0,0 +1,150 @@ +Subject: random: Make it work on rt +From: Thomas Gleixner +Date: Tue, 21 Aug 2012 20:38:50 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Delegate the random insertion to the forced threaded interrupt +handler. Store the return IP of the hard interrupt handler in the irq +descriptor and feed it into the random generator as a source of +entropy. + +Signed-off-by: Thomas Gleixner + +--- + drivers/char/random.c | 11 +++++------ + drivers/hv/hv.c | 4 +++- + drivers/hv/vmbus_drv.c | 4 +++- + include/linux/irqdesc.h | 1 + + include/linux/random.h | 2 +- + kernel/irq/handle.c | 8 +++++++- + kernel/irq/manage.c | 6 ++++++ + 7 files changed, 26 insertions(+), 10 deletions(-) + +--- a/drivers/char/random.c ++++ b/drivers/char/random.c +@@ -1215,28 +1215,27 @@ static __u32 get_reg(struct fast_pool *f + return *ptr; + } + +-void add_interrupt_randomness(int irq, int irq_flags) ++void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) + { + struct entropy_store *r; + struct fast_pool *fast_pool = this_cpu_ptr(&irq_randomness); +- struct pt_regs *regs = get_irq_regs(); + unsigned long now = jiffies; + cycles_t cycles = random_get_entropy(); + __u32 c_high, j_high; +- __u64 ip; + unsigned long seed; + int credit = 0; + + if (cycles == 0) +- cycles = get_reg(fast_pool, regs); ++ cycles = get_reg(fast_pool, NULL); + c_high = (sizeof(cycles) > 4) ? cycles >> 32 : 0; + j_high = (sizeof(now) > 4) ? now >> 32 : 0; + fast_pool->pool[0] ^= cycles ^ j_high ^ irq; + fast_pool->pool[1] ^= now ^ c_high; +- ip = regs ? instruction_pointer(regs) : _RET_IP_; ++ if (!ip) ++ ip = _RET_IP_; + fast_pool->pool[2] ^= ip; + fast_pool->pool[3] ^= (sizeof(ip) > 4) ? ip >> 32 : +- get_reg(fast_pool, regs); ++ get_reg(fast_pool, NULL); + + fast_mix(fast_pool); + add_interrupt_bench(cycles); +--- a/drivers/hv/hv.c ++++ b/drivers/hv/hv.c +@@ -112,10 +112,12 @@ int hv_post_message(union hv_connection_ + static void hv_stimer0_isr(void) + { + struct hv_per_cpu_context *hv_cpu; ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + + hv_cpu = this_cpu_ptr(hv_context.cpu_context); + hv_cpu->clk_evt->event_handler(hv_cpu->clk_evt); +- add_interrupt_randomness(stimer0_vector, 0); ++ add_interrupt_randomness(stimer0_vector, 0, ip); + } + + static int hv_ce_set_next_event(unsigned long delta, +--- a/drivers/hv/vmbus_drv.c ++++ b/drivers/hv/vmbus_drv.c +@@ -972,6 +972,8 @@ static void vmbus_isr(void) + void *page_addr = hv_cpu->synic_event_page; + struct hv_message *msg; + union hv_synic_event_flags *event; ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + bool handled = false; + + if (unlikely(page_addr == NULL)) +@@ -1015,7 +1017,7 @@ static void vmbus_isr(void) + tasklet_schedule(&hv_cpu->msg_dpc); + } + +- add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0); ++ add_interrupt_randomness(HYPERVISOR_CALLBACK_VECTOR, 0, ip); + } + + +--- a/include/linux/irqdesc.h ++++ b/include/linux/irqdesc.h +@@ -70,6 +70,7 @@ struct irq_desc { + unsigned int irqs_unhandled; + atomic_t threads_handled; + int threads_handled_last; ++ u64 random_ip; + raw_spinlock_t lock; + struct cpumask *percpu_enabled; + const struct cpumask *percpu_affinity; +--- a/include/linux/random.h ++++ b/include/linux/random.h +@@ -32,7 +32,7 @@ static inline void add_latent_entropy(vo + + extern void add_input_randomness(unsigned int type, unsigned int code, + unsigned int value) __latent_entropy; +-extern void add_interrupt_randomness(int irq, int irq_flags) __latent_entropy; ++extern void add_interrupt_randomness(int irq, int irq_flags, __u64 ip) __latent_entropy; + + extern void get_random_bytes(void *buf, int nbytes); + extern int wait_for_random_bytes(void); +--- a/kernel/irq/handle.c ++++ b/kernel/irq/handle.c +@@ -185,10 +185,16 @@ irqreturn_t handle_irq_event_percpu(stru + { + irqreturn_t retval; + unsigned int flags = 0; ++ struct pt_regs *regs = get_irq_regs(); ++ u64 ip = regs ? instruction_pointer(regs) : 0; + + retval = __handle_irq_event_percpu(desc, &flags); + +- add_interrupt_randomness(desc->irq_data.irq, flags); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ desc->random_ip = ip; ++#else ++ add_interrupt_randomness(desc->irq_data.irq, flags, ip); ++#endif + + if (!noirqdebug) + note_interrupt(desc, retval); +--- a/kernel/irq/manage.c ++++ b/kernel/irq/manage.c +@@ -1065,6 +1065,12 @@ static int irq_thread(void *data) + if (action_ret == IRQ_WAKE_THREAD) + irq_wake_secondary(desc, action); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ migrate_disable(); ++ add_interrupt_randomness(action->irq, 0, ++ desc->random_ip ^ (unsigned long) action); ++ migrate_enable(); ++#endif + wake_threads_waitq(desc); + } + diff --git a/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch b/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch new file mode 100644 index 000000000..fe8a3dbba --- /dev/null +++ b/debian/patches/features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch @@ -0,0 +1,412 @@ +From: "Paul E. McKenney" +Date: Mon, 4 Nov 2013 13:21:10 -0800 +Subject: rcu: Eliminate softirq processing from rcutree +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Running RCU out of softirq is a problem for some workloads that would +like to manage RCU core processing independently of other softirq work, +for example, setting kthread priority. This commit therefore moves the +RCU core work from softirq to a per-CPU/per-flavor SCHED_OTHER kthread +named rcuc. The SCHED_OTHER approach avoids the scalability problems +that appeared with the earlier attempt to move RCU core processing to +from softirq to kthreads. That said, kernels built with RCU_BOOST=y +will run the rcuc kthreads at the RCU-boosting priority. + +Reported-by: Thomas Gleixner +Tested-by: Mike Galbraith +Signed-off-by: Paul E. McKenney +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/tree.c | 112 +++++++++++++++++++++++++++++++++---- + kernel/rcu/tree.h | 4 - + kernel/rcu/tree_plugin.h | 142 +++-------------------------------------------- + 3 files changed, 114 insertions(+), 144 deletions(-) + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -58,6 +58,13 @@ + #include + #include + #include ++#include ++#include ++#include ++#include ++#include ++#include ++#include "../time/tick-internal.h" + + #include "tree.h" + #include "rcu.h" +@@ -2819,18 +2826,17 @@ static void + /* + * Do RCU core processing for the current CPU. + */ +-static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) ++static __latent_entropy void rcu_process_callbacks(void) + { + struct rcu_state *rsp; + + if (cpu_is_offline(smp_processor_id())) + return; +- trace_rcu_utilization(TPS("Start RCU core")); + for_each_rcu_flavor(rsp) + __rcu_process_callbacks(rsp); +- trace_rcu_utilization(TPS("End RCU core")); + } + ++static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + /* + * Schedule RCU callback invocation. If the specified type of RCU + * does not support RCU priority boosting, just do a direct call, +@@ -2842,18 +2848,105 @@ static void invoke_rcu_callbacks(struct + { + if (unlikely(!READ_ONCE(rcu_scheduler_fully_active))) + return; +- if (likely(!rsp->boost)) { +- rcu_do_batch(rsp, rdp); ++ rcu_do_batch(rsp, rdp); ++} ++ ++static void rcu_wake_cond(struct task_struct *t, int status) ++{ ++ /* ++ * If the thread is yielding, only wake it when this ++ * is invoked from idle ++ */ ++ if (t && (status != RCU_KTHREAD_YIELDING || is_idle_task(current))) ++ wake_up_process(t); ++} ++ ++/* ++ * Wake up this CPU's rcuc kthread to do RCU core processing. ++ */ ++static void invoke_rcu_core(void) ++{ ++ unsigned long flags; ++ struct task_struct *t; ++ ++ if (!cpu_online(smp_processor_id())) + return; ++ local_irq_save(flags); ++ __this_cpu_write(rcu_cpu_has_work, 1); ++ t = __this_cpu_read(rcu_cpu_kthread_task); ++ if (t != NULL && current != t) ++ rcu_wake_cond(t, __this_cpu_read(rcu_cpu_kthread_status)); ++ local_irq_restore(flags); ++} ++ ++static void rcu_cpu_kthread_park(unsigned int cpu) ++{ ++ per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; ++} ++ ++static int rcu_cpu_kthread_should_run(unsigned int cpu) ++{ ++ return __this_cpu_read(rcu_cpu_has_work); ++} ++ ++/* ++ * Per-CPU kernel thread that invokes RCU callbacks. This replaces the ++ * RCU softirq used in flavors and configurations of RCU that do not ++ * support RCU priority boosting. ++ */ ++static void rcu_cpu_kthread(unsigned int cpu) ++{ ++ unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); ++ char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); ++ int spincnt; ++ ++ for (spincnt = 0; spincnt < 10; spincnt++) { ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); ++ local_bh_disable(); ++ *statusp = RCU_KTHREAD_RUNNING; ++ this_cpu_inc(rcu_cpu_kthread_loops); ++ local_irq_disable(); ++ work = *workp; ++ *workp = 0; ++ local_irq_enable(); ++ if (work) ++ rcu_process_callbacks(); ++ local_bh_enable(); ++ if (*workp == 0) { ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); ++ *statusp = RCU_KTHREAD_WAITING; ++ return; ++ } + } +- invoke_rcu_callbacks_kthread(); ++ *statusp = RCU_KTHREAD_YIELDING; ++ trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); ++ schedule_timeout_interruptible(2); ++ trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); ++ *statusp = RCU_KTHREAD_WAITING; + } + +-static void invoke_rcu_core(void) ++static struct smp_hotplug_thread rcu_cpu_thread_spec = { ++ .store = &rcu_cpu_kthread_task, ++ .thread_should_run = rcu_cpu_kthread_should_run, ++ .thread_fn = rcu_cpu_kthread, ++ .thread_comm = "rcuc/%u", ++ .setup = rcu_cpu_kthread_setup, ++ .park = rcu_cpu_kthread_park, ++}; ++ ++/* ++ * Spawn per-CPU RCU core processing kthreads. ++ */ ++static int __init rcu_spawn_core_kthreads(void) + { +- if (cpu_online(smp_processor_id())) +- raise_softirq(RCU_SOFTIRQ); ++ int cpu; ++ ++ for_each_possible_cpu(cpu) ++ per_cpu(rcu_cpu_has_work, cpu) = 0; ++ BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); ++ return 0; + } ++early_initcall(rcu_spawn_core_kthreads); + + /* + * Handle any core-RCU processing required by a call_rcu() invocation. +@@ -4122,7 +4215,6 @@ void __init rcu_init(void) + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); + __rcu_init_preempt(); +- open_softirq(RCU_SOFTIRQ, rcu_process_callbacks); + + /* + * We don't need protection against CPU-hotplug here because +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -432,12 +432,10 @@ extern struct rcu_state rcu_preempt_stat + + int rcu_dynticks_snap(struct rcu_dynticks *rdtp); + +-#ifdef CONFIG_RCU_BOOST + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DECLARE_PER_CPU(int, rcu_cpu_kthread_cpu); + DECLARE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DECLARE_PER_CPU(char, rcu_cpu_has_work); +-#endif /* #ifdef CONFIG_RCU_BOOST */ + + #ifndef RCU_TREE_NONCORE + +@@ -457,8 +455,8 @@ void call_rcu(struct rcu_head *head, rcu + static void __init __rcu_init_preempt(void); + static void rcu_initiate_boost(struct rcu_node *rnp, unsigned long flags); + static void rcu_preempt_boost_start_gp(struct rcu_node *rnp); +-static void invoke_rcu_callbacks_kthread(void); + static bool rcu_is_callbacks_kthread(void); ++static void rcu_cpu_kthread_setup(unsigned int cpu); + #ifdef CONFIG_RCU_BOOST + static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp, + struct rcu_node *rnp); +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -24,42 +24,16 @@ + * Paul E. McKenney + */ + +-#include +-#include +-#include +-#include +-#include +-#include +-#include +-#include +-#include "../time/tick-internal.h" +- +-#ifdef CONFIG_RCU_BOOST +- + #include "../locking/rtmutex_common.h" + + /* + * Control variables for per-CPU and per-rcu_node kthreads. These + * handle all flavors of RCU. + */ +-static DEFINE_PER_CPU(struct task_struct *, rcu_cpu_kthread_task); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_status); + DEFINE_PER_CPU(unsigned int, rcu_cpu_kthread_loops); + DEFINE_PER_CPU(char, rcu_cpu_has_work); + +-#else /* #ifdef CONFIG_RCU_BOOST */ +- +-/* +- * Some architectures do not define rt_mutexes, but if !CONFIG_RCU_BOOST, +- * all uses are in dead code. Provide a definition to keep the compiler +- * happy, but add WARN_ON_ONCE() to complain if used in the wrong place. +- * This probably needs to be excluded from -rt builds. +- */ +-#define rt_mutex_owner(a) ({ WARN_ON_ONCE(1); NULL; }) +-#define rt_mutex_futex_unlock(x) WARN_ON_ONCE(1) +- +-#endif /* #else #ifdef CONFIG_RCU_BOOST */ +- + #ifdef CONFIG_RCU_NOCB_CPU + static cpumask_var_t rcu_nocb_mask; /* CPUs to have callbacks offloaded. */ + static bool __read_mostly rcu_nocb_poll; /* Offload kthread are to poll. */ +@@ -956,18 +930,21 @@ void exit_rcu(void) + + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++/* ++ * If boosting, set rcuc kthreads to realtime priority. ++ */ ++static void rcu_cpu_kthread_setup(unsigned int cpu) ++{ + #ifdef CONFIG_RCU_BOOST ++ struct sched_param sp; + +-static void rcu_wake_cond(struct task_struct *t, int status) +-{ +- /* +- * If the thread is yielding, only wake it when this +- * is invoked from idle +- */ +- if (status != RCU_KTHREAD_YIELDING || is_idle_task(current)) +- wake_up_process(t); ++ sp.sched_priority = kthread_prio; ++ sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); ++#endif /* #ifdef CONFIG_RCU_BOOST */ + } + ++#ifdef CONFIG_RCU_BOOST ++ + /* + * Carry out RCU priority boosting on the task indicated by ->exp_tasks + * or ->boost_tasks, advancing the pointer to the next task in the +@@ -1106,23 +1083,6 @@ static void rcu_initiate_boost(struct rc + } + + /* +- * Wake up the per-CPU kthread to invoke RCU callbacks. +- */ +-static void invoke_rcu_callbacks_kthread(void) +-{ +- unsigned long flags; +- +- local_irq_save(flags); +- __this_cpu_write(rcu_cpu_has_work, 1); +- if (__this_cpu_read(rcu_cpu_kthread_task) != NULL && +- current != __this_cpu_read(rcu_cpu_kthread_task)) { +- rcu_wake_cond(__this_cpu_read(rcu_cpu_kthread_task), +- __this_cpu_read(rcu_cpu_kthread_status)); +- } +- local_irq_restore(flags); +-} +- +-/* + * Is the current CPU running the RCU-callbacks kthread? + * Caller must have preemption disabled. + */ +@@ -1176,67 +1136,6 @@ static int rcu_spawn_one_boost_kthread(s + return 0; + } + +-static void rcu_kthread_do_work(void) +-{ +- rcu_do_batch(&rcu_sched_state, this_cpu_ptr(&rcu_sched_data)); +- rcu_do_batch(&rcu_bh_state, this_cpu_ptr(&rcu_bh_data)); +- rcu_do_batch(&rcu_preempt_state, this_cpu_ptr(&rcu_preempt_data)); +-} +- +-static void rcu_cpu_kthread_setup(unsigned int cpu) +-{ +- struct sched_param sp; +- +- sp.sched_priority = kthread_prio; +- sched_setscheduler_nocheck(current, SCHED_FIFO, &sp); +-} +- +-static void rcu_cpu_kthread_park(unsigned int cpu) +-{ +- per_cpu(rcu_cpu_kthread_status, cpu) = RCU_KTHREAD_OFFCPU; +-} +- +-static int rcu_cpu_kthread_should_run(unsigned int cpu) +-{ +- return __this_cpu_read(rcu_cpu_has_work); +-} +- +-/* +- * Per-CPU kernel thread that invokes RCU callbacks. This replaces the +- * RCU softirq used in flavors and configurations of RCU that do not +- * support RCU priority boosting. +- */ +-static void rcu_cpu_kthread(unsigned int cpu) +-{ +- unsigned int *statusp = this_cpu_ptr(&rcu_cpu_kthread_status); +- char work, *workp = this_cpu_ptr(&rcu_cpu_has_work); +- int spincnt; +- +- for (spincnt = 0; spincnt < 10; spincnt++) { +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_wait")); +- local_bh_disable(); +- *statusp = RCU_KTHREAD_RUNNING; +- this_cpu_inc(rcu_cpu_kthread_loops); +- local_irq_disable(); +- work = *workp; +- *workp = 0; +- local_irq_enable(); +- if (work) +- rcu_kthread_do_work(); +- local_bh_enable(); +- if (*workp == 0) { +- trace_rcu_utilization(TPS("End CPU kthread@rcu_wait")); +- *statusp = RCU_KTHREAD_WAITING; +- return; +- } +- } +- *statusp = RCU_KTHREAD_YIELDING; +- trace_rcu_utilization(TPS("Start CPU kthread@rcu_yield")); +- schedule_timeout_interruptible(2); +- trace_rcu_utilization(TPS("End CPU kthread@rcu_yield")); +- *statusp = RCU_KTHREAD_WAITING; +-} +- + /* + * Set the per-rcu_node kthread's affinity to cover all CPUs that are + * served by the rcu_node in question. The CPU hotplug lock is still +@@ -1267,26 +1166,12 @@ static void rcu_boost_kthread_setaffinit + free_cpumask_var(cm); + } + +-static struct smp_hotplug_thread rcu_cpu_thread_spec = { +- .store = &rcu_cpu_kthread_task, +- .thread_should_run = rcu_cpu_kthread_should_run, +- .thread_fn = rcu_cpu_kthread, +- .thread_comm = "rcuc/%u", +- .setup = rcu_cpu_kthread_setup, +- .park = rcu_cpu_kthread_park, +-}; +- + /* + * Spawn boost kthreads -- called as soon as the scheduler is running. + */ + static void __init rcu_spawn_boost_kthreads(void) + { + struct rcu_node *rnp; +- int cpu; +- +- for_each_possible_cpu(cpu) +- per_cpu(rcu_cpu_has_work, cpu) = 0; +- BUG_ON(smpboot_register_percpu_thread(&rcu_cpu_thread_spec)); + rcu_for_each_leaf_node(rcu_state_p, rnp) + (void)rcu_spawn_one_boost_kthread(rcu_state_p, rnp); + } +@@ -1309,11 +1194,6 @@ static void rcu_initiate_boost(struct rc + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } + +-static void invoke_rcu_callbacks_kthread(void) +-{ +- WARN_ON_ONCE(1); +-} +- + static bool rcu_is_callbacks_kthread(void) + { + return false; diff --git a/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch b/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch new file mode 100644 index 000000000..d1cba4ce6 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch @@ -0,0 +1,25 @@ +Subject: rcu: Disable RCU_FAST_NO_HZ on RT +From: Thomas Gleixner +Date: Sun, 28 Oct 2012 13:26:09 +0000 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This uses a timer_list timer from the irq disabled guts of the idle +code. Disable it for now to prevent wreckage. + +Signed-off-by: Thomas Gleixner + +--- + kernel/rcu/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/rcu/Kconfig ++++ b/kernel/rcu/Kconfig +@@ -172,7 +172,7 @@ config RCU_FANOUT_LEAF + + config RCU_FAST_NO_HZ + bool "Accelerate last non-dyntick-idle CPU's grace periods" +- depends on NO_HZ_COMMON && SMP && RCU_EXPERT ++ depends on NO_HZ_COMMON && SMP && RCU_EXPERT && !PREEMPT_RT_FULL + default n + help + This option permits CPUs to enter dynticks-idle state even if diff --git a/debian/patches/features/all/rt/rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch b/debian/patches/features/all/rt/rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch new file mode 100644 index 000000000..65a88b615 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch @@ -0,0 +1,30 @@ +From: Julia Cartwright +Date: Wed, 12 Oct 2016 11:21:14 -0500 +Subject: [PATCH] rcu: enable rcu_normal_after_boot by default for RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The forcing of an expedited grace period is an expensive and very +RT-application unfriendly operation, as it forcibly preempts all running +tasks on CPUs which are preventing the gp from expiring. + +By default, as a policy decision, disable the expediting of grace +periods (after boot) on configurations which enable PREEMPT_RT_FULL. + +Suggested-by: Luiz Capitulino +Signed-off-by: Julia Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/update.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -67,7 +67,7 @@ extern int rcu_expedited; /* from sysctl + module_param(rcu_expedited, int, 0); + extern int rcu_normal; /* from sysctl */ + module_param(rcu_normal, int, 0); +-static int rcu_normal_after_boot; ++static int rcu_normal_after_boot = IS_ENABLED(CONFIG_PREEMPT_RT_FULL); + module_param(rcu_normal_after_boot, int, 0); + #endif /* #ifndef CONFIG_TINY_RCU */ + diff --git a/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch b/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch new file mode 100644 index 000000000..dfccf7eb9 --- /dev/null +++ b/debian/patches/features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch @@ -0,0 +1,35 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 21 Mar 2014 20:19:05 +0100 +Subject: rcu: make RCU_BOOST default on RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Since it is no longer invoked from the softirq people run into OOM more +often if the priority of the RCU thread is too low. Making boosting +default on RT should help in those case and it can be switched off if +someone knows better. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/Kconfig | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/kernel/rcu/Kconfig ++++ b/kernel/rcu/Kconfig +@@ -36,7 +36,7 @@ config TINY_RCU + + config RCU_EXPERT + bool "Make expert-level adjustments to RCU configuration" +- default n ++ default y if PREEMPT_RT_FULL + help + This option needs to be enabled if you wish to make + expert-level adjustments to RCU configuration. By default, +@@ -191,7 +191,7 @@ config RCU_FAST_NO_HZ + config RCU_BOOST + bool "Enable RCU priority boosting" + depends on RT_MUTEXES && PREEMPT_RCU && RCU_EXPERT +- default n ++ default y if PREEMPT_RT_FULL + help + This option boosts the priority of preempted RCU readers that + block the current preemptible RCU grace period for too long. diff --git a/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch b/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch new file mode 100644 index 000000000..28346894e --- /dev/null +++ b/debian/patches/features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch @@ -0,0 +1,348 @@ +Subject: rcu: Merge RCU-bh into RCU-preempt +Date: Wed, 5 Oct 2011 11:59:38 -0700 +From: Thomas Gleixner +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The Linux kernel has long RCU-bh read-side critical sections that +intolerably increase scheduling latency under mainline's RCU-bh rules, +which include RCU-bh read-side critical sections being non-preemptible. +This patch therefore arranges for RCU-bh to be implemented in terms of +RCU-preempt for CONFIG_PREEMPT_RT_FULL=y. + +This has the downside of defeating the purpose of RCU-bh, namely, +handling the case where the system is subjected to a network-based +denial-of-service attack that keeps at least one CPU doing full-time +softirq processing. This issue will be fixed by a later commit. + +The current commit will need some work to make it appropriate for +mainline use, for example, it needs to be extended to cover Tiny RCU. + +[ paulmck: Added a useful changelog ] + +Signed-off-by: Thomas Gleixner +Signed-off-by: Paul E. McKenney +Link: http://lkml.kernel.org/r/20111005185938.GA20403@linux.vnet.ibm.com +Signed-off-by: Thomas Gleixner + +--- + include/linux/rcupdate.h | 19 +++++++++++++++++++ + include/linux/rcutree.h | 8 ++++++++ + kernel/rcu/rcu.h | 14 +++++++++++--- + kernel/rcu/rcutorture.c | 7 +++++++ + kernel/rcu/tree.c | 24 ++++++++++++++++++++++++ + kernel/rcu/tree.h | 2 ++ + kernel/rcu/update.c | 2 ++ + 7 files changed, 73 insertions(+), 3 deletions(-) + +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -56,7 +56,11 @@ void call_rcu(struct rcu_head *head, rcu + #define call_rcu call_rcu_sched + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define call_rcu_bh call_rcu ++#else + void call_rcu_bh(struct rcu_head *head, rcu_callback_t func); ++#endif + void call_rcu_sched(struct rcu_head *head, rcu_callback_t func); + void synchronize_sched(void); + void rcu_barrier_tasks(void); +@@ -264,7 +268,14 @@ extern struct lockdep_map rcu_sched_lock + extern struct lockdep_map rcu_callback_map; + int debug_lockdep_rcu_enabled(void); + int rcu_read_lock_held(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline int rcu_read_lock_bh_held(void) ++{ ++ return rcu_read_lock_held(); ++} ++#else + int rcu_read_lock_bh_held(void); ++#endif + int rcu_read_lock_sched_held(void); + + #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ +@@ -665,10 +676,14 @@ static inline void rcu_read_unlock(void) + static inline void rcu_read_lock_bh(void) + { + local_bh_disable(); ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_lock(); ++#else + __acquire(RCU_BH); + rcu_lock_acquire(&rcu_bh_lock_map); + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_lock_bh() used illegally while idle"); ++#endif + } + + /* +@@ -678,10 +693,14 @@ static inline void rcu_read_lock_bh(void + */ + static inline void rcu_read_unlock_bh(void) + { ++#ifdef CONFIG_PREEMPT_RT_FULL ++ rcu_read_unlock(); ++#else + RCU_LOCKDEP_WARN(!rcu_is_watching(), + "rcu_read_unlock_bh() used illegally while idle"); + rcu_lock_release(&rcu_bh_lock_map); + __release(RCU_BH); ++#endif + local_bh_enable(); + } + +--- a/include/linux/rcutree.h ++++ b/include/linux/rcutree.h +@@ -44,7 +44,11 @@ static inline void rcu_virt_note_context + rcu_note_context_switch(false); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define synchronize_rcu_bh synchronize_rcu ++#else + void synchronize_rcu_bh(void); ++#endif + void synchronize_sched_expedited(void); + void synchronize_rcu_expedited(void); + +@@ -72,7 +76,11 @@ static inline void synchronize_rcu_bh_ex + } + + void rcu_barrier(void); ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define rcu_barrier_bh rcu_barrier ++#else + void rcu_barrier_bh(void); ++#endif + void rcu_barrier_sched(void); + bool rcu_eqs_special_set(int cpu); + unsigned long get_state_synchronize_rcu(void); +--- a/kernel/rcu/rcu.h ++++ b/kernel/rcu/rcu.h +@@ -478,20 +478,28 @@ static inline void show_rcu_gp_kthreads( + extern unsigned long rcutorture_testseq; + extern unsigned long rcutorture_vernum; + unsigned long rcu_batches_started(void); +-unsigned long rcu_batches_started_bh(void); + unsigned long rcu_batches_started_sched(void); + unsigned long rcu_batches_completed(void); +-unsigned long rcu_batches_completed_bh(void); + unsigned long rcu_batches_completed_sched(void); + unsigned long rcu_exp_batches_completed(void); + unsigned long rcu_exp_batches_completed_sched(void); + unsigned long srcu_batches_completed(struct srcu_struct *sp); + void show_rcu_gp_kthreads(void); + void rcu_force_quiescent_state(void); +-void rcu_bh_force_quiescent_state(void); + void rcu_sched_force_quiescent_state(void); + extern struct workqueue_struct *rcu_gp_wq; + extern struct workqueue_struct *rcu_par_gp_wq; ++ ++#ifndef CONFIG_PREEMPT_RT_FULL ++void rcu_bh_force_quiescent_state(void); ++unsigned long rcu_batches_started_bh(void); ++unsigned long rcu_batches_completed_bh(void); ++#else ++# define rcu_bh_force_quiescent_state rcu_force_quiescent_state ++# define rcu_batches_completed_bh rcu_batches_completed ++# define rcu_batches_started_bh rcu_batches_completed ++#endif ++ + #endif /* #else #ifdef CONFIG_TINY_RCU */ + + #ifdef CONFIG_RCU_NOCB_CPU +--- a/kernel/rcu/rcutorture.c ++++ b/kernel/rcu/rcutorture.c +@@ -413,6 +413,7 @@ static struct rcu_torture_ops rcu_ops = + .name = "rcu" + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Definitions for rcu_bh torture testing. + */ +@@ -452,6 +453,12 @@ static struct rcu_torture_ops rcu_bh_ops + .name = "rcu_bh" + }; + ++#else ++static struct rcu_torture_ops rcu_bh_ops = { ++ .ttype = INVALID_RCU_FLAVOR, ++}; ++#endif ++ + /* + * Don't even think about trying any of these in real life!!! + * The names includes "busted", and they really means it! +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -243,6 +243,7 @@ void rcu_sched_qs(void) + this_cpu_ptr(&rcu_sched_data), true); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void rcu_bh_qs(void) + { + RCU_LOCKDEP_WARN(preemptible(), "rcu_bh_qs() invoked with preemption enabled!!!"); +@@ -253,6 +254,7 @@ void rcu_bh_qs(void) + __this_cpu_write(rcu_bh_data.cpu_no_qs.b.norm, false); + } + } ++#endif + + /* + * Steal a bit from the bottom of ->dynticks for idle entry/exit +@@ -549,11 +551,13 @@ EXPORT_SYMBOL_GPL(rcu_batches_started_sc + /* + * Return the number of RCU BH batches started thus far for debug & stats. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + unsigned long rcu_batches_started_bh(void) + { + return rcu_bh_state.gpnum; + } + EXPORT_SYMBOL_GPL(rcu_batches_started_bh); ++#endif + + /* + * Return the number of RCU batches completed thus far for debug & stats. +@@ -573,6 +577,7 @@ unsigned long rcu_batches_completed_sche + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Return the number of RCU BH batches completed thus far for debug & stats. + */ +@@ -581,6 +586,7 @@ unsigned long rcu_batches_completed_bh(v + return rcu_bh_state.completed; + } + EXPORT_SYMBOL_GPL(rcu_batches_completed_bh); ++#endif + + /* + * Return the number of RCU expedited batches completed thus far for +@@ -604,6 +610,7 @@ unsigned long rcu_exp_batches_completed_ + } + EXPORT_SYMBOL_GPL(rcu_exp_batches_completed_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * Force a quiescent state. + */ +@@ -622,6 +629,13 @@ void rcu_bh_force_quiescent_state(void) + } + EXPORT_SYMBOL_GPL(rcu_bh_force_quiescent_state); + ++#else ++void rcu_force_quiescent_state(void) ++{ ++} ++EXPORT_SYMBOL_GPL(rcu_force_quiescent_state); ++#endif ++ + /* + * Force a quiescent state for RCU-sched. + */ +@@ -672,9 +686,11 @@ void rcutorture_get_gp_data(enum rcutort + case RCU_FLAVOR: + rsp = rcu_state_p; + break; ++#ifndef CONFIG_PREEMPT_RT_FULL + case RCU_BH_FLAVOR: + rsp = &rcu_bh_state; + break; ++#endif + case RCU_SCHED_FLAVOR: + rsp = &rcu_sched_state; + break; +@@ -2986,6 +3002,7 @@ void call_rcu_sched(struct rcu_head *hea + } + EXPORT_SYMBOL_GPL(call_rcu_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * call_rcu_bh() - Queue an RCU for invocation after a quicker grace period. + * @head: structure to be used for queueing the RCU updates. +@@ -3013,6 +3030,7 @@ void call_rcu_bh(struct rcu_head *head, + __call_rcu(head, func, &rcu_bh_state, -1, 0); + } + EXPORT_SYMBOL_GPL(call_rcu_bh); ++#endif + + /* + * Queue an RCU callback for lazy invocation after a grace period. +@@ -3098,6 +3116,7 @@ void synchronize_sched(void) + } + EXPORT_SYMBOL_GPL(synchronize_sched); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * synchronize_rcu_bh - wait until an rcu_bh grace period has elapsed. + * +@@ -3124,6 +3143,7 @@ void synchronize_rcu_bh(void) + wait_rcu_gp(call_rcu_bh); + } + EXPORT_SYMBOL_GPL(synchronize_rcu_bh); ++#endif + + /** + * get_state_synchronize_rcu - Snapshot current RCU state +@@ -3457,6 +3477,7 @@ static void _rcu_barrier(struct rcu_stat + mutex_unlock(&rsp->barrier_mutex); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_barrier_bh - Wait until all in-flight call_rcu_bh() callbacks complete. + */ +@@ -3465,6 +3486,7 @@ void rcu_barrier_bh(void) + _rcu_barrier(&rcu_bh_state); + } + EXPORT_SYMBOL_GPL(rcu_barrier_bh); ++#endif + + /** + * rcu_barrier_sched - Wait for in-flight call_rcu_sched() callbacks. +@@ -4081,7 +4103,9 @@ void __init rcu_init(void) + + rcu_bootup_announce(); + rcu_init_geometry(); ++#ifndef CONFIG_PREEMPT_RT_FULL + rcu_init_one(&rcu_bh_state); ++#endif + rcu_init_one(&rcu_sched_state); + if (dump_tree) + rcu_dump_rcu_node_tree(&rcu_sched_state); +--- a/kernel/rcu/tree.h ++++ b/kernel/rcu/tree.h +@@ -422,7 +422,9 @@ extern struct list_head rcu_struct_flavo + */ + extern struct rcu_state rcu_sched_state; + ++#ifndef CONFIG_PREEMPT_RT_FULL + extern struct rcu_state rcu_bh_state; ++#endif + + #ifdef CONFIG_PREEMPT_RCU + extern struct rcu_state rcu_preempt_state; +--- a/kernel/rcu/update.c ++++ b/kernel/rcu/update.c +@@ -286,6 +286,7 @@ int rcu_read_lock_held(void) + } + EXPORT_SYMBOL_GPL(rcu_read_lock_held); + ++#ifndef CONFIG_PREEMPT_RT_FULL + /** + * rcu_read_lock_bh_held() - might we be in RCU-bh read-side critical section? + * +@@ -312,6 +313,7 @@ int rcu_read_lock_bh_held(void) + return in_softirq() || irqs_disabled(); + } + EXPORT_SYMBOL_GPL(rcu_read_lock_bh_held); ++#endif + + #endif /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ + diff --git a/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch b/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch new file mode 100644 index 000000000..42e5abbea --- /dev/null +++ b/debian/patches/features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch @@ -0,0 +1,69 @@ +Subject: ARM: Initialize split page table locks for vector page +From: Frank Rowand +Date: Sat, 1 Oct 2011 18:58:13 -0700 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Without this patch, ARM can not use SPLIT_PTLOCK_CPUS if +PREEMPT_RT_FULL=y because vectors_user_mapping() creates a +VM_ALWAYSDUMP mapping of the vector page (address 0xffff0000), but no +ptl->lock has been allocated for the page. An attempt to coredump +that page will result in a kernel NULL pointer dereference when +follow_page() attempts to lock the page. + +The call tree to the NULL pointer dereference is: + + do_notify_resume() + get_signal_to_deliver() + do_coredump() + elf_core_dump() + get_dump_page() + __get_user_pages() + follow_page() + pte_offset_map_lock() <----- a #define + ... + rt_spin_lock() + +The underlying problem is exposed by mm-shrink-the-page-frame-to-rt-size.patch. + +Signed-off-by: Frank Rowand +Cc: Frank +Cc: Peter Zijlstra +Link: http://lkml.kernel.org/r/4E87C535.2030907@am.sony.com +Signed-off-by: Thomas Gleixner +--- + arch/arm/kernel/process.c | 24 ++++++++++++++++++++++++ + 1 file changed, 24 insertions(+) + +--- a/arch/arm/kernel/process.c ++++ b/arch/arm/kernel/process.c +@@ -324,6 +324,30 @@ unsigned long arch_randomize_brk(struct + } + + #ifdef CONFIG_MMU ++/* ++ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not ++ * initialized by pgtable_page_ctor() then a coredump of the vector page will ++ * fail. ++ */ ++static int __init vectors_user_mapping_init_page(void) ++{ ++ struct page *page; ++ unsigned long addr = 0xffff0000; ++ pgd_t *pgd; ++ pud_t *pud; ++ pmd_t *pmd; ++ ++ pgd = pgd_offset_k(addr); ++ pud = pud_offset(pgd, addr); ++ pmd = pmd_offset(pud, addr); ++ page = pmd_page(*(pmd)); ++ ++ pgtable_page_ctor(page); ++ ++ return 0; ++} ++late_initcall(vectors_user_mapping_init_page); ++ + #ifdef CONFIG_KUSER_HELPERS + /* + * The vectors page is always readable from user space for the diff --git a/debian/patches/features/all/rt/rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch b/debian/patches/features/all/rt/rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch new file mode 100644 index 000000000..b5debad29 --- /dev/null +++ b/debian/patches/features/all/rt/rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch @@ -0,0 +1,155 @@ +From: Daniel Bristot de Oliveira +Date: Mon, 26 Jun 2017 17:07:15 +0200 +Subject: rt: Increase/decrease the nr of migratory tasks when enabling/disabling migration +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There is a problem in the migrate_disable()/enable() implementation +regarding the number of migratory tasks in the rt/dl RQs. The problem +is the following: + +When a task is attached to the rt runqueue, it is checked if it either +can run in more than one CPU, or if it is with migration disable. If +either check is true, the rt_rq->rt_nr_migratory counter is not +increased. The counter increases otherwise. + +When the task is detached, the same check is done. If either check is +true, the rt_rq->rt_nr_migratory counter is not decreased. The counter +decreases otherwise. The same check is done in the dl scheduler. + +One important thing is that, migrate disable/enable does not touch this +counter for tasks attached to the rt rq. So suppose the following chain +of events. + +Assumptions: +Task A is the only runnable task in A Task B runs on the CPU B +Task A runs on CFS (non-rt) Task B has RT priority +Thus, rt_nr_migratory is 0 B is running +Task A can run on all CPUS. + +Timeline: + CPU A/TASK A CPU B/TASK B +A takes the rt mutex X . +A disables migration . + . B tries to take the rt mutex X + . As it is held by A { + . A inherits the rt priority of B + . A is dequeued from CFS RQ of CPU A + . A is enqueued in the RT RQ of CPU A + . As migration is disabled + . rt_nr_migratory in A is not increased + . +A enables migration +A releases the rt mutex X { + A returns to its original priority + A ask to be dequeued from RT RQ { + As migration is now enabled and it can run on all CPUS { + rt_nr_migratory should be decreased + As rt_nr_migratory is 0, rt_nr_migratory under flows + } +} + +This variable is important because it notifies if there are more than one +runnable & migratory task in the runqueue. If there are more than one +tasks, the rt_rq is set as overloaded, and then tries to migrate some +tasks. This rule is important to keep the scheduler working conserving, +that is, in a system with M CPUs, the M highest priority tasks should be +running. + +As rt_nr_migratory is unsigned, it will become > 0, notifying that the +RQ is overloaded, activating pushing mechanism without need. + +This patch fixes this problem by decreasing/increasing the +rt/dl_nr_migratory in the migrate disable/enable operations. + +Reported-by: Pei Zhang +Reported-by: Luiz Capitulino +Signed-off-by: Daniel Bristot de Oliveira +Cc: Luis Claudio R. Goncalves +Cc: Clark Williams +Cc: Luiz Capitulino +Cc: Sebastian Andrzej Siewior +Cc: Thomas Gleixner +Cc: Steven Rostedt +Cc: Peter Zijlstra +Cc: Ingo Molnar +Cc: LKML +Cc: linux-rt-users +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/sched/core.c | 49 ++++++++++++++++++++++++++++++++++++++++++++----- + 1 file changed, 44 insertions(+), 5 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7161,6 +7161,47 @@ const u32 sched_prio_to_wmult[40] = { + + #if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) + ++static inline void ++update_nr_migratory(struct task_struct *p, long delta) ++{ ++ if (unlikely((p->sched_class == &rt_sched_class || ++ p->sched_class == &dl_sched_class) && ++ p->nr_cpus_allowed > 1)) { ++ if (p->sched_class == &rt_sched_class) ++ task_rq(p)->rt.rt_nr_migratory += delta; ++ else ++ task_rq(p)->dl.dl_nr_migratory += delta; ++ } ++} ++ ++static inline void ++migrate_disable_update_cpus_allowed(struct task_struct *p) ++{ ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ p->cpus_ptr = cpumask_of(smp_processor_id()); ++ ++ rq = task_rq_lock(p, &rf); ++ update_nr_migratory(p, -1); ++ p->nr_cpus_allowed = 1; ++ task_rq_unlock(rq, p, &rf); ++} ++ ++static inline void ++migrate_enable_update_cpus_allowed(struct task_struct *p) ++{ ++ struct rq *rq; ++ struct rq_flags rf; ++ ++ p->cpus_ptr = &p->cpus_mask; ++ ++ rq = task_rq_lock(p, &rf); ++ p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); ++ update_nr_migratory(p, 1); ++ task_rq_unlock(rq, p, &rf); ++} ++ + void migrate_disable(void) + { + struct task_struct *p = current; +@@ -7184,10 +7225,9 @@ void migrate_disable(void) + } + + preempt_disable(); +- p->migrate_disable = 1; + +- p->cpus_ptr = cpumask_of(smp_processor_id()); +- p->nr_cpus_allowed = 1; ++ migrate_disable_update_cpus_allowed(p); ++ p->migrate_disable = 1; + + preempt_enable(); + } +@@ -7219,9 +7259,8 @@ void migrate_enable(void) + + preempt_disable(); + +- p->cpus_ptr = &p->cpus_mask; +- p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask); + p->migrate_disable = 0; ++ migrate_enable_update_cpus_allowed(p); + + if (p->migrate_disable_update) { + struct rq *rq; diff --git a/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch b/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch new file mode 100644 index 000000000..11dbf185c --- /dev/null +++ b/debian/patches/features/all/rt/rt-introduce-cpu-chill.patch @@ -0,0 +1,105 @@ +Subject: rt: Introduce cpu_chill() +From: Thomas Gleixner +Date: Wed, 07 Mar 2012 20:51:03 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Retry loops on RT might loop forever when the modifying side was +preempted. Add cpu_chill() to replace cpu_relax(). cpu_chill() +defaults to cpu_relax() for non RT. On RT it puts the looping task to +sleep for a tick so the preempted task can make progress. + +Steven Rostedt changed it to use a hrtimer instead of msleep(): +| +|Ulrich Obergfell pointed out that cpu_chill() calls msleep() which is woken +|up by the ksoftirqd running the TIMER softirq. But as the cpu_chill() is +|called from softirq context, it may block the ksoftirqd() from running, in +|which case, it may never wake up the msleep() causing the deadlock. + ++ bigeasy later changed to schedule_hrtimeout() +|If a task calls cpu_chill() and gets woken up by a regular or spurious +|wakeup and has a signal pending, then it exits the sleep loop in +|do_nanosleep() and sets up the restart block. If restart->nanosleep.type is +|not TI_NONE then this results in accessing a stale user pointer from a +|previously interrupted syscall and a copy to user based on the stale +|pointer or a BUG() when 'type' is not supported in nanosleep_copyout(). + ++ bigeasy: add PF_NOFREEZE: +| [....] Waiting for /dev to be fully populated... +| ===================================== +| [ BUG: udevd/229 still has locks held! ] +| 3.12.11-rt17 #23 Not tainted +| ------------------------------------- +| 1 lock held by udevd/229: +| #0: (&type->i_mutex_dir_key#2){+.+.+.}, at: lookup_slow+0x28/0x98 +| +| stack backtrace: +| CPU: 0 PID: 229 Comm: udevd Not tainted 3.12.11-rt17 #23 +| (unwind_backtrace+0x0/0xf8) from (show_stack+0x10/0x14) +| (show_stack+0x10/0x14) from (dump_stack+0x74/0xbc) +| (dump_stack+0x74/0xbc) from (do_nanosleep+0x120/0x160) +| (do_nanosleep+0x120/0x160) from (hrtimer_nanosleep+0x90/0x110) +| (hrtimer_nanosleep+0x90/0x110) from (cpu_chill+0x30/0x38) +| (cpu_chill+0x30/0x38) from (dentry_kill+0x158/0x1ec) +| (dentry_kill+0x158/0x1ec) from (dput+0x74/0x15c) +| (dput+0x74/0x15c) from (lookup_real+0x4c/0x50) +| (lookup_real+0x4c/0x50) from (__lookup_hash+0x34/0x44) +| (__lookup_hash+0x34/0x44) from (lookup_slow+0x38/0x98) +| (lookup_slow+0x38/0x98) from (path_lookupat+0x208/0x7fc) +| (path_lookupat+0x208/0x7fc) from (filename_lookup+0x20/0x60) +| (filename_lookup+0x20/0x60) from (user_path_at_empty+0x50/0x7c) +| (user_path_at_empty+0x50/0x7c) from (user_path_at+0x14/0x1c) +| (user_path_at+0x14/0x1c) from (vfs_fstatat+0x48/0x94) +| (vfs_fstatat+0x48/0x94) from (SyS_stat64+0x14/0x30) +| (SyS_stat64+0x14/0x30) from (ret_fast_syscall+0x0/0x48) + +Signed-off-by: Thomas Gleixner +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/delay.h | 6 ++++++ + kernel/time/hrtimer.c | 21 +++++++++++++++++++++ + 2 files changed, 27 insertions(+) + +--- a/include/linux/delay.h ++++ b/include/linux/delay.h +@@ -64,4 +64,10 @@ static inline void ssleep(unsigned int s + msleep(seconds * 1000); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void cpu_chill(void); ++#else ++# define cpu_chill() cpu_relax() ++#endif ++ + #endif /* defined(_LINUX_DELAY_H) */ +--- a/kernel/time/hrtimer.c ++++ b/kernel/time/hrtimer.c +@@ -1895,6 +1895,27 @@ COMPAT_SYSCALL_DEFINE2(nanosleep, struct + } + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Sleep for 1 ms in hope whoever holds what we want will let it go. ++ */ ++void cpu_chill(void) ++{ ++ ktime_t chill_time; ++ unsigned int freeze_flag = current->flags & PF_NOFREEZE; ++ ++ chill_time = ktime_set(0, NSEC_PER_MSEC); ++ set_current_state(TASK_UNINTERRUPTIBLE); ++ current->flags |= PF_NOFREEZE; ++ sleeping_lock_inc(); ++ schedule_hrtimeout(&chill_time, HRTIMER_MODE_REL_HARD); ++ sleeping_lock_dec(); ++ if (!freeze_flag) ++ current->flags &= ~PF_NOFREEZE; ++} ++EXPORT_SYMBOL(cpu_chill); ++#endif ++ + /* + * Functions related to boot-time initialization: + */ diff --git a/debian/patches/features/all/rt/rt-local-irq-lock.patch b/debian/patches/features/all/rt/rt-local-irq-lock.patch new file mode 100644 index 000000000..1d19bd0f1 --- /dev/null +++ b/debian/patches/features/all/rt/rt-local-irq-lock.patch @@ -0,0 +1,331 @@ +Subject: rt: Add local irq locks +From: Thomas Gleixner +Date: Mon, 20 Jun 2011 09:03:47 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Introduce locallock. For !RT this maps to preempt_disable()/ +local_irq_disable() so there is not much that changes. For RT this will +map to a spinlock. This makes preemption possible and locked "ressource" +gets the lockdep anotation it wouldn't have otherwise. The locks are +recursive for owner == current. Also, all locks user migrate_disable() +which ensures that the task is not migrated to another CPU while the lock +is held and the owner is preempted. + +Signed-off-by: Thomas Gleixner +--- + include/linux/locallock.h | 271 ++++++++++++++++++++++++++++++++++++++++++++++ + include/linux/percpu.h | 29 ++++ + 2 files changed, 300 insertions(+) + +--- /dev/null ++++ b/include/linux/locallock.h +@@ -0,0 +1,271 @@ ++#ifndef _LINUX_LOCALLOCK_H ++#define _LINUX_LOCALLOCK_H ++ ++#include ++#include ++ ++#ifdef CONFIG_PREEMPT_RT_BASE ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define LL_WARN(cond) WARN_ON(cond) ++#else ++# define LL_WARN(cond) do { } while (0) ++#endif ++ ++/* ++ * per cpu lock based substitute for local_irq_*() ++ */ ++struct local_irq_lock { ++ spinlock_t lock; ++ struct task_struct *owner; ++ int nestcnt; ++ unsigned long flags; ++}; ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) \ ++ DEFINE_PER_CPU(struct local_irq_lock, lvar) = { \ ++ .lock = __SPIN_LOCK_UNLOCKED((lvar).lock) } ++ ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) \ ++ DECLARE_PER_CPU(struct local_irq_lock, lvar) ++ ++#define local_irq_lock_init(lvar) \ ++ do { \ ++ int __cpu; \ ++ for_each_possible_cpu(__cpu) \ ++ spin_lock_init(&per_cpu(lvar, __cpu).lock); \ ++ } while (0) ++ ++static inline void __local_lock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ spin_lock(&lv->lock); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ } ++ lv->nestcnt++; ++} ++ ++#define local_lock(lvar) \ ++ do { __local_lock(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_on(lvar, cpu) \ ++ do { __local_lock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline int __local_trylock(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current && spin_trylock(&lv->lock)) { ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++ return 1; ++ } else if (lv->owner == current) { ++ lv->nestcnt++; ++ return 1; ++ } ++ return 0; ++} ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ int __locked; \ ++ __locked = __local_trylock(&get_local_var(lvar)); \ ++ if (!__locked) \ ++ put_local_var(lvar); \ ++ __locked; \ ++ }) ++ ++static inline void __local_unlock(struct local_irq_lock *lv) ++{ ++ LL_WARN(lv->nestcnt == 0); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return; ++ ++ lv->owner = NULL; ++ spin_unlock(&lv->lock); ++} ++ ++#define local_unlock(lvar) \ ++ do { \ ++ __local_unlock(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_on(lvar, cpu) \ ++ do { __local_unlock(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_lock_irq(struct local_irq_lock *lv) ++{ ++ spin_lock_irqsave(&lv->lock, lv->flags); ++ LL_WARN(lv->owner); ++ LL_WARN(lv->nestcnt); ++ lv->owner = current; ++ lv->nestcnt = 1; ++} ++ ++#define local_lock_irq(lvar) \ ++ do { __local_lock_irq(&get_local_var(lvar)); } while (0) ++ ++#define local_lock_irq_on(lvar, cpu) \ ++ do { __local_lock_irq(&per_cpu(lvar, cpu)); } while (0) ++ ++static inline void __local_unlock_irq(struct local_irq_lock *lv) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ lv->owner = NULL; ++ lv->nestcnt = 0; ++ spin_unlock_irq(&lv->lock); ++} ++ ++#define local_unlock_irq(lvar) \ ++ do { \ ++ __local_unlock_irq(this_cpu_ptr(&lvar)); \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irq_on(lvar, cpu) \ ++ do { \ ++ __local_unlock_irq(&per_cpu(lvar, cpu)); \ ++ } while (0) ++ ++static inline int __local_lock_irqsave(struct local_irq_lock *lv) ++{ ++ if (lv->owner != current) { ++ __local_lock_irq(lv); ++ return 0; ++ } else { ++ lv->nestcnt++; ++ return 1; ++ } ++} ++ ++#define local_lock_irqsave(lvar, _flags) \ ++ do { \ ++ if (__local_lock_irqsave(&get_local_var(lvar))) \ ++ put_local_var(lvar); \ ++ _flags = __this_cpu_read(lvar.flags); \ ++ } while (0) ++ ++#define local_lock_irqsave_on(lvar, _flags, cpu) \ ++ do { \ ++ __local_lock_irqsave(&per_cpu(lvar, cpu)); \ ++ _flags = per_cpu(lvar, cpu).flags; \ ++ } while (0) ++ ++static inline int __local_unlock_irqrestore(struct local_irq_lock *lv, ++ unsigned long flags) ++{ ++ LL_WARN(!lv->nestcnt); ++ LL_WARN(lv->owner != current); ++ if (--lv->nestcnt) ++ return 0; ++ ++ lv->owner = NULL; ++ spin_unlock_irqrestore(&lv->lock, lv->flags); ++ return 1; ++} ++ ++#define local_unlock_irqrestore(lvar, flags) \ ++ do { \ ++ if (__local_unlock_irqrestore(this_cpu_ptr(&lvar), flags)) \ ++ put_local_var(lvar); \ ++ } while (0) ++ ++#define local_unlock_irqrestore_on(lvar, flags, cpu) \ ++ do { \ ++ __local_unlock_irqrestore(&per_cpu(lvar, cpu), flags); \ ++ } while (0) ++ ++#define local_spin_trylock_irq(lvar, lock) \ ++ ({ \ ++ int __locked; \ ++ local_lock_irq(lvar); \ ++ __locked = spin_trylock(lock); \ ++ if (!__locked) \ ++ local_unlock_irq(lvar); \ ++ __locked; \ ++ }) ++ ++#define local_spin_lock_irq(lvar, lock) \ ++ do { \ ++ local_lock_irq(lvar); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irq(lvar, lock) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irq(lvar); \ ++ } while (0) ++ ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ do { \ ++ local_lock_irqsave(lvar, flags); \ ++ spin_lock(lock); \ ++ } while (0) ++ ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ do { \ ++ spin_unlock(lock); \ ++ local_unlock_irqrestore(lvar, flags); \ ++ } while (0) ++ ++#define get_locked_var(lvar, var) \ ++ (*({ \ ++ local_lock(lvar); \ ++ this_cpu_ptr(&var); \ ++ })) ++ ++#define put_locked_var(lvar, var) local_unlock(lvar); ++ ++#define local_lock_cpu(lvar) \ ++ ({ \ ++ local_lock(lvar); \ ++ smp_processor_id(); \ ++ }) ++ ++#define local_unlock_cpu(lvar) local_unlock(lvar) ++ ++#else /* PREEMPT_RT_BASE */ ++ ++#define DEFINE_LOCAL_IRQ_LOCK(lvar) __typeof__(const int) lvar ++#define DECLARE_LOCAL_IRQ_LOCK(lvar) extern __typeof__(const int) lvar ++ ++static inline void local_irq_lock_init(int lvar) { } ++ ++#define local_trylock(lvar) \ ++ ({ \ ++ preempt_disable(); \ ++ 1; \ ++ }) ++ ++#define local_lock(lvar) preempt_disable() ++#define local_unlock(lvar) preempt_enable() ++#define local_lock_irq(lvar) local_irq_disable() ++#define local_lock_irq_on(lvar, cpu) local_irq_disable() ++#define local_unlock_irq(lvar) local_irq_enable() ++#define local_unlock_irq_on(lvar, cpu) local_irq_enable() ++#define local_lock_irqsave(lvar, flags) local_irq_save(flags) ++#define local_unlock_irqrestore(lvar, flags) local_irq_restore(flags) ++ ++#define local_spin_trylock_irq(lvar, lock) spin_trylock_irq(lock) ++#define local_spin_lock_irq(lvar, lock) spin_lock_irq(lock) ++#define local_spin_unlock_irq(lvar, lock) spin_unlock_irq(lock) ++#define local_spin_lock_irqsave(lvar, lock, flags) \ ++ spin_lock_irqsave(lock, flags) ++#define local_spin_unlock_irqrestore(lvar, lock, flags) \ ++ spin_unlock_irqrestore(lock, flags) ++ ++#define get_locked_var(lvar, var) get_cpu_var(var) ++#define put_locked_var(lvar, var) put_cpu_var(var) ++ ++#define local_lock_cpu(lvar) get_cpu() ++#define local_unlock_cpu(lvar) put_cpu() ++ ++#endif ++ ++#endif +--- a/include/linux/percpu.h ++++ b/include/linux/percpu.h +@@ -19,6 +19,35 @@ + #define PERCPU_MODULE_RESERVE 0 + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++#define get_local_var(var) (*({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(&var); })) ++ ++#define put_local_var(var) do { \ ++ (void)&(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++# define get_local_ptr(var) ({ \ ++ migrate_disable(); \ ++ this_cpu_ptr(var); }) ++ ++# define put_local_ptr(var) do { \ ++ (void)(var); \ ++ migrate_enable(); \ ++} while (0) ++ ++#else ++ ++#define get_local_var(var) get_cpu_var(var) ++#define put_local_var(var) put_cpu_var(var) ++#define get_local_ptr(var) get_cpu_ptr(var) ++#define put_local_ptr(var) put_cpu_ptr(var) ++ ++#endif ++ + /* minimum unit size, also is the maximum supported allocation size */ + #define PCPU_MIN_UNIT_SIZE PFN_ALIGN(32 << 10) + diff --git a/debian/patches/features/all/rt/rt-preempt-base-config.patch b/debian/patches/features/all/rt/rt-preempt-base-config.patch new file mode 100644 index 000000000..8a3bf9845 --- /dev/null +++ b/debian/patches/features/all/rt/rt-preempt-base-config.patch @@ -0,0 +1,54 @@ +Subject: rt: Provide PREEMPT_RT_BASE config switch +From: Thomas Gleixner +Date: Fri, 17 Jun 2011 12:39:57 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Introduce PREEMPT_RT_BASE which enables parts of +PREEMPT_RT_FULL. Forces interrupt threading and enables some of the RT +substitutions for testing. + +Signed-off-by: Thomas Gleixner +--- + kernel/Kconfig.preempt | 19 +++++++++++++++++-- + 1 file changed, 17 insertions(+), 2 deletions(-) + +--- a/kernel/Kconfig.preempt ++++ b/kernel/Kconfig.preempt +@@ -1,3 +1,10 @@ ++config PREEMPT ++ bool ++ select PREEMPT_COUNT ++ ++config PREEMPT_RT_BASE ++ bool ++ select PREEMPT + + choice + prompt "Preemption Model" +@@ -33,9 +40,9 @@ config PREEMPT_VOLUNTARY + + Select this if you are building a kernel for a desktop system. + +-config PREEMPT ++config PREEMPT__LL + bool "Preemptible Kernel (Low-Latency Desktop)" +- select PREEMPT_COUNT ++ select PREEMPT + select UNINLINE_SPIN_UNLOCK if !ARCH_INLINE_SPIN_UNLOCK + help + This option reduces the latency of the kernel by making +@@ -52,6 +59,14 @@ config PREEMPT + embedded system with latency requirements in the milliseconds + range. + ++config PREEMPT_RTB ++ bool "Preemptible Kernel (Basic RT)" ++ select PREEMPT_RT_BASE ++ help ++ This option is basically the same as (Low-Latency Desktop) but ++ enables changes which are preliminary for the full preemptible ++ RT kernel. ++ + endchoice + + config PREEMPT_COUNT diff --git a/debian/patches/features/all/rt/rt-serial-warn-fix.patch b/debian/patches/features/all/rt/rt-serial-warn-fix.patch new file mode 100644 index 000000000..1e532269a --- /dev/null +++ b/debian/patches/features/all/rt/rt-serial-warn-fix.patch @@ -0,0 +1,38 @@ +Subject: rt: Improve the serial console PASS_LIMIT +From: Ingo Molnar +Date: Wed Dec 14 13:05:54 CET 2011 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Beyond the warning: + + drivers/tty/serial/8250/8250.c:1613:6: warning: unused variable ‘pass_counter’ [-Wunused-variable] + +the solution of just looping infinitely was ugly - up it to 1 million to +give it a chance to continue in some really ugly situation. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner +--- + drivers/tty/serial/8250/8250_core.c | 11 ++++++++++- + 1 file changed, 10 insertions(+), 1 deletion(-) + +--- a/drivers/tty/serial/8250/8250_core.c ++++ b/drivers/tty/serial/8250/8250_core.c +@@ -54,7 +54,16 @@ static struct uart_driver serial8250_reg + + static unsigned int skip_txen_test; /* force skip of txen test at init time */ + +-#define PASS_LIMIT 512 ++/* ++ * On -rt we can have a more delays, and legitimately ++ * so - so don't drop work spuriously and spam the ++ * syslog: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# define PASS_LIMIT 1000000 ++#else ++# define PASS_LIMIT 512 ++#endif + + #include + /* diff --git a/debian/patches/features/all/rt/rtmutex-Make-lock_killable-work.patch b/debian/patches/features/all/rt/rtmutex-Make-lock_killable-work.patch new file mode 100644 index 000000000..441caba10 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-Make-lock_killable-work.patch @@ -0,0 +1,45 @@ +From: Thomas Gleixner +Date: Sat, 1 Apr 2017 12:50:59 +0200 +Subject: [PATCH] rtmutex: Make lock_killable work +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Locking an rt mutex killable does not work because signal handling is +restricted to TASK_INTERRUPTIBLE. + +Use signal_pending_state() unconditionaly. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 19 +++++++------------ + 1 file changed, 7 insertions(+), 12 deletions(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1201,18 +1201,13 @@ static int __sched + if (try_to_take_rt_mutex(lock, current, waiter)) + break; + +- /* +- * TASK_INTERRUPTIBLE checks for signals and +- * timeout. Ignored otherwise. +- */ +- if (likely(state == TASK_INTERRUPTIBLE)) { +- /* Signal pending? */ +- if (signal_pending(current)) +- ret = -EINTR; +- if (timeout && !timeout->task) +- ret = -ETIMEDOUT; +- if (ret) +- break; ++ if (timeout && !timeout->task) { ++ ret = -ETIMEDOUT; ++ break; ++ } ++ if (signal_pending_state(state, current)) { ++ ret = -EINTR; ++ break; + } + + raw_spin_unlock_irq(&lock->wait_lock); diff --git a/debian/patches/features/all/rt/rtmutex-Provide-rt_mutex_slowlock_locked.patch b/debian/patches/features/all/rt/rtmutex-Provide-rt_mutex_slowlock_locked.patch new file mode 100644 index 000000000..6c9b57dac --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-Provide-rt_mutex_slowlock_locked.patch @@ -0,0 +1,129 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 16:14:22 +0200 +Subject: rtmutex: Provide rt_mutex_slowlock_locked() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This is the inner-part of rt_mutex_slowlock(), required for rwsem-rt. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 67 ++++++++++++++++++++++------------------ + kernel/locking/rtmutex_common.h | 6 +++ + 2 files changed, 44 insertions(+), 29 deletions(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1244,35 +1244,16 @@ static void rt_mutex_handle_deadlock(int + } + } + +-/* +- * Slow path lock function: +- */ +-static int __sched +-rt_mutex_slowlock(struct rt_mutex *lock, int state, +- struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *waiter) + { +- struct rt_mutex_waiter waiter; +- unsigned long flags; +- int ret = 0; +- +- rt_mutex_init_waiter(&waiter); +- +- /* +- * Technically we could use raw_spin_[un]lock_irq() here, but this can +- * be called in early boot if the cmpxchg() fast path is disabled +- * (debug, no architecture support). In this case we will acquire the +- * rtmutex with lock->wait_lock held. But we cannot unconditionally +- * enable interrupts in that early boot case. So we need to use the +- * irqsave/restore variants. +- */ +- raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ int ret; + + /* Try to acquire the lock again: */ +- if (try_to_take_rt_mutex(lock, current, NULL)) { +- raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ if (try_to_take_rt_mutex(lock, current, NULL)) + return 0; +- } + + set_current_state(state); + +@@ -1280,16 +1261,16 @@ rt_mutex_slowlock(struct rt_mutex *lock, + if (unlikely(timeout)) + hrtimer_start_expires(&timeout->timer, HRTIMER_MODE_ABS); + +- ret = task_blocks_on_rt_mutex(lock, &waiter, current, chwalk); ++ ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); + + if (likely(!ret)) + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, &waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, waiter); + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); +- remove_waiter(lock, &waiter); +- rt_mutex_handle_deadlock(ret, chwalk, &waiter); ++ remove_waiter(lock, waiter); ++ rt_mutex_handle_deadlock(ret, chwalk, waiter); + } + + /* +@@ -1297,6 +1278,34 @@ rt_mutex_slowlock(struct rt_mutex *lock, + * unconditionally. We might have to fix that up. + */ + fixup_rt_mutex_waiters(lock); ++ return ret; ++} ++ ++/* ++ * Slow path lock function: ++ */ ++static int __sched ++rt_mutex_slowlock(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk) ++{ ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ int ret = 0; ++ ++ rt_mutex_init_waiter(&waiter); ++ ++ /* ++ * Technically we could use raw_spin_[un]lock_irq() here, but this can ++ * be called in early boot if the cmpxchg() fast path is disabled ++ * (debug, no architecture support). In this case we will acquire the ++ * rtmutex with lock->wait_lock held. But we cannot unconditionally ++ * enable interrupts in that early boot case. So we need to use the ++ * irqsave/restore variants. ++ */ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, &waiter); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -159,6 +159,12 @@ extern bool __rt_mutex_futex_unlock(stru + struct wake_q_head *wqh); + + extern void rt_mutex_postunlock(struct wake_q_head *wake_q); ++/* RW semaphore special interface */ ++ ++int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, ++ struct hrtimer_sleeper *timeout, ++ enum rtmutex_chainwalk chwalk, ++ struct rt_mutex_waiter *waiter); + + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" diff --git a/debian/patches/features/all/rt/rtmutex-add-mutex-implementation-based-on-rtmutex.patch b/debian/patches/features/all/rt/rtmutex-add-mutex-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..73d88b4bb --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-mutex-implementation-based-on-rtmutex.patch @@ -0,0 +1,373 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 17:17:03 +0200 +Subject: rtmutex: add mutex implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/mutex_rt.h | 130 ++++++++++++++++++++++++++ + kernel/locking/mutex-rt.c | 223 ++++++++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 353 insertions(+) + create mode 100644 include/linux/mutex_rt.h + create mode 100644 kernel/locking/mutex-rt.c + +--- /dev/null ++++ b/include/linux/mutex_rt.h +@@ -0,0 +1,130 @@ ++#ifndef __LINUX_MUTEX_RT_H ++#define __LINUX_MUTEX_RT_H ++ ++#ifndef __LINUX_MUTEX_H ++#error "Please include mutex.h" ++#endif ++ ++#include ++ ++/* FIXME: Just for __lockfunc */ ++#include ++ ++struct mutex { ++ struct rt_mutex lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __MUTEX_INITIALIZER(mutexname) \ ++ { \ ++ .lock = __RT_MUTEX_INITIALIZER(mutexname.lock) \ ++ __DEP_MAP_MUTEX_INITIALIZER(mutexname) \ ++ } ++ ++#define DEFINE_MUTEX(mutexname) \ ++ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) ++ ++extern void __mutex_do_init(struct mutex *lock, const char *name, struct lock_class_key *key); ++extern void __lockfunc _mutex_lock(struct mutex *lock); ++extern void __lockfunc _mutex_lock_io(struct mutex *lock); ++extern void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_interruptible(struct mutex *lock); ++extern int __lockfunc _mutex_lock_killable(struct mutex *lock); ++extern void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass); ++extern void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock); ++extern int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass); ++extern int __lockfunc _mutex_trylock(struct mutex *lock); ++extern void __lockfunc _mutex_unlock(struct mutex *lock); ++ ++#define mutex_is_locked(l) rt_mutex_is_locked(&(l)->lock) ++#define mutex_lock(l) _mutex_lock(l) ++#define mutex_lock_interruptible(l) _mutex_lock_interruptible(l) ++#define mutex_lock_killable(l) _mutex_lock_killable(l) ++#define mutex_trylock(l) _mutex_trylock(l) ++#define mutex_unlock(l) _mutex_unlock(l) ++#define mutex_lock_io(l) _mutex_lock_io(l); ++ ++#define __mutex_owner(l) ((l)->lock.owner) ++ ++#ifdef CONFIG_DEBUG_MUTEXES ++#define mutex_destroy(l) rt_mutex_destroy(&(l)->lock) ++#else ++static inline void mutex_destroy(struct mutex *lock) {} ++#endif ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define mutex_lock_nested(l, s) _mutex_lock_nested(l, s) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible_nested(l, s) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable_nested(l, s) ++# define mutex_lock_io_nested(l, s) _mutex_lock_io_nested(l, s) ++ ++# define mutex_lock_nest_lock(lock, nest_lock) \ ++do { \ ++ typecheck(struct lockdep_map *, &(nest_lock)->dep_map); \ ++ _mutex_lock_nest_lock(lock, &(nest_lock)->dep_map); \ ++} while (0) ++ ++#else ++# define mutex_lock_nested(l, s) _mutex_lock(l) ++# define mutex_lock_interruptible_nested(l, s) \ ++ _mutex_lock_interruptible(l) ++# define mutex_lock_killable_nested(l, s) \ ++ _mutex_lock_killable(l) ++# define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock) ++# define mutex_lock_io_nested(l, s) _mutex_lock_io(l) ++#endif ++ ++# define mutex_init(mutex) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), #mutex, &__key); \ ++} while (0) ++ ++# define __mutex_init(mutex, name, key) \ ++do { \ ++ rt_mutex_init(&(mutex)->lock); \ ++ __mutex_do_init((mutex), name, key); \ ++} while (0) ++ ++/** ++ * These values are chosen such that FAIL and SUCCESS match the ++ * values of the regular mutex_trylock(). ++ */ ++enum mutex_trylock_recursive_enum { ++ MUTEX_TRYLOCK_FAILED = 0, ++ MUTEX_TRYLOCK_SUCCESS = 1, ++ MUTEX_TRYLOCK_RECURSIVE, ++}; ++/** ++ * mutex_trylock_recursive - trylock variant that allows recursive locking ++ * @lock: mutex to be locked ++ * ++ * This function should not be used, _ever_. It is purely for hysterical GEM ++ * raisins, and once those are gone this will be removed. ++ * ++ * Returns: ++ * MUTEX_TRYLOCK_FAILED - trylock failed, ++ * MUTEX_TRYLOCK_SUCCESS - lock acquired, ++ * MUTEX_TRYLOCK_RECURSIVE - we already owned the lock. ++ */ ++int __rt_mutex_owner_current(struct rt_mutex *lock); ++ ++static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum ++mutex_trylock_recursive(struct mutex *lock) ++{ ++ if (unlikely(__rt_mutex_owner_current(&lock->lock))) ++ return MUTEX_TRYLOCK_RECURSIVE; ++ ++ return mutex_trylock(lock); ++} ++ ++extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock); ++ ++#endif +--- /dev/null ++++ b/kernel/locking/mutex-rt.c +@@ -0,0 +1,223 @@ ++/* ++ * kernel/rt.c ++ * ++ * Real-Time Preemption Support ++ * ++ * started by Ingo Molnar: ++ * ++ * Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * ++ * historic credit for proving that Linux spinlocks can be implemented via ++ * RT-aware mutexes goes to many people: The Pmutex project (Dirk Grambow ++ * and others) who prototyped it on 2.4 and did lots of comparative ++ * research and analysis; TimeSys, for proving that you can implement a ++ * fully preemptible kernel via the use of IRQ threading and mutexes; ++ * Bill Huey for persuasively arguing on lkml that the mutex model is the ++ * right one; and to MontaVista, who ported pmutexes to 2.6. ++ * ++ * This code is a from-scratch implementation and is not based on pmutexes, ++ * but the idea of converting spinlocks to mutexes is used here too. ++ * ++ * lock debugging, locking tree, deadlock detection: ++ * ++ * Copyright (C) 2004, LynuxWorks, Inc., Igor Manyilov, Bill Huey ++ * Released under the General Public License (GPL). ++ * ++ * Includes portions of the generic R/W semaphore implementation from: ++ * ++ * Copyright (c) 2001 David Howells (dhowells@redhat.com). ++ * - Derived partially from idea by Andrea Arcangeli ++ * - Derived also from comments by Linus ++ * ++ * Pending ownership of locks and ownership stealing: ++ * ++ * Copyright (C) 2005, Kihon Technologies Inc., Steven Rostedt ++ * ++ * (also by Steven Rostedt) ++ * - Converted single pi_lock to individual task locks. ++ * ++ * By Esben Nielsen: ++ * Doing priority inheritance with help of the scheduler. ++ * ++ * Copyright (C) 2006, Timesys Corp., Thomas Gleixner ++ * - major rework based on Esben Nielsens initial patch ++ * - replaced thread_info references by task_struct refs ++ * - removed task->pending_owner dependency ++ * - BKL drop/reacquire for semaphore style locks to avoid deadlocks ++ * in the scheduler return path as discussed with Steven Rostedt ++ * ++ * Copyright (C) 2006, Kihon Technologies Inc. ++ * Steven Rostedt ++ * - debugged and patched Thomas Gleixner's rework. ++ * - added back the cmpxchg to the rework. ++ * - turned atomic require back on for SMP. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#include "rtmutex_common.h" ++ ++/* ++ * struct mutex functions ++ */ ++void __mutex_do_init(struct mutex *mutex, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)mutex, sizeof(*mutex)); ++ lockdep_init_map(&mutex->dep_map, name, key, 0); ++#endif ++ mutex->lock.save_state = 0; ++} ++EXPORT_SYMBOL(__mutex_do_init); ++ ++void __lockfunc _mutex_lock(struct mutex *lock) ++{ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock); ++ ++void __lockfunc _mutex_lock_io(struct mutex *lock) ++{ ++ int token; ++ ++ token = io_schedule_prepare(); ++ _mutex_lock(lock); ++ io_schedule_finish(token); ++} ++EXPORT_SYMBOL_GPL(_mutex_lock_io); ++ ++int __lockfunc _mutex_lock_interruptible(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible); ++ ++int __lockfunc _mutex_lock_killable(struct mutex *lock) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable); ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc _mutex_lock_nested(struct mutex *lock, int subclass) ++{ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock_nested); ++ ++void __lockfunc _mutex_lock_io_nested(struct mutex *lock, int subclass) ++{ ++ int token; ++ ++ token = io_schedule_prepare(); ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++ ++ io_schedule_finish(token); ++} ++EXPORT_SYMBOL_GPL(_mutex_lock_io_nested); ++ ++void __lockfunc _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest) ++{ ++ mutex_acquire_nest(&lock->dep_map, 0, 0, nest, _RET_IP_); ++ __rt_mutex_lock_state(&lock->lock, TASK_UNINTERRUPTIBLE); ++} ++EXPORT_SYMBOL(_mutex_lock_nest_lock); ++ ++int __lockfunc _mutex_lock_interruptible_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire_nest(&lock->dep_map, subclass, 0, NULL, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_INTERRUPTIBLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_interruptible_nested); ++ ++int __lockfunc _mutex_lock_killable_nested(struct mutex *lock, int subclass) ++{ ++ int ret; ++ ++ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ ret = __rt_mutex_lock_state(&lock->lock, TASK_KILLABLE); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_lock_killable_nested); ++#endif ++ ++int __lockfunc _mutex_trylock(struct mutex *lock) ++{ ++ int ret = __rt_mutex_trylock(&lock->lock); ++ ++ if (ret) ++ mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ ++ return ret; ++} ++EXPORT_SYMBOL(_mutex_trylock); ++ ++void __lockfunc _mutex_unlock(struct mutex *lock) ++{ ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ __rt_mutex_unlock(&lock->lock); ++} ++EXPORT_SYMBOL(_mutex_unlock); ++ ++/** ++ * atomic_dec_and_mutex_lock - return holding mutex if we dec to 0 ++ * @cnt: the atomic which we are to dec ++ * @lock: the mutex to return holding if we dec to 0 ++ * ++ * return true and hold lock if we dec to 0, return false otherwise ++ */ ++int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock) ++{ ++ /* dec if we can't possibly hit 0 */ ++ if (atomic_add_unless(cnt, -1, 1)) ++ return 0; ++ /* we might hit 0, so take the lock */ ++ mutex_lock(lock); ++ if (!atomic_dec_and_test(cnt)) { ++ /* when we actually did the dec, we didn't hit 0 */ ++ mutex_unlock(lock); ++ return 0; ++ } ++ /* we hit 0, and we hold the lock */ ++ return 1; ++} ++EXPORT_SYMBOL(atomic_dec_and_mutex_lock); diff --git a/debian/patches/features/all/rt/rtmutex-add-rwlock-implementation-based-on-rtmutex.patch b/debian/patches/features/all/rt/rtmutex-add-rwlock-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..23d0a9d42 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-rwlock-implementation-based-on-rtmutex.patch @@ -0,0 +1,569 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 17:18:06 +0200 +Subject: rtmutex: add rwlock implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The implementation is bias-based, similar to the rwsem implementation. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/rwlock_rt.h | 119 ++++++++++++ + include/linux/rwlock_types_rt.h | 55 +++++ + kernel/locking/rwlock-rt.c | 368 ++++++++++++++++++++++++++++++++++++++++ + 3 files changed, 542 insertions(+) + create mode 100644 include/linux/rwlock_rt.h + create mode 100644 include/linux/rwlock_types_rt.h + create mode 100644 kernel/locking/rwlock-rt.c + +--- /dev/null ++++ b/include/linux/rwlock_rt.h +@@ -0,0 +1,119 @@ ++#ifndef __LINUX_RWLOCK_RT_H ++#define __LINUX_RWLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++extern void __lockfunc rt_write_lock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_trylock(rwlock_t *rwlock); ++extern int __lockfunc rt_read_trylock(rwlock_t *rwlock); ++extern void __lockfunc rt_write_unlock(rwlock_t *rwlock); ++extern void __lockfunc rt_read_unlock(rwlock_t *rwlock); ++extern int __lockfunc rt_read_can_lock(rwlock_t *rwlock); ++extern int __lockfunc rt_write_can_lock(rwlock_t *rwlock); ++extern void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key); ++ ++#define read_can_lock(rwlock) rt_read_can_lock(rwlock) ++#define write_can_lock(rwlock) rt_write_can_lock(rwlock) ++ ++#define read_trylock(lock) __cond_lock(lock, rt_read_trylock(lock)) ++#define write_trylock(lock) __cond_lock(lock, rt_write_trylock(lock)) ++ ++static inline int __write_trylock_rt_irqsave(rwlock_t *lock, unsigned long *flags) ++{ ++ /* XXX ARCH_IRQ_ENABLED */ ++ *flags = 0; ++ return rt_write_trylock(lock); ++} ++ ++#define write_trylock_irqsave(lock, flags) \ ++ __cond_lock(lock, __write_trylock_rt_irqsave(lock, &(flags))) ++ ++#define read_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ rt_read_lock(lock); \ ++ flags = 0; \ ++ } while (0) ++ ++#define write_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ rt_write_lock(lock); \ ++ flags = 0; \ ++ } while (0) ++ ++#define read_lock(lock) rt_read_lock(lock) ++ ++#define read_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_read_lock(lock); \ ++ } while (0) ++ ++#define read_lock_irq(lock) read_lock(lock) ++ ++#define write_lock(lock) rt_write_lock(lock) ++ ++#define write_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_write_lock(lock); \ ++ } while (0) ++ ++#define write_lock_irq(lock) write_lock(lock) ++ ++#define read_unlock(lock) rt_read_unlock(lock) ++ ++#define read_unlock_bh(lock) \ ++ do { \ ++ rt_read_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define read_unlock_irq(lock) read_unlock(lock) ++ ++#define write_unlock(lock) rt_write_unlock(lock) ++ ++#define write_unlock_bh(lock) \ ++ do { \ ++ rt_write_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define write_unlock_irq(lock) write_unlock(lock) ++ ++#define read_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_read_unlock(lock); \ ++ } while (0) ++ ++#define write_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ rt_write_unlock(lock); \ ++ } while (0) ++ ++#define rwlock_init(rwl) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rt_rwlock_init(rwl, #rwl, &__key); \ ++} while (0) ++ ++/* ++ * Internal functions made global for CPU pinning ++ */ ++void __read_rt_lock(struct rt_rw_lock *lock); ++int __read_rt_trylock(struct rt_rw_lock *lock); ++void __write_rt_lock(struct rt_rw_lock *lock); ++int __write_rt_trylock(struct rt_rw_lock *lock); ++void __read_rt_unlock(struct rt_rw_lock *lock); ++void __write_rt_unlock(struct rt_rw_lock *lock); ++ ++#endif +--- /dev/null ++++ b/include/linux/rwlock_types_rt.h +@@ -0,0 +1,55 @@ ++#ifndef __LINUX_RWLOCK_TYPES_RT_H ++#define __LINUX_RWLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define RW_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define RW_DEP_MAP_INIT(lockname) ++#endif ++ ++typedef struct rt_rw_lock rwlock_t; ++ ++#define __RW_LOCK_UNLOCKED(name) __RWLOCK_RT_INITIALIZER(name) ++ ++#define DEFINE_RWLOCK(name) \ ++ rwlock_t name = __RW_LOCK_UNLOCKED(name) ++ ++/* ++ * A reader biased implementation primarily for CPU pinning. ++ * ++ * Can be selected as general replacement for the single reader RT rwlock ++ * variant ++ */ ++struct rt_rw_lock { ++ struct rt_mutex rtmutex; ++ atomic_t readers; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define READER_BIAS (1U << 31) ++#define WRITER_BIAS (1U << 30) ++ ++#define __RWLOCK_RT_INITIALIZER(name) \ ++{ \ ++ .readers = ATOMIC_INIT(READER_BIAS), \ ++ .rtmutex = __RT_MUTEX_INITIALIZER_SAVE_STATE(name.rtmutex), \ ++ RW_DEP_MAP_INIT(name) \ ++} ++ ++void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, ++ struct lock_class_key *key); ++ ++#define rwlock_biased_rt_init(rwlock) \ ++ do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __rwlock_biased_rt_init((rwlock), #rwlock, &__key); \ ++ } while (0) ++ ++#endif +--- /dev/null ++++ b/kernel/locking/rwlock-rt.c +@@ -0,0 +1,368 @@ ++/* ++ */ ++#include ++#include ++ ++#include "rtmutex_common.h" ++#include ++ ++/* ++ * RT-specific reader/writer locks ++ * ++ * write_lock() ++ * 1) Lock lock->rtmutex ++ * 2) Remove the reader BIAS to force readers into the slow path ++ * 3) Wait until all readers have left the critical region ++ * 4) Mark it write locked ++ * ++ * write_unlock() ++ * 1) Remove the write locked marker ++ * 2) Set the reader BIAS so readers can use the fast path again ++ * 3) Unlock lock->rtmutex to release blocked readers ++ * ++ * read_lock() ++ * 1) Try fast path acquisition (reader BIAS is set) ++ * 2) Take lock->rtmutex.wait_lock which protects the writelocked flag ++ * 3) If !writelocked, acquire it for read ++ * 4) If writelocked, block on lock->rtmutex ++ * 5) unlock lock->rtmutex, goto 1) ++ * ++ * read_unlock() ++ * 1) Try fast path release (reader count != 1) ++ * 2) Wake the writer waiting in write_lock()#3 ++ * ++ * read_lock()#3 has the consequence, that rw locks on RT are not writer ++ * fair, but writers, which should be avoided in RT tasks (think tasklist ++ * lock), are subject to the rtmutex priority/DL inheritance mechanism. ++ * ++ * It's possible to make the rw locks writer fair by keeping a list of ++ * active readers. A blocked writer would force all newly incoming readers ++ * to block on the rtmutex, but the rtmutex would have to be proxy locked ++ * for one reader after the other. We can't use multi-reader inheritance ++ * because there is no way to support that with ++ * SCHED_DEADLINE. Implementing the one by one reader boosting/handover ++ * mechanism is a major surgery for a very dubious value. ++ * ++ * The risk of writer starvation is there, but the pathological use cases ++ * which trigger it are not necessarily the typical RT workloads. ++ */ ++ ++void __rwlock_biased_rt_init(struct rt_rw_lock *lock, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held semaphore: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++ atomic_set(&lock->readers, READER_BIAS); ++ rt_mutex_init(&lock->rtmutex); ++ lock->rtmutex.save_state = 1; ++} ++ ++int __read_rt_trylock(struct rt_rw_lock *lock) ++{ ++ int r, old; ++ ++ /* ++ * Increment reader count, if lock->readers < 0, i.e. READER_BIAS is ++ * set. ++ */ ++ for (r = atomic_read(&lock->readers); r < 0;) { ++ old = atomic_cmpxchg(&lock->readers, r, r + 1); ++ if (likely(old == r)) ++ return 1; ++ r = old; ++ } ++ return 0; ++} ++ ++void __sched __read_rt_lock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ ++ if (__read_rt_trylock(lock)) ++ return; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* ++ * Allow readers as long as the writer has not completely ++ * acquired the semaphore for write. ++ */ ++ if (atomic_read(&lock->readers) != WRITER_BIAS) { ++ atomic_inc(&lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return; ++ } ++ ++ /* ++ * Call into the slow lock path with the rtmutex->wait_lock ++ * held, so this can't result in the following race: ++ * ++ * Reader1 Reader2 Writer ++ * read_lock() ++ * write_lock() ++ * rtmutex_lock(m) ++ * swait() ++ * read_lock() ++ * unlock(m->wait_lock) ++ * read_unlock() ++ * swake() ++ * lock(m->wait_lock) ++ * lock->writelocked=true ++ * unlock(m->wait_lock) ++ * ++ * write_unlock() ++ * lock->writelocked=false ++ * rtmutex_unlock(m) ++ * read_lock() ++ * write_lock() ++ * rtmutex_lock(m) ++ * swait() ++ * rtmutex_lock(m) ++ * ++ * That would put Reader1 behind the writer waiting on ++ * Reader2 to call read_unlock() which might be unbound. ++ */ ++ rt_mutex_init_waiter(&waiter, false); ++ rt_spin_lock_slowlock_locked(m, &waiter, flags); ++ /* ++ * The slowlock() above is guaranteed to return with the rtmutex is ++ * now held, so there can't be a writer active. Increment the reader ++ * count and immediately drop the rtmutex again. ++ */ ++ atomic_inc(&lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ rt_spin_lock_slowunlock(m); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++void __read_rt_unlock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct task_struct *tsk; ++ ++ /* ++ * sem->readers can only hit 0 when a writer is waiting for the ++ * active readers to leave the critical region. ++ */ ++ if (!atomic_dec_and_test(&lock->readers)) ++ return; ++ ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Wake the writer, i.e. the rtmutex owner. It might release the ++ * rtmutex concurrently in the fast path, but to clean up the rw ++ * lock it needs to acquire m->wait_lock. The worst case which can ++ * happen is a spurious wakeup. ++ */ ++ tsk = rt_mutex_owner(m); ++ if (tsk) ++ wake_up_process(tsk); ++ ++ raw_spin_unlock_irq(&m->wait_lock); ++} ++ ++static void __write_unlock_common(struct rt_rw_lock *lock, int bias, ++ unsigned long flags) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ ++ atomic_add(READER_BIAS - bias, &lock->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ rt_spin_lock_slowunlock(m); ++} ++ ++void __sched __write_rt_lock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ struct task_struct *self = current; ++ unsigned long flags; ++ ++ /* Take the rtmutex as a first step */ ++ __rt_spin_lock(m); ++ ++ /* Force readers into slow path */ ++ atomic_sub(READER_BIAS, &lock->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ ++ for (;;) { ++ /* Have all readers left the critical region? */ ++ if (!atomic_read(&lock->readers)) { ++ atomic_set(&lock->readers, WRITER_BIAS); ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock(&self->pi_lock); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return; ++ } ++ ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ ++ if (atomic_read(&lock->readers) != 0) ++ schedule(); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ } ++} ++ ++int __write_rt_trylock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ unsigned long flags; ++ ++ if (!__rt_mutex_trylock(m)) ++ return 0; ++ ++ atomic_sub(READER_BIAS, &lock->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ if (!atomic_read(&lock->readers)) { ++ atomic_set(&lock->readers, WRITER_BIAS); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 1; ++ } ++ __write_unlock_common(lock, 0, flags); ++ return 0; ++} ++ ++void __write_rt_unlock(struct rt_rw_lock *lock) ++{ ++ struct rt_mutex *m = &lock->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ __write_unlock_common(lock, WRITER_BIAS, flags); ++} ++ ++/* Map the reader biased implementation */ ++static inline int do_read_rt_trylock(rwlock_t *rwlock) ++{ ++ return __read_rt_trylock(rwlock); ++} ++ ++static inline int do_write_rt_trylock(rwlock_t *rwlock) ++{ ++ return __write_rt_trylock(rwlock); ++} ++ ++static inline void do_read_rt_lock(rwlock_t *rwlock) ++{ ++ __read_rt_lock(rwlock); ++} ++ ++static inline void do_write_rt_lock(rwlock_t *rwlock) ++{ ++ __write_rt_lock(rwlock); ++} ++ ++static inline void do_read_rt_unlock(rwlock_t *rwlock) ++{ ++ __read_rt_unlock(rwlock); ++} ++ ++static inline void do_write_rt_unlock(rwlock_t *rwlock) ++{ ++ __write_rt_unlock(rwlock); ++} ++ ++static inline void do_rwlock_rt_init(rwlock_t *rwlock, const char *name, ++ struct lock_class_key *key) ++{ ++ __rwlock_biased_rt_init(rwlock, name, key); ++} ++ ++int __lockfunc rt_read_can_lock(rwlock_t *rwlock) ++{ ++ return atomic_read(&rwlock->readers) < 0; ++} ++ ++int __lockfunc rt_write_can_lock(rwlock_t *rwlock) ++{ ++ return atomic_read(&rwlock->readers) == READER_BIAS; ++} ++ ++/* ++ * The common functions which get wrapped into the rwlock API. ++ */ ++int __lockfunc rt_read_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = do_read_rt_trylock(rwlock); ++ if (ret) ++ rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_read_trylock); ++ ++int __lockfunc rt_write_trylock(rwlock_t *rwlock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = do_write_rt_trylock(rwlock); ++ if (ret) ++ rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_write_trylock); ++ ++void __lockfunc rt_read_lock(rwlock_t *rwlock) ++{ ++ migrate_disable(); ++ rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); ++ do_read_rt_lock(rwlock); ++} ++EXPORT_SYMBOL(rt_read_lock); ++ ++void __lockfunc rt_write_lock(rwlock_t *rwlock) ++{ ++ migrate_disable(); ++ rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); ++ do_write_rt_lock(rwlock); ++} ++EXPORT_SYMBOL(rt_write_lock); ++ ++void __lockfunc rt_read_unlock(rwlock_t *rwlock) ++{ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ do_read_rt_unlock(rwlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_read_unlock); ++ ++void __lockfunc rt_write_unlock(rwlock_t *rwlock) ++{ ++ rwlock_release(&rwlock->dep_map, 1, _RET_IP_); ++ do_write_rt_unlock(rwlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_write_unlock); ++ ++void __rt_rwlock_init(rwlock_t *rwlock, char *name, struct lock_class_key *key) ++{ ++ do_rwlock_rt_init(rwlock, name, key); ++} ++EXPORT_SYMBOL(__rt_rwlock_init); diff --git a/debian/patches/features/all/rt/rtmutex-add-rwsem-implementation-based-on-rtmutex.patch b/debian/patches/features/all/rt/rtmutex-add-rwsem-implementation-based-on-rtmutex.patch new file mode 100644 index 000000000..4184e5308 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-rwsem-implementation-based-on-rtmutex.patch @@ -0,0 +1,417 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 17:28:34 +0200 +Subject: rtmutex: add rwsem implementation based on rtmutex +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The RT specific R/W semaphore implementation restricts the number of readers +to one because a writer cannot block on multiple readers and inherit its +priority or budget. + +The single reader restricting is painful in various ways: + + - Performance bottleneck for multi-threaded applications in the page fault + path (mmap sem) + + - Progress blocker for drivers which are carefully crafted to avoid the + potential reader/writer deadlock in mainline. + +The analysis of the writer code pathes shows, that properly written RT tasks +should not take them. Syscalls like mmap(), file access which take mmap sem +write locked have unbound latencies which are completely unrelated to mmap +sem. Other R/W sem users like graphics drivers are not suitable for RT tasks +either. + +So there is little risk to hurt RT tasks when the RT rwsem implementation is +changed in the following way: + + - Allow concurrent readers + + - Make writers block until the last reader left the critical section. This + blocking is not subject to priority/budget inheritance. + + - Readers blocked on a writer inherit their priority/budget in the normal + way. + +There is a drawback with this scheme. R/W semaphores become writer unfair +though the applications which have triggered writer starvation (mostly on +mmap_sem) in the past are not really the typical workloads running on a RT +system. So while it's unlikely to hit writer starvation, it's possible. If +there are unexpected workloads on RT systems triggering it, we need to rethink +the approach. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/rwsem_rt.h | 68 ++++++++++ + kernel/locking/rwsem-rt.c | 293 ++++++++++++++++++++++++++++++++++++++++++++++ + 2 files changed, 361 insertions(+) + create mode 100644 include/linux/rwsem_rt.h + create mode 100644 kernel/locking/rwsem-rt.c + +--- /dev/null ++++ b/include/linux/rwsem_rt.h +@@ -0,0 +1,68 @@ ++#ifndef _LINUX_RWSEM_RT_H ++#define _LINUX_RWSEM_RT_H ++ ++#ifndef _LINUX_RWSEM_H ++#error "Include rwsem.h" ++#endif ++ ++#include ++#include ++ ++#define READER_BIAS (1U << 31) ++#define WRITER_BIAS (1U << 30) ++ ++struct rw_semaphore { ++ atomic_t readers; ++ struct rt_mutex rtmutex; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++}; ++ ++#define __RWSEM_INITIALIZER(name) \ ++{ \ ++ .readers = ATOMIC_INIT(READER_BIAS), \ ++ .rtmutex = __RT_MUTEX_INITIALIZER(name.rtmutex), \ ++ RW_DEP_MAP_INIT(name) \ ++} ++ ++#define DECLARE_RWSEM(lockname) \ ++ struct rw_semaphore lockname = __RWSEM_INITIALIZER(lockname) ++ ++extern void __rwsem_init(struct rw_semaphore *rwsem, const char *name, ++ struct lock_class_key *key); ++ ++#define __init_rwsem(sem, name, key) \ ++do { \ ++ rt_mutex_init(&(sem)->rtmutex); \ ++ __rwsem_init((sem), (name), (key)); \ ++} while (0) ++ ++#define init_rwsem(sem) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ __init_rwsem((sem), #sem, &__key); \ ++} while (0) ++ ++static inline int rwsem_is_locked(struct rw_semaphore *sem) ++{ ++ return atomic_read(&sem->readers) != READER_BIAS; ++} ++ ++static inline int rwsem_is_contended(struct rw_semaphore *sem) ++{ ++ return atomic_read(&sem->readers) > 0; ++} ++ ++extern void __down_read(struct rw_semaphore *sem); ++extern int __down_read_killable(struct rw_semaphore *sem); ++extern int __down_read_trylock(struct rw_semaphore *sem); ++extern void __down_write(struct rw_semaphore *sem); ++extern int __must_check __down_write_killable(struct rw_semaphore *sem); ++extern int __down_write_trylock(struct rw_semaphore *sem); ++extern void __up_read(struct rw_semaphore *sem); ++extern void __up_write(struct rw_semaphore *sem); ++extern void __downgrade_write(struct rw_semaphore *sem); ++ ++#endif +--- /dev/null ++++ b/kernel/locking/rwsem-rt.c +@@ -0,0 +1,293 @@ ++/* ++ */ ++#include ++#include ++#include ++#include ++ ++#include "rtmutex_common.h" ++ ++/* ++ * RT-specific reader/writer semaphores ++ * ++ * down_write() ++ * 1) Lock sem->rtmutex ++ * 2) Remove the reader BIAS to force readers into the slow path ++ * 3) Wait until all readers have left the critical region ++ * 4) Mark it write locked ++ * ++ * up_write() ++ * 1) Remove the write locked marker ++ * 2) Set the reader BIAS so readers can use the fast path again ++ * 3) Unlock sem->rtmutex to release blocked readers ++ * ++ * down_read() ++ * 1) Try fast path acquisition (reader BIAS is set) ++ * 2) Take sem->rtmutex.wait_lock which protects the writelocked flag ++ * 3) If !writelocked, acquire it for read ++ * 4) If writelocked, block on sem->rtmutex ++ * 5) unlock sem->rtmutex, goto 1) ++ * ++ * up_read() ++ * 1) Try fast path release (reader count != 1) ++ * 2) Wake the writer waiting in down_write()#3 ++ * ++ * down_read()#3 has the consequence, that rw semaphores on RT are not writer ++ * fair, but writers, which should be avoided in RT tasks (think mmap_sem), ++ * are subject to the rtmutex priority/DL inheritance mechanism. ++ * ++ * It's possible to make the rw semaphores writer fair by keeping a list of ++ * active readers. A blocked writer would force all newly incoming readers to ++ * block on the rtmutex, but the rtmutex would have to be proxy locked for one ++ * reader after the other. We can't use multi-reader inheritance because there ++ * is no way to support that with SCHED_DEADLINE. Implementing the one by one ++ * reader boosting/handover mechanism is a major surgery for a very dubious ++ * value. ++ * ++ * The risk of writer starvation is there, but the pathological use cases ++ * which trigger it are not necessarily the typical RT workloads. ++ */ ++ ++void __rwsem_init(struct rw_semaphore *sem, const char *name, ++ struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held semaphore: ++ */ ++ debug_check_no_locks_freed((void *)sem, sizeof(*sem)); ++ lockdep_init_map(&sem->dep_map, name, key, 0); ++#endif ++ atomic_set(&sem->readers, READER_BIAS); ++} ++EXPORT_SYMBOL(__rwsem_init); ++ ++int __down_read_trylock(struct rw_semaphore *sem) ++{ ++ int r, old; ++ ++ /* ++ * Increment reader count, if sem->readers < 0, i.e. READER_BIAS is ++ * set. ++ */ ++ for (r = atomic_read(&sem->readers); r < 0;) { ++ old = atomic_cmpxchg(&sem->readers, r, r + 1); ++ if (likely(old == r)) ++ return 1; ++ r = old; ++ } ++ return 0; ++} ++ ++static int __sched __down_read_common(struct rw_semaphore *sem, int state) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ struct rt_mutex_waiter waiter; ++ int ret; ++ ++ if (__down_read_trylock(sem)) ++ return 0; ++ ++ might_sleep(); ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Allow readers as long as the writer has not completely ++ * acquired the semaphore for write. ++ */ ++ if (atomic_read(&sem->readers) != WRITER_BIAS) { ++ atomic_inc(&sem->readers); ++ raw_spin_unlock_irq(&m->wait_lock); ++ return 0; ++ } ++ ++ /* ++ * Call into the slow lock path with the rtmutex->wait_lock ++ * held, so this can't result in the following race: ++ * ++ * Reader1 Reader2 Writer ++ * down_read() ++ * down_write() ++ * rtmutex_lock(m) ++ * swait() ++ * down_read() ++ * unlock(m->wait_lock) ++ * up_read() ++ * swake() ++ * lock(m->wait_lock) ++ * sem->writelocked=true ++ * unlock(m->wait_lock) ++ * ++ * up_write() ++ * sem->writelocked=false ++ * rtmutex_unlock(m) ++ * down_read() ++ * down_write() ++ * rtmutex_lock(m) ++ * swait() ++ * rtmutex_lock(m) ++ * ++ * That would put Reader1 behind the writer waiting on ++ * Reader2 to call up_read() which might be unbound. ++ */ ++ rt_mutex_init_waiter(&waiter, false); ++ ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, ++ &waiter); ++ /* ++ * The slowlock() above is guaranteed to return with the rtmutex (for ++ * ret = 0) is now held, so there can't be a writer active. Increment ++ * the reader count and immediately drop the rtmutex again. ++ * For ret != 0 we don't hold the rtmutex and need unlock the wait_lock. ++ * We don't own the lock then. ++ */ ++ if (!ret) ++ atomic_inc(&sem->readers); ++ raw_spin_unlock_irq(&m->wait_lock); ++ if (!ret) ++ __rt_mutex_unlock(m); ++ ++ debug_rt_mutex_free_waiter(&waiter); ++ return ret; ++} ++ ++void __down_read(struct rw_semaphore *sem) ++{ ++ int ret; ++ ++ ret = __down_read_common(sem, TASK_UNINTERRUPTIBLE); ++ WARN_ON_ONCE(ret); ++} ++ ++int __down_read_killable(struct rw_semaphore *sem) ++{ ++ int ret; ++ ++ ret = __down_read_common(sem, TASK_KILLABLE); ++ if (likely(!ret)) ++ return ret; ++ WARN_ONCE(ret != -EINTR, "Unexpected state: %d\n", ret); ++ return -EINTR; ++} ++ ++void __up_read(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ struct task_struct *tsk; ++ ++ /* ++ * sem->readers can only hit 0 when a writer is waiting for the ++ * active readers to leave the critical region. ++ */ ++ if (!atomic_dec_and_test(&sem->readers)) ++ return; ++ ++ might_sleep(); ++ raw_spin_lock_irq(&m->wait_lock); ++ /* ++ * Wake the writer, i.e. the rtmutex owner. It might release the ++ * rtmutex concurrently in the fast path (due to a signal), but to ++ * clean up the rwsem it needs to acquire m->wait_lock. The worst ++ * case which can happen is a spurious wakeup. ++ */ ++ tsk = rt_mutex_owner(m); ++ if (tsk) ++ wake_up_process(tsk); ++ ++ raw_spin_unlock_irq(&m->wait_lock); ++} ++ ++static void __up_write_unlock(struct rw_semaphore *sem, int bias, ++ unsigned long flags) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ ++ atomic_add(READER_BIAS - bias, &sem->readers); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ __rt_mutex_unlock(m); ++} ++ ++static int __sched __down_write_common(struct rw_semaphore *sem, int state) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ /* Take the rtmutex as a first step */ ++ if (__rt_mutex_lock_state(m, state)) ++ return -EINTR; ++ ++ /* Force readers into slow path */ ++ atomic_sub(READER_BIAS, &sem->readers); ++ might_sleep(); ++ ++ set_current_state(state); ++ for (;;) { ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* Have all readers left the critical region? */ ++ if (!atomic_read(&sem->readers)) { ++ atomic_set(&sem->readers, WRITER_BIAS); ++ __set_current_state(TASK_RUNNING); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 0; ++ } ++ ++ if (signal_pending_state(state, current)) { ++ __set_current_state(TASK_RUNNING); ++ __up_write_unlock(sem, 0, flags); ++ return -EINTR; ++ } ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ ++ if (atomic_read(&sem->readers) != 0) { ++ schedule(); ++ set_current_state(state); ++ } ++ } ++} ++ ++void __sched __down_write(struct rw_semaphore *sem) ++{ ++ __down_write_common(sem, TASK_UNINTERRUPTIBLE); ++} ++ ++int __sched __down_write_killable(struct rw_semaphore *sem) ++{ ++ return __down_write_common(sem, TASK_KILLABLE); ++} ++ ++int __down_write_trylock(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ if (!__rt_mutex_trylock(m)) ++ return 0; ++ ++ atomic_sub(READER_BIAS, &sem->readers); ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ if (!atomic_read(&sem->readers)) { ++ atomic_set(&sem->readers, WRITER_BIAS); ++ raw_spin_unlock_irqrestore(&m->wait_lock, flags); ++ return 1; ++ } ++ __up_write_unlock(sem, 0, flags); ++ return 0; ++} ++ ++void __up_write(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ __up_write_unlock(sem, WRITER_BIAS, flags); ++} ++ ++void __downgrade_write(struct rw_semaphore *sem) ++{ ++ struct rt_mutex *m = &sem->rtmutex; ++ unsigned long flags; ++ ++ raw_spin_lock_irqsave(&m->wait_lock, flags); ++ /* Release it and account current as reader */ ++ __up_write_unlock(sem, WRITER_BIAS - 1, flags); ++} diff --git a/debian/patches/features/all/rt/rtmutex-add-sleeping-lock-implementation.patch b/debian/patches/features/all/rt/rtmutex-add-sleeping-lock-implementation.patch new file mode 100644 index 000000000..583ba3677 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-sleeping-lock-implementation.patch @@ -0,0 +1,1188 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 17:11:19 +0200 +Subject: rtmutex: add sleeping lock implementation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/kernel.h | 4 + include/linux/rtmutex.h | 21 + + include/linux/sched.h | 8 + include/linux/sched/wake_q.h | 27 ++ + include/linux/spinlock_rt.h | 156 +++++++++++++ + include/linux/spinlock_types_rt.h | 48 ++++ + kernel/fork.c | 1 + kernel/futex.c | 11 + kernel/locking/rtmutex.c | 436 ++++++++++++++++++++++++++++++++++---- + kernel/locking/rtmutex_common.h | 15 + + kernel/sched/core.c | 28 +- + 11 files changed, 696 insertions(+), 59 deletions(-) + create mode 100644 include/linux/spinlock_rt.h + create mode 100644 include/linux/spinlock_types_rt.h + +--- a/include/linux/kernel.h ++++ b/include/linux/kernel.h +@@ -226,6 +226,9 @@ extern int _cond_resched(void); + */ + # define might_sleep() \ + do { __might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) ++ ++# define might_sleep_no_state_check() \ ++ do { ___might_sleep(__FILE__, __LINE__, 0); might_resched(); } while (0) + # define sched_annotate_sleep() (current->task_state_change = 0) + #else + static inline void ___might_sleep(const char *file, int line, +@@ -233,6 +236,7 @@ extern int _cond_resched(void); + static inline void __might_sleep(const char *file, int line, + int preempt_offset) { } + # define might_sleep() do { might_resched(); } while (0) ++# define might_sleep_no_state_check() do { might_resched(); } while (0) + # define sched_annotate_sleep() do { } while (0) + #endif + +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -14,11 +14,15 @@ + #define __LINUX_RT_MUTEX_H + + #include +-#include + #include ++#include + + extern int max_lock_depth; /* for sysctl */ + ++#ifdef CONFIG_DEBUG_MUTEXES ++#include ++#endif ++ + /** + * The rt_mutex structure + * +@@ -31,8 +35,8 @@ struct rt_mutex { + raw_spinlock_t wait_lock; + struct rb_root_cached waiters; + struct task_struct *owner; +-#ifdef CONFIG_DEBUG_RT_MUTEXES + int save_state; ++#ifdef CONFIG_DEBUG_RT_MUTEXES + const char *name, *file; + int line; + void *magic; +@@ -82,16 +86,23 @@ do { \ + #define __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) + #endif + +-#define __RT_MUTEX_INITIALIZER(mutexname) \ +- { .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ ++#define __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(mutexname.wait_lock) \ + , .waiters = RB_ROOT_CACHED \ + , .owner = NULL \ + __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \ +- __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname)} ++ __DEP_MAP_RT_MUTEX_INITIALIZER(mutexname) ++ ++#define __RT_MUTEX_INITIALIZER(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) } + + #define DEFINE_RT_MUTEX(mutexname) \ + struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname) + ++#define __RT_MUTEX_INITIALIZER_SAVE_STATE(mutexname) \ ++ { __RT_MUTEX_INITIALIZER_PLAIN(mutexname) \ ++ , .save_state = 1 } ++ + /** + * rt_mutex_is_locked - is the mutex locked + * @lock: the mutex to be queried +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -134,6 +134,9 @@ struct task_group; + smp_store_mb(current->state, (state_value)); \ + } while (0) + ++#define __set_current_state_no_track(state_value) \ ++ current->state = (state_value); ++ + #define set_special_state(state_value) \ + do { \ + unsigned long flags; /* may shadow */ \ +@@ -143,6 +146,7 @@ struct task_group; + current->state = (state_value); \ + raw_spin_unlock_irqrestore(¤t->pi_lock, flags); \ + } while (0) ++ + #else + /* + * set_current_state() includes a barrier so that the write of current->state +@@ -187,6 +191,9 @@ struct task_group; + #define set_current_state(state_value) \ + smp_store_mb(current->state, (state_value)) + ++#define __set_current_state_no_track(state_value) \ ++ __set_current_state(state_value) ++ + /* + * set_special_state() should be used for those states when the blocking task + * can not use the regular condition based wait-loop. In that case we must +@@ -908,6 +915,7 @@ struct task_struct { + raw_spinlock_t pi_lock; + + struct wake_q_node wake_q; ++ struct wake_q_node wake_q_sleeper; + + #ifdef CONFIG_RT_MUTEXES + /* PI waiters blocked on a rt_mutex held by this task: */ +--- a/include/linux/sched/wake_q.h ++++ b/include/linux/sched/wake_q.h +@@ -47,8 +47,29 @@ static inline void wake_q_init(struct wa + head->lastp = &head->first; + } + +-extern void wake_q_add(struct wake_q_head *head, +- struct task_struct *task); +-extern void wake_up_q(struct wake_q_head *head); ++extern void __wake_q_add(struct wake_q_head *head, ++ struct task_struct *task, bool sleeper); ++static inline void wake_q_add(struct wake_q_head *head, ++ struct task_struct *task) ++{ ++ __wake_q_add(head, task, false); ++} ++ ++static inline void wake_q_add_sleeper(struct wake_q_head *head, ++ struct task_struct *task) ++{ ++ __wake_q_add(head, task, true); ++} ++ ++extern void __wake_up_q(struct wake_q_head *head, bool sleeper); ++static inline void wake_up_q(struct wake_q_head *head) ++{ ++ __wake_up_q(head, false); ++} ++ ++static inline void wake_up_q_sleeper(struct wake_q_head *head) ++{ ++ __wake_up_q(head, true); ++} + + #endif /* _LINUX_SCHED_WAKE_Q_H */ +--- /dev/null ++++ b/include/linux/spinlock_rt.h +@@ -0,0 +1,156 @@ ++#ifndef __LINUX_SPINLOCK_RT_H ++#define __LINUX_SPINLOCK_RT_H ++ ++#ifndef __LINUX_SPINLOCK_H ++#error Do not include directly. Use spinlock.h ++#endif ++ ++#include ++ ++extern void ++__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key); ++ ++#define spin_lock_init(slock) \ ++do { \ ++ static struct lock_class_key __key; \ ++ \ ++ rt_mutex_init(&(slock)->lock); \ ++ __rt_spin_lock_init(slock, #slock, &__key); \ ++} while (0) ++ ++extern void __lockfunc rt_spin_lock(spinlock_t *lock); ++extern unsigned long __lockfunc rt_spin_lock_trace_flags(spinlock_t *lock); ++extern void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass); ++extern void __lockfunc rt_spin_unlock(spinlock_t *lock); ++extern void __lockfunc rt_spin_unlock_wait(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags); ++extern int __lockfunc rt_spin_trylock_bh(spinlock_t *lock); ++extern int __lockfunc rt_spin_trylock(spinlock_t *lock); ++extern int atomic_dec_and_spin_lock(atomic_t *atomic, spinlock_t *lock); ++ ++/* ++ * lockdep-less calls, for derived types like rwlock: ++ * (for trylock they can use rt_mutex_trylock() directly. ++ * Migrate disable handling must be done at the call site. ++ */ ++extern void __lockfunc __rt_spin_lock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_trylock(struct rt_mutex *lock); ++extern void __lockfunc __rt_spin_unlock(struct rt_mutex *lock); ++ ++#define spin_lock(lock) rt_spin_lock(lock) ++ ++#define spin_lock_bh(lock) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock(lock); \ ++ } while (0) ++ ++#define spin_lock_irq(lock) spin_lock(lock) ++ ++#define spin_do_trylock(lock) __cond_lock(lock, rt_spin_trylock(lock)) ++ ++#define spin_trylock(lock) \ ++({ \ ++ int __locked; \ ++ __locked = spin_do_trylock(lock); \ ++ __locked; \ ++}) ++ ++#ifdef CONFIG_LOCKDEP ++# define spin_lock_nested(lock, subclass) \ ++ do { \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++#define spin_lock_bh_nested(lock, subclass) \ ++ do { \ ++ local_bh_disable(); \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ rt_spin_lock_nested(lock, subclass); \ ++ } while (0) ++#else ++# define spin_lock_nested(lock, subclass) spin_lock(lock) ++# define spin_lock_bh_nested(lock, subclass) spin_lock_bh(lock) ++ ++# define spin_lock_irqsave_nested(lock, flags, subclass) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++#endif ++ ++#define spin_lock_irqsave(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ flags = 0; \ ++ spin_lock(lock); \ ++ } while (0) ++ ++static inline unsigned long spin_lock_trace_flags(spinlock_t *lock) ++{ ++ unsigned long flags = 0; ++#ifdef CONFIG_TRACE_IRQFLAGS ++ flags = rt_spin_lock_trace_flags(lock); ++#else ++ spin_lock(lock); /* lock_local */ ++#endif ++ return flags; ++} ++ ++/* FIXME: we need rt_spin_lock_nest_lock */ ++#define spin_lock_nest_lock(lock, nest_lock) spin_lock_nested(lock, 0) ++ ++#define spin_unlock(lock) rt_spin_unlock(lock) ++ ++#define spin_unlock_bh(lock) \ ++ do { \ ++ rt_spin_unlock(lock); \ ++ local_bh_enable(); \ ++ } while (0) ++ ++#define spin_unlock_irq(lock) spin_unlock(lock) ++ ++#define spin_unlock_irqrestore(lock, flags) \ ++ do { \ ++ typecheck(unsigned long, flags); \ ++ (void) flags; \ ++ spin_unlock(lock); \ ++ } while (0) ++ ++#define spin_trylock_bh(lock) __cond_lock(lock, rt_spin_trylock_bh(lock)) ++#define spin_trylock_irq(lock) spin_trylock(lock) ++ ++#define spin_trylock_irqsave(lock, flags) \ ++ rt_spin_trylock_irqsave(lock, &(flags)) ++ ++#define spin_unlock_wait(lock) rt_spin_unlock_wait(lock) ++ ++#ifdef CONFIG_GENERIC_LOCKBREAK ++# define spin_is_contended(lock) ((lock)->break_lock) ++#else ++# define spin_is_contended(lock) (((void)(lock), 0)) ++#endif ++ ++static inline int spin_can_lock(spinlock_t *lock) ++{ ++ return !rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline int spin_is_locked(spinlock_t *lock) ++{ ++ return rt_mutex_is_locked(&lock->lock); ++} ++ ++static inline void assert_spin_locked(spinlock_t *lock) ++{ ++ BUG_ON(!spin_is_locked(lock)); ++} ++ ++#endif +--- /dev/null ++++ b/include/linux/spinlock_types_rt.h +@@ -0,0 +1,48 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RT_H ++#define __LINUX_SPINLOCK_TYPES_RT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++#include ++ ++/* ++ * PREEMPT_RT: spinlocks - an RT mutex plus lock-break field: ++ */ ++typedef struct spinlock { ++ struct rt_mutex lock; ++ unsigned int break_lock; ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} spinlock_t; ++ ++#ifdef CONFIG_DEBUG_RT_MUTEXES ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ .file = __FILE__, \ ++ .line = __LINE__ , \ ++ } ++#else ++# define __RT_SPIN_INITIALIZER(name) \ ++ { \ ++ .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock), \ ++ .save_state = 1, \ ++ } ++#endif ++ ++/* ++.wait_list = PLIST_HEAD_INIT_RAW((name).lock.wait_list, (name).lock.wait_lock) ++*/ ++ ++#define __SPIN_LOCK_UNLOCKED(name) \ ++ { .lock = __RT_SPIN_INITIALIZER(name.lock), \ ++ SPIN_DEP_MAP_INIT(name) } ++ ++#define DEFINE_SPINLOCK(name) \ ++ spinlock_t name = __SPIN_LOCK_UNLOCKED(name) ++ ++#endif +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -895,6 +895,7 @@ static struct task_struct *dup_task_stru + tsk->splice_pipe = NULL; + tsk->task_frag.page = NULL; + tsk->wake_q.next = NULL; ++ tsk->wake_q_sleeper.next = NULL; + + account_kernel_stack(tsk, 1); + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -1414,6 +1414,7 @@ static int wake_futex_pi(u32 __user *uad + struct task_struct *new_owner; + bool postunlock = false; + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + int ret = 0; + + new_owner = rt_mutex_next_owner(&pi_state->pi_mutex); +@@ -1475,13 +1476,13 @@ static int wake_futex_pi(u32 __user *uad + pi_state->owner = new_owner; + raw_spin_unlock(&new_owner->pi_lock); + +- postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); +- ++ postunlock = __rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q, ++ &wake_sleeper_q); + out_unlock: + raw_spin_unlock_irq(&pi_state->pi_mutex.wait_lock); + + if (postunlock) +- rt_mutex_postunlock(&wake_q); ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + + return ret; + } +@@ -2793,7 +2794,7 @@ static int futex_lock_pi(u32 __user *uad + goto no_block; + } + +- rt_mutex_init_waiter(&rt_waiter); ++ rt_mutex_init_waiter(&rt_waiter, false); + + /* + * On PREEMPT_RT_FULL, when hb->lock becomes an rt_mutex, we must not +@@ -3165,7 +3166,7 @@ static int futex_wait_requeue_pi(u32 __u + * The waiter is allocated on our stack, manipulated by the requeue + * code while we sleep on uaddr. + */ +- rt_mutex_init_waiter(&rt_waiter); ++ rt_mutex_init_waiter(&rt_waiter, false); + + ret = get_futex_key(uaddr2, flags & FLAGS_SHARED, &key2, VERIFY_WRITE); + if (unlikely(ret != 0)) +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -7,6 +7,11 @@ + * Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner + * Copyright (C) 2005 Kihon Technologies Inc., Steven Rostedt + * Copyright (C) 2006 Esben Nielsen ++ * Adaptive Spinlocks: ++ * Copyright (C) 2008 Novell, Inc., Gregory Haskins, Sven Dietrich, ++ * and Peter Morreale, ++ * Adaptive Spinlocks simplification: ++ * Copyright (C) 2008 Red Hat, Inc., Steven Rostedt + * + * See Documentation/locking/rt-mutex-design.txt for details. + */ +@@ -234,7 +239,7 @@ static inline bool unlock_rt_mutex_safe( + * Only use with rt_mutex_waiter_{less,equal}() + */ + #define task_to_waiter(p) \ +- &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline } ++ &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline, .task = (p) } + + static inline int + rt_mutex_waiter_less(struct rt_mutex_waiter *left, +@@ -274,6 +279,27 @@ rt_mutex_waiter_equal(struct rt_mutex_wa + return 1; + } + ++#define STEAL_NORMAL 0 ++#define STEAL_LATERAL 1 ++ ++static inline int ++rt_mutex_steal(struct rt_mutex *lock, struct rt_mutex_waiter *waiter, int mode) ++{ ++ struct rt_mutex_waiter *top_waiter = rt_mutex_top_waiter(lock); ++ ++ if (waiter == top_waiter || rt_mutex_waiter_less(waiter, top_waiter)) ++ return 1; ++ ++ /* ++ * Note that RT tasks are excluded from lateral-steals ++ * to prevent the introduction of an unbounded latency. ++ */ ++ if (mode == STEAL_NORMAL || rt_task(waiter->task)) ++ return 0; ++ ++ return rt_mutex_waiter_equal(waiter, top_waiter); ++} ++ + static void + rt_mutex_enqueue(struct rt_mutex *lock, struct rt_mutex_waiter *waiter) + { +@@ -378,6 +404,14 @@ static bool rt_mutex_cond_detect_deadloc + return debug_rt_mutex_detect_deadlock(waiter, chwalk); + } + ++static void rt_mutex_wake_waiter(struct rt_mutex_waiter *waiter) ++{ ++ if (waiter->savestate) ++ wake_up_lock_sleeper(waiter->task); ++ else ++ wake_up_process(waiter->task); ++} ++ + /* + * Max number of times we'll walk the boosting chain: + */ +@@ -703,13 +737,16 @@ static int rt_mutex_adjust_prio_chain(st + * follow here. This is the end of the chain we are walking. + */ + if (!rt_mutex_owner(lock)) { ++ struct rt_mutex_waiter *lock_top_waiter; ++ + /* + * If the requeue [7] above changed the top waiter, + * then we need to wake the new top waiter up to try + * to get the lock. + */ +- if (prerequeue_top_waiter != rt_mutex_top_waiter(lock)) +- wake_up_process(rt_mutex_top_waiter(lock)->task); ++ lock_top_waiter = rt_mutex_top_waiter(lock); ++ if (prerequeue_top_waiter != lock_top_waiter) ++ rt_mutex_wake_waiter(lock_top_waiter); + raw_spin_unlock_irq(&lock->wait_lock); + return 0; + } +@@ -811,9 +848,11 @@ static int rt_mutex_adjust_prio_chain(st + * @task: The task which wants to acquire the lock + * @waiter: The waiter that is queued to the lock's wait tree if the + * callsite called task_blocked_on_lock(), otherwise NULL ++ * @mode: Lock steal mode (STEAL_NORMAL, STEAL_LATERAL) + */ +-static int try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, +- struct rt_mutex_waiter *waiter) ++static int __try_to_take_rt_mutex(struct rt_mutex *lock, ++ struct task_struct *task, ++ struct rt_mutex_waiter *waiter, int mode) + { + lockdep_assert_held(&lock->wait_lock); + +@@ -849,12 +888,11 @@ static int try_to_take_rt_mutex(struct r + */ + if (waiter) { + /* +- * If waiter is not the highest priority waiter of +- * @lock, give up. ++ * If waiter is not the highest priority waiter of @lock, ++ * or its peer when lateral steal is allowed, give up. + */ +- if (waiter != rt_mutex_top_waiter(lock)) ++ if (!rt_mutex_steal(lock, waiter, mode)) + return 0; +- + /* + * We can acquire the lock. Remove the waiter from the + * lock waiters tree. +@@ -872,14 +910,12 @@ static int try_to_take_rt_mutex(struct r + */ + if (rt_mutex_has_waiters(lock)) { + /* +- * If @task->prio is greater than or equal to +- * the top waiter priority (kernel view), +- * @task lost. ++ * If @task->prio is greater than the top waiter ++ * priority (kernel view), or equal to it when a ++ * lateral steal is forbidden, @task lost. + */ +- if (!rt_mutex_waiter_less(task_to_waiter(task), +- rt_mutex_top_waiter(lock))) ++ if (!rt_mutex_steal(lock, task_to_waiter(task), mode)) + return 0; +- + /* + * The current top waiter stays enqueued. We + * don't have to change anything in the lock +@@ -926,6 +962,296 @@ static int try_to_take_rt_mutex(struct r + return 1; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * preemptible spin_lock functions: ++ */ ++static inline void rt_spin_lock_fastlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ might_sleep_no_state_check(); ++ ++ if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) ++ return; ++ else ++ slowfn(lock); ++} ++ ++static inline void rt_spin_lock_fastunlock(struct rt_mutex *lock, ++ void (*slowfn)(struct rt_mutex *lock)) ++{ ++ if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) ++ return; ++ else ++ slowfn(lock); ++} ++#ifdef CONFIG_SMP ++/* ++ * Note that owner is a speculative pointer and dereferencing relies ++ * on rcu_read_lock() and the check against the lock owner. ++ */ ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *owner) ++{ ++ int res = 0; ++ ++ rcu_read_lock(); ++ for (;;) { ++ if (owner != rt_mutex_owner(lock)) ++ break; ++ /* ++ * Ensure that owner->on_cpu is dereferenced _after_ ++ * checking the above to be valid. ++ */ ++ barrier(); ++ if (!owner->on_cpu) { ++ res = 1; ++ break; ++ } ++ cpu_relax(); ++ } ++ rcu_read_unlock(); ++ return res; ++} ++#else ++static int adaptive_wait(struct rt_mutex *lock, ++ struct task_struct *orig_owner) ++{ ++ return 1; ++} ++#endif ++ ++static int task_blocks_on_rt_mutex(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ struct task_struct *task, ++ enum rtmutex_chainwalk chwalk); ++/* ++ * Slow path lock function spin_lock style: this variant is very ++ * careful not to miss any non-lock wakeups. ++ * ++ * We store the current state under p->pi_lock in p->saved_state and ++ * the try_to_wake_up() code handles this accordingly. ++ */ ++void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ unsigned long flags) ++{ ++ struct task_struct *lock_owner, *self = current; ++ struct rt_mutex_waiter *top_waiter; ++ int ret; ++ ++ if (__try_to_take_rt_mutex(lock, self, NULL, STEAL_LATERAL)) ++ return; ++ ++ BUG_ON(rt_mutex_owner(lock) == self); ++ ++ /* ++ * We save whatever state the task is in and we'll restore it ++ * after acquiring the lock taking real wakeups into account ++ * as well. We are serialized via pi_lock against wakeups. See ++ * try_to_wake_up(). ++ */ ++ raw_spin_lock(&self->pi_lock); ++ self->saved_state = self->state; ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ ++ ret = task_blocks_on_rt_mutex(lock, waiter, self, RT_MUTEX_MIN_CHAINWALK); ++ BUG_ON(ret); ++ ++ for (;;) { ++ /* Try to acquire the lock again. */ ++ if (__try_to_take_rt_mutex(lock, self, waiter, STEAL_LATERAL)) ++ break; ++ ++ top_waiter = rt_mutex_top_waiter(lock); ++ lock_owner = rt_mutex_owner(lock); ++ ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ debug_rt_mutex_print_deadlock(waiter); ++ ++ if (top_waiter != waiter || adaptive_wait(lock, lock_owner)) ++ schedule(); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(TASK_UNINTERRUPTIBLE); ++ raw_spin_unlock(&self->pi_lock); ++ } ++ ++ /* ++ * Restore the task state to current->saved_state. We set it ++ * to the original state above and the try_to_wake_up() code ++ * has possibly updated it when a real (non-rtmutex) wakeup ++ * happened while we were blocked. Clear saved_state so ++ * try_to_wakeup() does not get confused. ++ */ ++ raw_spin_lock(&self->pi_lock); ++ __set_current_state_no_track(self->saved_state); ++ self->saved_state = TASK_RUNNING; ++ raw_spin_unlock(&self->pi_lock); ++ ++ /* ++ * try_to_take_rt_mutex() sets the waiter bit ++ * unconditionally. We might have to fix that up: ++ */ ++ fixup_rt_mutex_waiters(lock); ++ ++ BUG_ON(rt_mutex_has_waiters(lock) && waiter == rt_mutex_top_waiter(lock)); ++ BUG_ON(!RB_EMPTY_NODE(&waiter->tree_entry)); ++} ++ ++static void noinline __sched rt_spin_lock_slowlock(struct rt_mutex *lock) ++{ ++ struct rt_mutex_waiter waiter; ++ unsigned long flags; ++ ++ rt_mutex_init_waiter(&waiter, true); ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ rt_spin_lock_slowlock_locked(lock, &waiter, flags); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ debug_rt_mutex_free_waiter(&waiter); ++} ++ ++static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper); ++/* ++ * Slow path to release a rt_mutex spin_lock style ++ */ ++void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock) ++{ ++ unsigned long flags; ++ DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); ++ bool postunlock; ++ ++ raw_spin_lock_irqsave(&lock->wait_lock, flags); ++ postunlock = __rt_mutex_unlock_common(lock, &wake_q, &wake_sleeper_q); ++ raw_spin_unlock_irqrestore(&lock->wait_lock, flags); ++ ++ if (postunlock) ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); ++} ++ ++void __lockfunc rt_spin_lock(spinlock_t *lock) ++{ ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(rt_spin_lock); ++ ++void __lockfunc __rt_spin_lock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastlock(lock, rt_spin_lock_slowlock); ++} ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) ++{ ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); ++ rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); ++} ++EXPORT_SYMBOL(rt_spin_lock_nested); ++#endif ++ ++void __lockfunc rt_spin_unlock(spinlock_t *lock) ++{ ++ /* NOTE: we always pass in '1' for nested, for simplicity */ ++ spin_release(&lock->dep_map, 1, _RET_IP_); ++ rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); ++ migrate_enable(); ++} ++EXPORT_SYMBOL(rt_spin_unlock); ++ ++void __lockfunc __rt_spin_unlock(struct rt_mutex *lock) ++{ ++ rt_spin_lock_fastunlock(lock, rt_spin_lock_slowunlock); ++} ++EXPORT_SYMBOL(__rt_spin_unlock); ++ ++/* ++ * Wait for the lock to get unlocked: instead of polling for an unlock ++ * (like raw spinlocks do), we lock and unlock, to force the kernel to ++ * schedule if there's contention: ++ */ ++void __lockfunc rt_spin_unlock_wait(spinlock_t *lock) ++{ ++ spin_lock(lock); ++ spin_unlock(lock); ++} ++EXPORT_SYMBOL(rt_spin_unlock_wait); ++ ++int __lockfunc rt_spin_trylock(spinlock_t *lock) ++{ ++ int ret; ++ ++ migrate_disable(); ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ else ++ migrate_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock); ++ ++int __lockfunc rt_spin_trylock_bh(spinlock_t *lock) ++{ ++ int ret; ++ ++ local_bh_disable(); ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } else ++ local_bh_enable(); ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_bh); ++ ++int __lockfunc rt_spin_trylock_irqsave(spinlock_t *lock, unsigned long *flags) ++{ ++ int ret; ++ ++ *flags = 0; ++ ret = __rt_mutex_trylock(&lock->lock); ++ if (ret) { ++ migrate_disable(); ++ spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); ++ } ++ return ret; ++} ++EXPORT_SYMBOL(rt_spin_trylock_irqsave); ++ ++void ++__rt_spin_lock_init(spinlock_t *lock, const char *name, struct lock_class_key *key) ++{ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ /* ++ * Make sure we are not reinitializing a held lock: ++ */ ++ debug_check_no_locks_freed((void *)lock, sizeof(*lock)); ++ lockdep_init_map(&lock->dep_map, name, key, 0); ++#endif ++} ++EXPORT_SYMBOL(__rt_spin_lock_init); ++ ++#endif /* PREEMPT_RT_FULL */ ++ ++static inline int ++try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, ++ struct rt_mutex_waiter *waiter) ++{ ++ return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL); ++} ++ + /* + * Task blocks on lock. + * +@@ -1039,6 +1365,7 @@ static int task_blocks_on_rt_mutex(struc + * Called with lock->wait_lock held and interrupts disabled. + */ + static void mark_wakeup_next_waiter(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q, + struct rt_mutex *lock) + { + struct rt_mutex_waiter *waiter; +@@ -1078,7 +1405,10 @@ static void mark_wakeup_next_waiter(stru + * Pairs with preempt_enable() in rt_mutex_postunlock(); + */ + preempt_disable(); +- wake_q_add(wake_q, waiter->task); ++ if (waiter->savestate) ++ wake_q_add_sleeper(wake_sleeper_q, waiter->task); ++ else ++ wake_q_add(wake_q, waiter->task); + raw_spin_unlock(¤t->pi_lock); + } + +@@ -1162,21 +1492,22 @@ void rt_mutex_adjust_pi(struct task_stru + return; + } + next_lock = waiter->lock; +- raw_spin_unlock_irqrestore(&task->pi_lock, flags); + + /* gets dropped in rt_mutex_adjust_prio_chain()! */ + get_task_struct(task); + ++ raw_spin_unlock_irqrestore(&task->pi_lock, flags); + rt_mutex_adjust_prio_chain(task, RT_MUTEX_MIN_CHAINWALK, NULL, + next_lock, NULL, task); + } + +-void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter) ++void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savestate) + { + debug_rt_mutex_init_waiter(waiter); + RB_CLEAR_NODE(&waiter->pi_tree_entry); + RB_CLEAR_NODE(&waiter->tree_entry); + waiter->task = NULL; ++ waiter->savestate = savestate; + } + + /** +@@ -1293,7 +1624,7 @@ rt_mutex_slowlock(struct rt_mutex *lock, + unsigned long flags; + int ret = 0; + +- rt_mutex_init_waiter(&waiter); ++ rt_mutex_init_waiter(&waiter, false); + + /* + * Technically we could use raw_spin_[un]lock_irq() here, but this can +@@ -1366,7 +1697,8 @@ static inline int rt_mutex_slowtrylock(s + * Return whether the current task needs to call rt_mutex_postunlock(). + */ + static bool __sched rt_mutex_slowunlock(struct rt_mutex *lock, +- struct wake_q_head *wake_q) ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q) + { + unsigned long flags; + +@@ -1420,7 +1752,7 @@ static bool __sched rt_mutex_slowunlock( + * + * Queue the next waiter for wakeup once we release the wait_lock. + */ +- mark_wakeup_next_waiter(wake_q, lock); ++ mark_wakeup_next_waiter(wake_q, wake_sleeper_q, lock); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + return true; /* call rt_mutex_postunlock() */ +@@ -1472,9 +1804,11 @@ rt_mutex_fasttrylock(struct rt_mutex *lo + /* + * Performs the wakeup of the the top-waiter and re-enables preemption. + */ +-void rt_mutex_postunlock(struct wake_q_head *wake_q) ++void rt_mutex_postunlock(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q) + { + wake_up_q(wake_q); ++ wake_up_q_sleeper(wake_sleeper_q); + + /* Pairs with preempt_disable() in rt_mutex_slowunlock() */ + preempt_enable(); +@@ -1483,15 +1817,17 @@ void rt_mutex_postunlock(struct wake_q_h + static inline void + rt_mutex_fastunlock(struct rt_mutex *lock, + bool (*slowfn)(struct rt_mutex *lock, +- struct wake_q_head *wqh)) ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper)) + { + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + + if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) + return; + +- if (slowfn(lock, &wake_q)) +- rt_mutex_postunlock(&wake_q); ++ if (slowfn(lock, &wake_q, &wake_sleeper_q)) ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + } + + int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) +@@ -1673,16 +2009,13 @@ void __sched __rt_mutex_unlock(struct rt + void __sched rt_mutex_unlock(struct rt_mutex *lock) + { + mutex_release(&lock->dep_map, 1, _RET_IP_); +- rt_mutex_fastunlock(lock, rt_mutex_slowunlock); ++ __rt_mutex_unlock(lock); + } + EXPORT_SYMBOL_GPL(rt_mutex_unlock); + +-/** +- * Futex variant, that since futex variants do not use the fast-path, can be +- * simple and will not need to retry. +- */ +-bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wake_q) ++static bool __sched __rt_mutex_unlock_common(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper) + { + lockdep_assert_held(&lock->wait_lock); + +@@ -1699,23 +2032,35 @@ bool __sched __rt_mutex_futex_unlock(str + * avoid inversion prior to the wakeup. preempt_disable() + * therein pairs with rt_mutex_postunlock(). + */ +- mark_wakeup_next_waiter(wake_q, lock); ++ mark_wakeup_next_waiter(wake_q, wq_sleeper, lock); + + return true; /* call postunlock() */ + } + ++/** ++ * Futex variant, that since futex variants do not use the fast-path, can be ++ * simple and will not need to retry. ++ */ ++bool __sched __rt_mutex_futex_unlock(struct rt_mutex *lock, ++ struct wake_q_head *wake_q, ++ struct wake_q_head *wq_sleeper) ++{ ++ return __rt_mutex_unlock_common(lock, wake_q, wq_sleeper); ++} ++ + void __sched rt_mutex_futex_unlock(struct rt_mutex *lock) + { + DEFINE_WAKE_Q(wake_q); ++ DEFINE_WAKE_Q(wake_sleeper_q); + unsigned long flags; + bool postunlock; + + raw_spin_lock_irqsave(&lock->wait_lock, flags); +- postunlock = __rt_mutex_futex_unlock(lock, &wake_q); ++ postunlock = __rt_mutex_futex_unlock(lock, &wake_q, &wake_sleeper_q); + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + + if (postunlock) +- rt_mutex_postunlock(&wake_q); ++ rt_mutex_postunlock(&wake_q, &wake_sleeper_q); + } + + /** +@@ -1754,7 +2099,7 @@ void __rt_mutex_init(struct rt_mutex *lo + if (name && key) + debug_rt_mutex_init(lock, name, key); + } +-EXPORT_SYMBOL_GPL(__rt_mutex_init); ++EXPORT_SYMBOL(__rt_mutex_init); + + /** + * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a +@@ -1923,6 +2268,7 @@ int rt_mutex_wait_proxy_lock(struct rt_m + struct hrtimer_sleeper *to, + struct rt_mutex_waiter *waiter) + { ++ struct task_struct *tsk = current; + int ret; + + raw_spin_lock_irq(&lock->wait_lock); +@@ -1934,6 +2280,24 @@ int rt_mutex_wait_proxy_lock(struct rt_m + * have to fix that up. + */ + fixup_rt_mutex_waiters(lock); ++ /* ++ * RT has a problem here when the wait got interrupted by a timeout ++ * or a signal. task->pi_blocked_on is still set. The task must ++ * acquire the hash bucket lock when returning from this function. ++ * ++ * If the hash bucket lock is contended then the ++ * BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)) in ++ * task_blocks_on_rt_mutex() will trigger. This can be avoided by ++ * clearing task->pi_blocked_on which removes the task from the ++ * boosting chain of the rtmutex. That's correct because the task ++ * is not longer blocked on it. ++ */ ++ if (ret) { ++ raw_spin_lock(&tsk->pi_lock); ++ tsk->pi_blocked_on = NULL; ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ + raw_spin_unlock_irq(&lock->wait_lock); + + return ret; +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -15,6 +15,7 @@ + + #include + #include ++#include + + /* + * This is the control structure for tasks blocked on a rt_mutex, +@@ -29,6 +30,7 @@ struct rt_mutex_waiter { + struct rb_node pi_tree_entry; + struct task_struct *task; + struct rt_mutex *lock; ++ bool savestate; + #ifdef CONFIG_DEBUG_RT_MUTEXES + unsigned long ip; + struct pid *deadlock_task_pid; +@@ -138,7 +140,7 @@ extern void rt_mutex_init_proxy_locked(s + struct task_struct *proxy_owner); + extern void rt_mutex_proxy_unlock(struct rt_mutex *lock, + struct task_struct *proxy_owner); +-extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter); ++extern void rt_mutex_init_waiter(struct rt_mutex_waiter *waiter, bool savetate); + extern int __rt_mutex_start_proxy_lock(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, + struct task_struct *task); +@@ -156,9 +158,12 @@ extern int __rt_mutex_futex_trylock(stru + + extern void rt_mutex_futex_unlock(struct rt_mutex *lock); + extern bool __rt_mutex_futex_unlock(struct rt_mutex *lock, +- struct wake_q_head *wqh); ++ struct wake_q_head *wqh, ++ struct wake_q_head *wq_sleeper); ++ ++extern void rt_mutex_postunlock(struct wake_q_head *wake_q, ++ struct wake_q_head *wake_sleeper_q); + +-extern void rt_mutex_postunlock(struct wake_q_head *wake_q); + /* RW semaphore special interface */ + + extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); +@@ -168,6 +173,10 @@ int __sched rt_mutex_slowlock_locked(str + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, + struct rt_mutex_waiter *waiter); ++void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, ++ struct rt_mutex_waiter *waiter, ++ unsigned long flags); ++void __sched rt_spin_lock_slowunlock(struct rt_mutex *lock); + + #ifdef CONFIG_DEBUG_RT_MUTEXES + # include "rtmutex-debug.h" +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -407,9 +407,15 @@ static bool set_nr_if_polling(struct tas + #endif + #endif + +-void wake_q_add(struct wake_q_head *head, struct task_struct *task) ++void __wake_q_add(struct wake_q_head *head, struct task_struct *task, ++ bool sleeper) + { +- struct wake_q_node *node = &task->wake_q; ++ struct wake_q_node *node; ++ ++ if (sleeper) ++ node = &task->wake_q_sleeper; ++ else ++ node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means +@@ -431,24 +437,32 @@ void wake_q_add(struct wake_q_head *head + head->lastp = &node->next; + } + +-void wake_up_q(struct wake_q_head *head) ++void __wake_up_q(struct wake_q_head *head, bool sleeper) + { + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + +- task = container_of(node, struct task_struct, wake_q); ++ if (sleeper) ++ task = container_of(node, struct task_struct, wake_q_sleeper); ++ else ++ task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* Task can safely be re-inserted now: */ + node = node->next; +- task->wake_q.next = NULL; +- ++ if (sleeper) ++ task->wake_q_sleeper.next = NULL; ++ else ++ task->wake_q.next = NULL; + /* + * wake_up_process() implies a wmb() to pair with the queueing + * in wake_q_add() so as not to miss wakeups. + */ +- wake_up_process(task); ++ if (sleeper) ++ wake_up_lock_sleeper(task); ++ else ++ wake_up_process(task); + put_task_struct(task); + } + } diff --git a/debian/patches/features/all/rt/rtmutex-add-ww_mutex-addon-for-mutex-rt.patch b/debian/patches/features/all/rt/rtmutex-add-ww_mutex-addon-for-mutex-rt.patch new file mode 100644 index 000000000..bca1a5120 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-add-ww_mutex-addon-for-mutex-rt.patch @@ -0,0 +1,426 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 12 Oct 2017 17:34:38 +0200 +Subject: rtmutex: add ww_mutex addon for mutex-rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 269 ++++++++++++++++++++++++++++++++++++++-- + kernel/locking/rtmutex_common.h | 2 + kernel/locking/rwsem-rt.c | 2 + 3 files changed, 260 insertions(+), 13 deletions(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -23,6 +23,7 @@ + #include + #include + #include ++#include + + #include "rtmutex_common.h" + +@@ -1245,6 +1246,40 @@ EXPORT_SYMBOL(__rt_spin_lock_init); + + #endif /* PREEMPT_RT_FULL */ + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct ww_acquire_ctx *hold_ctx = READ_ONCE(ww->ctx); ++ ++ if (!hold_ctx) ++ return 0; ++ ++ if (unlikely(ctx == hold_ctx)) ++ return -EALREADY; ++ ++ if (ctx->stamp - hold_ctx->stamp <= LONG_MAX && ++ (ctx->stamp != hold_ctx->stamp || ctx > hold_ctx)) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(ctx->contending_lock); ++ ctx->contending_lock = ww; ++#endif ++ return -EDEADLK; ++ } ++ ++ return 0; ++} ++#else ++ static inline int __sched ++__mutex_lock_check_stamp(struct rt_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ BUG(); ++ return 0; ++} ++ ++#endif ++ + static inline int + try_to_take_rt_mutex(struct rt_mutex *lock, struct task_struct *task, + struct rt_mutex_waiter *waiter) +@@ -1523,7 +1558,8 @@ void rt_mutex_init_waiter(struct rt_mute + static int __sched + __rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- struct rt_mutex_waiter *waiter) ++ struct rt_mutex_waiter *waiter, ++ struct ww_acquire_ctx *ww_ctx) + { + int ret = 0; + +@@ -1541,6 +1577,12 @@ static int __sched + break; + } + ++ if (ww_ctx && ww_ctx->acquired > 0) { ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ if (ret) ++ break; ++ } ++ + raw_spin_unlock_irq(&lock->wait_lock); + + debug_rt_mutex_print_deadlock(waiter); +@@ -1575,16 +1617,106 @@ static void rt_mutex_handle_deadlock(int + } + } + ++static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++#ifdef CONFIG_DEBUG_MUTEXES ++ /* ++ * If this WARN_ON triggers, you used ww_mutex_lock to acquire, ++ * but released with a normal mutex_unlock in this call. ++ * ++ * This should never happen, always use ww_mutex_unlock. ++ */ ++ DEBUG_LOCKS_WARN_ON(ww->ctx); ++ ++ /* ++ * Not quite done after calling ww_acquire_done() ? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->done_acquire); ++ ++ if (ww_ctx->contending_lock) { ++ /* ++ * After -EDEADLK you tried to ++ * acquire a different ww_mutex? Bad! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->contending_lock != ww); ++ ++ /* ++ * You called ww_mutex_lock after receiving -EDEADLK, ++ * but 'forgot' to unlock everything else first? ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->acquired > 0); ++ ww_ctx->contending_lock = NULL; ++ } ++ ++ /* ++ * Naughty, using a different class will lead to undefined behavior! ++ */ ++ DEBUG_LOCKS_WARN_ON(ww_ctx->ww_class != ww->ww_class); ++#endif ++ ww_ctx->acquired++; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ struct ww_mutex *ww = container_of(lock, struct ww_mutex, base.lock); ++ struct rt_mutex_waiter *waiter, *n; ++ ++ /* ++ * This branch gets optimized out for the common case, ++ * and is only important for ww_mutex_lock. ++ */ ++ ww_mutex_lock_acquired(ww, ww_ctx); ++ ww->ctx = ww_ctx; ++ ++ /* ++ * Give any possible sleeping processes the chance to wake up, ++ * so they can recheck if they have to back off. ++ */ ++ rbtree_postorder_for_each_entry_safe(waiter, n, &lock->waiters.rb_root, ++ tree_entry) { ++ /* XXX debug rt mutex waiter wakeup */ ++ ++ BUG_ON(waiter->lock != lock); ++ rt_mutex_wake_waiter(waiter); ++ } ++} ++ ++#else ++ ++static void ww_mutex_account_lock(struct rt_mutex *lock, ++ struct ww_acquire_ctx *ww_ctx) ++{ ++ BUG(); ++} ++#endif ++ + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter) + { + int ret; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (ww_ctx) { ++ struct ww_mutex *ww; ++ ++ ww = container_of(lock, struct ww_mutex, base.lock); ++ if (unlikely(ww_ctx == READ_ONCE(ww->ctx))) ++ return -EALREADY; ++ } ++#endif ++ + /* Try to acquire the lock again: */ +- if (try_to_take_rt_mutex(lock, current, NULL)) ++ if (try_to_take_rt_mutex(lock, current, NULL)) { ++ if (ww_ctx) ++ ww_mutex_account_lock(lock, ww_ctx); + return 0; ++ } + + set_current_state(state); + +@@ -1594,14 +1726,24 @@ int __sched rt_mutex_slowlock_locked(str + + ret = task_blocks_on_rt_mutex(lock, waiter, current, chwalk); + +- if (likely(!ret)) ++ if (likely(!ret)) { + /* sleep on the mutex */ +- ret = __rt_mutex_slowlock(lock, state, timeout, waiter); ++ ret = __rt_mutex_slowlock(lock, state, timeout, waiter, ++ ww_ctx); ++ } else if (ww_ctx) { ++ /* ww_mutex received EDEADLK, let it become EALREADY */ ++ ret = __mutex_lock_check_stamp(lock, ww_ctx); ++ BUG_ON(!ret); ++ } + + if (unlikely(ret)) { + __set_current_state(TASK_RUNNING); + remove_waiter(lock, waiter); +- rt_mutex_handle_deadlock(ret, chwalk, waiter); ++ /* ww_mutex wants to report EDEADLK/EALREADY, let it */ ++ if (!ww_ctx) ++ rt_mutex_handle_deadlock(ret, chwalk, waiter); ++ } else if (ww_ctx) { ++ ww_mutex_account_lock(lock, ww_ctx); + } + + /* +@@ -1618,7 +1760,8 @@ int __sched rt_mutex_slowlock_locked(str + static int __sched + rt_mutex_slowlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx) + { + struct rt_mutex_waiter waiter; + unsigned long flags; +@@ -1636,7 +1779,8 @@ rt_mutex_slowlock(struct rt_mutex *lock, + */ + raw_spin_lock_irqsave(&lock->wait_lock, flags); + +- ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, &waiter); ++ ret = rt_mutex_slowlock_locked(lock, state, timeout, chwalk, ww_ctx, ++ &waiter); + + raw_spin_unlock_irqrestore(&lock->wait_lock, flags); + +@@ -1766,29 +1910,33 @@ static bool __sched rt_mutex_slowunlock( + */ + static inline int + rt_mutex_fastlock(struct rt_mutex *lock, int state, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + +- return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK); ++ return slowfn(lock, state, NULL, RT_MUTEX_MIN_CHAINWALK, ww_ctx); + } + + static inline int + rt_mutex_timed_fastlock(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + int (*slowfn)(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, +- enum rtmutex_chainwalk chwalk)) ++ enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx)) + { + if (chwalk == RT_MUTEX_MIN_CHAINWALK && + likely(rt_mutex_cmpxchg_acquire(lock, NULL, current))) + return 0; + +- return slowfn(lock, state, timeout, chwalk); ++ return slowfn(lock, state, timeout, chwalk, ww_ctx); + } + + static inline int +@@ -1953,6 +2101,7 @@ rt_mutex_timed_lock(struct rt_mutex *loc + mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); + ret = rt_mutex_timed_fastlock(lock, TASK_INTERRUPTIBLE, timeout, + RT_MUTEX_MIN_CHAINWALK, ++ NULL, + rt_mutex_slowlock); + if (ret) + mutex_release(&lock->dep_map, 1, _RET_IP_); +@@ -2274,7 +2423,7 @@ int rt_mutex_wait_proxy_lock(struct rt_m + raw_spin_lock_irq(&lock->wait_lock); + /* sleep on the mutex */ + set_current_state(TASK_INTERRUPTIBLE); +- ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter); ++ ret = __rt_mutex_slowlock(lock, TASK_INTERRUPTIBLE, to, waiter, NULL); + /* + * try_to_take_rt_mutex() sets the waiter bit unconditionally. We might + * have to fix that up. +@@ -2358,3 +2507,99 @@ bool rt_mutex_cleanup_proxy_lock(struct + + return cleanup; + } ++ ++static inline int ++ww_mutex_deadlock_injection(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++#ifdef CONFIG_DEBUG_WW_MUTEX_SLOWPATH ++ unsigned tmp; ++ ++ if (ctx->deadlock_inject_countdown-- == 0) { ++ tmp = ctx->deadlock_inject_interval; ++ if (tmp > UINT_MAX/4) ++ tmp = UINT_MAX; ++ else ++ tmp = tmp*2 + tmp + tmp/2; ++ ++ ctx->deadlock_inject_interval = tmp; ++ ctx->deadlock_inject_countdown = tmp; ++ ctx->contending_lock = lock; ++ ++ ww_mutex_unlock(lock); ++ ++ return -EDEADLK; ++ } ++#endif ++ ++ return 0; ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++int __sched ++ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, ++ ctx ? &ctx->dep_map : NULL, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_INTERRUPTIBLE, NULL, 0, ++ ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ctx && ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(ww_mutex_lock_interruptible); ++ ++int __sched ++ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx) ++{ ++ int ret; ++ ++ might_sleep(); ++ ++ mutex_acquire_nest(&lock->base.dep_map, 0, 0, ++ ctx ? &ctx->dep_map : NULL, _RET_IP_); ++ ret = rt_mutex_slowlock(&lock->base.lock, TASK_UNINTERRUPTIBLE, NULL, 0, ++ ctx); ++ if (ret) ++ mutex_release(&lock->base.dep_map, 1, _RET_IP_); ++ else if (!ret && ctx && ctx->acquired > 1) ++ return ww_mutex_deadlock_injection(lock, ctx); ++ ++ return ret; ++} ++EXPORT_SYMBOL_GPL(ww_mutex_lock); ++ ++void __sched ww_mutex_unlock(struct ww_mutex *lock) ++{ ++ int nest = !!lock->ctx; ++ ++ /* ++ * The unlocking fastpath is the 0->1 transition from 'locked' ++ * into 'unlocked' state: ++ */ ++ if (nest) { ++#ifdef CONFIG_DEBUG_MUTEXES ++ DEBUG_LOCKS_WARN_ON(!lock->ctx->acquired); ++#endif ++ if (lock->ctx->acquired > 0) ++ lock->ctx->acquired--; ++ lock->ctx = NULL; ++ } ++ ++ mutex_release(&lock->base.dep_map, nest, _RET_IP_); ++ __rt_mutex_unlock(&lock->base.lock); ++} ++EXPORT_SYMBOL(ww_mutex_unlock); ++ ++int __rt_mutex_owner_current(struct rt_mutex *lock) ++{ ++ return rt_mutex_owner(lock) == current; ++} ++EXPORT_SYMBOL(__rt_mutex_owner_current); ++#endif +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -165,6 +165,7 @@ extern void rt_mutex_postunlock(struct w + struct wake_q_head *wake_sleeper_q); + + /* RW semaphore special interface */ ++struct ww_acquire_ctx; + + extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); + extern int __rt_mutex_trylock(struct rt_mutex *lock); +@@ -172,6 +173,7 @@ extern void __rt_mutex_unlock(struct rt_ + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, ++ struct ww_acquire_ctx *ww_ctx, + struct rt_mutex_waiter *waiter); + void __sched rt_spin_lock_slowlock_locked(struct rt_mutex *lock, + struct rt_mutex_waiter *waiter, +--- a/kernel/locking/rwsem-rt.c ++++ b/kernel/locking/rwsem-rt.c +@@ -131,7 +131,7 @@ static int __sched __down_read_common(st + */ + rt_mutex_init_waiter(&waiter, false); + ret = rt_mutex_slowlock_locked(m, state, NULL, RT_MUTEX_MIN_CHAINWALK, +- &waiter); ++ NULL, &waiter); + /* + * The slowlock() above is guaranteed to return with the rtmutex (for + * ret = 0) is now held, so there can't be a writer active. Increment diff --git a/debian/patches/features/all/rt/rtmutex-annotate-sleeping-lock-context.patch b/debian/patches/features/all/rt/rtmutex-annotate-sleeping-lock-context.patch new file mode 100644 index 000000000..4c9ee012c --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-annotate-sleeping-lock-context.patch @@ -0,0 +1,292 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 21 Sep 2017 14:25:13 +0200 +Subject: [PATCH] rtmutex: annotate sleeping lock context +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The RCU code complains on schedule() within a rcu_readlock() section. +The valid scenario on -RT is if a sleeping is held. In order to suppress +the warning the mirgrate_disable counter was used to identify the +invocation of schedule() due to lock contention. + +Grygorii Strashko report that during CPU hotplug we might see the +warning via + rt_spin_lock() -> migrate_disable() -> pin_current_cpu() -> __read_rt_lock() + +because the counter is not yet set. +It is also possible to trigger the warning from cpu_chill() +(seen on a kblockd_mod_delayed_work_on() caller). + +To address this RCU warning I annotate the sleeping lock context. The +counter is incremented before migrate_disable() so the warning Grygorii +should not trigger anymore. Additionally I use that counter in +cpu_chill() to avoid the RCU warning from there. + +Reported-by: Grygorii Strashko +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/preempt.h | 9 +++++++++ + include/linux/sched.h | 26 ++++++++++++++++++++++++++ + kernel/locking/rtmutex.c | 12 ++++++++++-- + kernel/locking/rwlock-rt.c | 18 ++++++++++++++---- + kernel/rcu/tree_plugin.h | 6 +++++- + kernel/sched/core.c | 45 +++++++++++++++++++++++++++++++++++++++++++++ + 6 files changed, 109 insertions(+), 7 deletions(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -211,6 +211,15 @@ extern void migrate_enable(void); + + int __migrate_disabled(struct task_struct *p); + ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++ ++extern void migrate_disable(void); ++extern void migrate_enable(void); ++static inline int __migrate_disabled(struct task_struct *p) ++{ ++ return 0; ++} ++ + #else + #define migrate_disable() barrier() + #define migrate_enable() barrier() +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -673,6 +673,15 @@ struct task_struct { + # ifdef CONFIG_SCHED_DEBUG + int migrate_disable_atomic; + # endif ++ ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++ int migrate_disable; ++# ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable_atomic; ++# endif ++#endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ int sleeping_lock; + #endif + + #ifdef CONFIG_PREEMPT_RCU +@@ -1800,6 +1809,23 @@ static __always_inline bool need_resched + return unlikely(tif_need_resched()); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static inline void sleeping_lock_inc(void) ++{ ++ current->sleeping_lock++; ++} ++ ++static inline void sleeping_lock_dec(void) ++{ ++ current->sleeping_lock--; ++} ++ ++#else ++ ++static inline void sleeping_lock_inc(void) { } ++static inline void sleeping_lock_dec(void) { } ++#endif ++ + /* + * Wrappers for p->thread_info->cpu access. No-op on UP. + */ +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1141,6 +1141,7 @@ void __sched rt_spin_lock_slowunlock(str + + void __lockfunc rt_spin_lock(spinlock_t *lock) + { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1155,6 +1156,7 @@ void __lockfunc __rt_spin_lock(struct rt + #ifdef CONFIG_DEBUG_LOCK_ALLOC + void __lockfunc rt_spin_lock_nested(spinlock_t *lock, int subclass) + { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_); + rt_spin_lock_fastlock(&lock->lock, rt_spin_lock_slowlock); +@@ -1168,6 +1170,7 @@ void __lockfunc rt_spin_unlock(spinlock_ + spin_release(&lock->dep_map, 1, _RET_IP_); + rt_spin_lock_fastunlock(&lock->lock, rt_spin_lock_slowunlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_spin_unlock); + +@@ -1193,12 +1196,15 @@ int __lockfunc rt_spin_trylock(spinlock_ + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = __rt_mutex_trylock(&lock->lock); +- if (ret) ++ if (ret) { + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_spin_trylock); +@@ -1210,6 +1216,7 @@ int __lockfunc rt_spin_trylock_bh(spinlo + local_bh_disable(); + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } else +@@ -1225,6 +1232,7 @@ int __lockfunc rt_spin_trylock_irqsave(s + *flags = 0; + ret = __rt_mutex_trylock(&lock->lock); + if (ret) { ++ sleeping_lock_inc(); + migrate_disable(); + spin_acquire(&lock->dep_map, 0, 1, _RET_IP_); + } +--- a/kernel/locking/rwlock-rt.c ++++ b/kernel/locking/rwlock-rt.c +@@ -305,12 +305,15 @@ int __lockfunc rt_read_trylock(rwlock_t + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = do_read_rt_trylock(rwlock); +- if (ret) ++ if (ret) { + rwlock_acquire_read(&rwlock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_read_trylock); +@@ -319,18 +322,22 @@ int __lockfunc rt_write_trylock(rwlock_t + { + int ret; + ++ sleeping_lock_inc(); + migrate_disable(); + ret = do_write_rt_trylock(rwlock); +- if (ret) ++ if (ret) { + rwlock_acquire(&rwlock->dep_map, 0, 1, _RET_IP_); +- else ++ } else { + migrate_enable(); ++ sleeping_lock_dec(); ++ } + return ret; + } + EXPORT_SYMBOL(rt_write_trylock); + + void __lockfunc rt_read_lock(rwlock_t *rwlock) + { ++ sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire_read(&rwlock->dep_map, 0, 0, _RET_IP_); + do_read_rt_lock(rwlock); +@@ -339,6 +346,7 @@ EXPORT_SYMBOL(rt_read_lock); + + void __lockfunc rt_write_lock(rwlock_t *rwlock) + { ++ sleeping_lock_inc(); + migrate_disable(); + rwlock_acquire(&rwlock->dep_map, 0, 0, _RET_IP_); + do_write_rt_lock(rwlock); +@@ -350,6 +358,7 @@ void __lockfunc rt_read_unlock(rwlock_t + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_read_rt_unlock(rwlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_read_unlock); + +@@ -358,6 +367,7 @@ void __lockfunc rt_write_unlock(rwlock_t + rwlock_release(&rwlock->dep_map, 1, _RET_IP_); + do_write_rt_unlock(rwlock); + migrate_enable(); ++ sleeping_lock_dec(); + } + EXPORT_SYMBOL(rt_write_unlock); + +--- a/kernel/rcu/tree_plugin.h ++++ b/kernel/rcu/tree_plugin.h +@@ -325,9 +325,13 @@ static void rcu_preempt_note_context_swi + struct task_struct *t = current; + struct rcu_data *rdp; + struct rcu_node *rnp; ++ int sleeping_l = 0; + + lockdep_assert_irqs_disabled(); +- WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0); ++#if defined(CONFIG_PREEMPT_RT_FULL) ++ sleeping_l = t->sleeping_lock; ++#endif ++ WARN_ON_ONCE(!preempt && t->rcu_read_lock_nesting > 0 && !sleeping_l); + if (t->rcu_read_lock_nesting > 0 && + !t->rcu_read_unlock_special.b.blocked) { + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -7330,4 +7330,49 @@ void migrate_enable(void) + preempt_enable(); + } + EXPORT_SYMBOL(migrate_enable); ++ ++#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) ++void migrate_disable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic++; ++#endif ++ return; ++ } ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ p->migrate_disable++; ++} ++EXPORT_SYMBOL(migrate_disable); ++ ++void migrate_enable(void) ++{ ++ struct task_struct *p = current; ++ ++ if (in_atomic() || irqs_disabled()) { ++#ifdef CONFIG_SCHED_DEBUG ++ p->migrate_disable_atomic--; ++#endif ++ return; ++ } ++ ++#ifdef CONFIG_SCHED_DEBUG ++ if (unlikely(p->migrate_disable_atomic)) { ++ tracing_off(); ++ WARN_ON_ONCE(1); ++ } ++#endif ++ ++ WARN_ON_ONCE(p->migrate_disable <= 0); ++ p->migrate_disable--; ++} ++EXPORT_SYMBOL(migrate_enable); + #endif diff --git a/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch b/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch new file mode 100644 index 000000000..d976479c5 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-avoid-include-hell.patch @@ -0,0 +1,24 @@ +Subject: rtmutex: Avoid include hell +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 20:06:39 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Include only the required raw types. This avoids pulling in the +complete spinlock header which in turn requires rtmutex.h at some point. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rtmutex.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -15,7 +15,7 @@ + + #include + #include +-#include ++#include + + extern int max_lock_depth; /* for sysctl */ + diff --git a/debian/patches/features/all/rt/rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch b/debian/patches/features/all/rt/rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch new file mode 100644 index 000000000..f7e4e2ab7 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch @@ -0,0 +1,145 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 16:36:39 +0200 +Subject: rtmutex: export lockdep-less version of rt_mutex's lock, + trylock and unlock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Required for lock implementation ontop of rtmutex. + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 67 +++++++++++++++++++++++++--------------- + kernel/locking/rtmutex_common.h | 3 + + 2 files changed, 46 insertions(+), 24 deletions(-) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1494,12 +1494,33 @@ rt_mutex_fastunlock(struct rt_mutex *loc + rt_mutex_postunlock(&wake_q); + } + +-static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) ++int __sched __rt_mutex_lock_state(struct rt_mutex *lock, int state) + { + might_sleep(); ++ return rt_mutex_fastlock(lock, state, NULL, rt_mutex_slowlock); ++} ++ ++/** ++ * rt_mutex_lock_state - lock a rt_mutex with a given state ++ * ++ * @lock: The rt_mutex to be locked ++ * @state: The state to set when blocking on the rt_mutex ++ */ ++static inline int __sched rt_mutex_lock_state(struct rt_mutex *lock, ++ unsigned int subclass, int state) ++{ ++ int ret; + + mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_); +- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock); ++ ret = __rt_mutex_lock_state(lock, state); ++ if (ret) ++ mutex_release(&lock->dep_map, 1, _RET_IP_); ++ return ret; ++} ++ ++static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass) ++{ ++ rt_mutex_lock_state(lock, subclass, TASK_UNINTERRUPTIBLE); + } + + #ifdef CONFIG_DEBUG_LOCK_ALLOC +@@ -1540,16 +1561,7 @@ EXPORT_SYMBOL_GPL(rt_mutex_lock); + */ + int __sched rt_mutex_lock_interruptible(struct rt_mutex *lock) + { +- int ret; +- +- might_sleep(); +- +- mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_); +- ret = rt_mutex_fastlock(lock, TASK_INTERRUPTIBLE, rt_mutex_slowlock); +- if (ret) +- mutex_release(&lock->dep_map, 1, _RET_IP_); +- +- return ret; ++ return rt_mutex_lock_state(lock, 0, TASK_INTERRUPTIBLE); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_interruptible); + +@@ -1575,13 +1587,10 @@ int __sched __rt_mutex_futex_trylock(str + * Returns: + * 0 on success + * -EINTR when interrupted by a signal +- * -EDEADLK when the lock would deadlock (when deadlock detection is on) + */ + int __sched rt_mutex_lock_killable(struct rt_mutex *lock) + { +- might_sleep(); +- +- return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++ return rt_mutex_lock_state(lock, 0, TASK_KILLABLE); + } + EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); + +@@ -1616,6 +1625,18 @@ rt_mutex_timed_lock(struct rt_mutex *loc + } + EXPORT_SYMBOL_GPL(rt_mutex_timed_lock); + ++int __sched __rt_mutex_trylock(struct rt_mutex *lock) ++{ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (WARN_ON_ONCE(in_irq() || in_nmi())) ++#else ++ if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) ++#endif ++ return 0; ++ ++ return rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); ++} ++ + /** + * rt_mutex_trylock - try to lock a rt_mutex + * +@@ -1631,14 +1652,7 @@ int __sched rt_mutex_trylock(struct rt_m + { + int ret; + +-#ifdef CONFIG_PREEMPT_RT_FULL +- if (WARN_ON_ONCE(in_irq() || in_nmi())) +-#else +- if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) +-#endif +- return 0; +- +- ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); ++ ret = __rt_mutex_trylock(lock); + if (ret) + mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_); + +@@ -1646,6 +1660,11 @@ int __sched rt_mutex_trylock(struct rt_m + } + EXPORT_SYMBOL_GPL(rt_mutex_trylock); + ++void __sched __rt_mutex_unlock(struct rt_mutex *lock) ++{ ++ rt_mutex_fastunlock(lock, rt_mutex_slowunlock); ++} ++ + /** + * rt_mutex_unlock - unlock a rt_mutex + * +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -161,6 +161,9 @@ extern bool __rt_mutex_futex_unlock(stru + extern void rt_mutex_postunlock(struct wake_q_head *wake_q); + /* RW semaphore special interface */ + ++extern int __rt_mutex_lock_state(struct rt_mutex *lock, int state); ++extern int __rt_mutex_trylock(struct rt_mutex *lock); ++extern void __rt_mutex_unlock(struct rt_mutex *lock); + int __sched rt_mutex_slowlock_locked(struct rt_mutex *lock, int state, + struct hrtimer_sleeper *timeout, + enum rtmutex_chainwalk chwalk, diff --git a/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch b/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch new file mode 100644 index 000000000..cf15d4a09 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-futex-prepare-rt.patch @@ -0,0 +1,245 @@ +Subject: rtmutex: Handle the various new futex race conditions +From: Thomas Gleixner +Date: Fri, 10 Jun 2011 11:04:15 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +RT opens a few new interesting race conditions in the rtmutex/futex +combo due to futex hash bucket lock being a 'sleeping' spinlock and +therefor not disabling preemption. + +Signed-off-by: Thomas Gleixner +--- + kernel/futex.c | 77 ++++++++++++++++++++++++++++++++-------- + kernel/locking/rtmutex.c | 36 +++++++++++++++--- + kernel/locking/rtmutex_common.h | 2 + + 3 files changed, 94 insertions(+), 21 deletions(-) + +--- a/kernel/futex.c ++++ b/kernel/futex.c +@@ -2086,6 +2086,16 @@ static int futex_requeue(u32 __user *uad + requeue_pi_wake_futex(this, &key2, hb2); + drop_count++; + continue; ++ } else if (ret == -EAGAIN) { ++ /* ++ * Waiter was woken by timeout or ++ * signal and has set pi_blocked_on to ++ * PI_WAKEUP_INPROGRESS before we ++ * tried to enqueue it on the rtmutex. ++ */ ++ this->pi_state = NULL; ++ put_pi_state(pi_state); ++ continue; + } else if (ret) { + /* + * rt_mutex_start_proxy_lock() detected a +@@ -3126,7 +3136,7 @@ static int futex_wait_requeue_pi(u32 __u + struct hrtimer_sleeper timeout, *to = NULL; + struct futex_pi_state *pi_state = NULL; + struct rt_mutex_waiter rt_waiter; +- struct futex_hash_bucket *hb; ++ struct futex_hash_bucket *hb, *hb2; + union futex_key key2 = FUTEX_KEY_INIT; + struct futex_q q = futex_q_init; + int res, ret; +@@ -3184,20 +3194,55 @@ static int futex_wait_requeue_pi(u32 __u + /* Queue the futex_q, drop the hb lock, wait for wakeup. */ + futex_wait_queue_me(hb, &q, to); + +- spin_lock(&hb->lock); +- ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); +- spin_unlock(&hb->lock); +- if (ret) +- goto out_put_keys; ++ /* ++ * On RT we must avoid races with requeue and trying to block ++ * on two mutexes (hb->lock and uaddr2's rtmutex) by ++ * serializing access to pi_blocked_on with pi_lock. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ if (current->pi_blocked_on) { ++ /* ++ * We have been requeued or are in the process of ++ * being requeued. ++ */ ++ raw_spin_unlock_irq(¤t->pi_lock); ++ } else { ++ /* ++ * Setting pi_blocked_on to PI_WAKEUP_INPROGRESS ++ * prevents a concurrent requeue from moving us to the ++ * uaddr2 rtmutex. After that we can safely acquire ++ * (and possibly block on) hb->lock. ++ */ ++ current->pi_blocked_on = PI_WAKEUP_INPROGRESS; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ spin_lock(&hb->lock); ++ ++ /* ++ * Clean up pi_blocked_on. We might leak it otherwise ++ * when we succeeded with the hb->lock in the fast ++ * path. ++ */ ++ raw_spin_lock_irq(¤t->pi_lock); ++ current->pi_blocked_on = NULL; ++ raw_spin_unlock_irq(¤t->pi_lock); ++ ++ ret = handle_early_requeue_pi_wakeup(hb, &q, &key2, to); ++ spin_unlock(&hb->lock); ++ if (ret) ++ goto out_put_keys; ++ } + + /* +- * In order for us to be here, we know our q.key == key2, and since +- * we took the hb->lock above, we also know that futex_requeue() has +- * completed and we no longer have to concern ourselves with a wakeup +- * race with the atomic proxy lock acquisition by the requeue code. The +- * futex_requeue dropped our key1 reference and incremented our key2 +- * reference count. ++ * In order to be here, we have either been requeued, are in ++ * the process of being requeued, or requeue successfully ++ * acquired uaddr2 on our behalf. If pi_blocked_on was ++ * non-null above, we may be racing with a requeue. Do not ++ * rely on q->lock_ptr to be hb2->lock until after blocking on ++ * hb->lock or hb2->lock. The futex_requeue dropped our key1 ++ * reference and incremented our key2 reference count. + */ ++ hb2 = hash_futex(&key2); + + /* Check if the requeue code acquired the second futex for us. */ + if (!q.rt_waiter) { +@@ -3206,7 +3251,8 @@ static int futex_wait_requeue_pi(u32 __u + * did a lock-steal - fix up the PI-state in that case. + */ + if (q.pi_state && (q.pi_state->owner != current)) { +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + ret = fixup_pi_state_owner(uaddr2, &q, current); + if (ret && rt_mutex_owner(&q.pi_state->pi_mutex) == current) { + pi_state = q.pi_state; +@@ -3217,7 +3263,7 @@ static int futex_wait_requeue_pi(u32 __u + * the requeue_pi() code acquired for us. + */ + put_pi_state(q.pi_state); +- spin_unlock(q.lock_ptr); ++ spin_unlock(&hb2->lock); + } + } else { + struct rt_mutex *pi_mutex; +@@ -3231,7 +3277,8 @@ static int futex_wait_requeue_pi(u32 __u + pi_mutex = &q.pi_state->pi_mutex; + ret = rt_mutex_wait_proxy_lock(pi_mutex, to, &rt_waiter); + +- spin_lock(q.lock_ptr); ++ spin_lock(&hb2->lock); ++ BUG_ON(&hb2->lock != q.lock_ptr); + if (ret && !rt_mutex_cleanup_proxy_lock(pi_mutex, &rt_waiter)) + ret = 0; + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -135,6 +135,11 @@ static void fixup_rt_mutex_waiters(struc + WRITE_ONCE(*p, owner & ~RT_MUTEX_HAS_WAITERS); + } + ++static int rt_mutex_real_waiter(struct rt_mutex_waiter *waiter) ++{ ++ return waiter && waiter != PI_WAKEUP_INPROGRESS; ++} ++ + /* + * We can speed up the acquire/release, if there's no debugging state to be + * set up. +@@ -379,7 +384,8 @@ int max_lock_depth = 1024; + + static inline struct rt_mutex *task_blocked_on_lock(struct task_struct *p) + { +- return p->pi_blocked_on ? p->pi_blocked_on->lock : NULL; ++ return rt_mutex_real_waiter(p->pi_blocked_on) ? ++ p->pi_blocked_on->lock : NULL; + } + + /* +@@ -515,7 +521,7 @@ static int rt_mutex_adjust_prio_chain(st + * reached or the state of the chain has changed while we + * dropped the locks. + */ +- if (!waiter) ++ if (!rt_mutex_real_waiter(waiter)) + goto out_unlock_pi; + + /* +@@ -951,6 +957,22 @@ static int task_blocks_on_rt_mutex(struc + return -EDEADLK; + + raw_spin_lock(&task->pi_lock); ++ /* ++ * In the case of futex requeue PI, this will be a proxy ++ * lock. The task will wake unaware that it is enqueueed on ++ * this lock. Avoid blocking on two locks and corrupting ++ * pi_blocked_on via the PI_WAKEUP_INPROGRESS ++ * flag. futex_wait_requeue_pi() sets this when it wakes up ++ * before requeue (due to a signal or timeout). Do not enqueue ++ * the task if PI_WAKEUP_INPROGRESS is set. ++ */ ++ if (task != current && task->pi_blocked_on == PI_WAKEUP_INPROGRESS) { ++ raw_spin_unlock(&task->pi_lock); ++ return -EAGAIN; ++ } ++ ++ BUG_ON(rt_mutex_real_waiter(task->pi_blocked_on)); ++ + waiter->task = task; + waiter->lock = lock; + waiter->prio = task->prio; +@@ -974,7 +996,7 @@ static int task_blocks_on_rt_mutex(struc + rt_mutex_enqueue_pi(owner, waiter); + + rt_mutex_adjust_prio(owner); +- if (owner->pi_blocked_on) ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) + chain_walk = 1; + } else if (rt_mutex_cond_detect_deadlock(waiter, chwalk)) { + chain_walk = 1; +@@ -1070,7 +1092,7 @@ static void remove_waiter(struct rt_mute + { + bool is_top_waiter = (waiter == rt_mutex_top_waiter(lock)); + struct task_struct *owner = rt_mutex_owner(lock); +- struct rt_mutex *next_lock; ++ struct rt_mutex *next_lock = NULL; + + lockdep_assert_held(&lock->wait_lock); + +@@ -1096,7 +1118,8 @@ static void remove_waiter(struct rt_mute + rt_mutex_adjust_prio(owner); + + /* Store the lock on which owner is blocked or NULL */ +- next_lock = task_blocked_on_lock(owner); ++ if (rt_mutex_real_waiter(owner->pi_blocked_on)) ++ next_lock = task_blocked_on_lock(owner); + + raw_spin_unlock(&owner->pi_lock); + +@@ -1132,7 +1155,8 @@ void rt_mutex_adjust_pi(struct task_stru + raw_spin_lock_irqsave(&task->pi_lock, flags); + + waiter = task->pi_blocked_on; +- if (!waiter || rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { ++ if (!rt_mutex_real_waiter(waiter) || ++ rt_mutex_waiter_equal(waiter, task_to_waiter(task))) { + raw_spin_unlock_irqrestore(&task->pi_lock, flags); + return; + } +--- a/kernel/locking/rtmutex_common.h ++++ b/kernel/locking/rtmutex_common.h +@@ -130,6 +130,8 @@ enum rtmutex_chainwalk { + /* + * PI-futex support (proxy locking functions, etc.): + */ ++#define PI_WAKEUP_INPROGRESS ((struct rt_mutex_waiter *) 1) ++ + extern struct task_struct *rt_mutex_next_owner(struct rt_mutex *lock); + extern void rt_mutex_init_proxy_locked(struct rt_mutex *lock, + struct task_struct *proxy_owner); diff --git a/debian/patches/features/all/rt/rtmutex-lock-killable.patch b/debian/patches/features/all/rt/rtmutex-lock-killable.patch new file mode 100644 index 000000000..04bd0cc2e --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-lock-killable.patch @@ -0,0 +1,52 @@ +Subject: rtmutex: Add rtmutex_lock_killable() +From: Thomas Gleixner +Date: Thu, 09 Jun 2011 11:43:52 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Add "killable" type to rtmutex. We need this since rtmutex are used as +"normal" mutexes which do use this type. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rtmutex.h | 1 + + kernel/locking/rtmutex.c | 19 +++++++++++++++++++ + 2 files changed, 20 insertions(+) + +--- a/include/linux/rtmutex.h ++++ b/include/linux/rtmutex.h +@@ -115,6 +115,7 @@ extern void rt_mutex_lock(struct rt_mute + #endif + + extern int rt_mutex_lock_interruptible(struct rt_mutex *lock); ++extern int rt_mutex_lock_killable(struct rt_mutex *lock); + extern int rt_mutex_timed_lock(struct rt_mutex *lock, + struct hrtimer_sleeper *timeout); + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1563,6 +1563,25 @@ int __sched __rt_mutex_futex_trylock(str + } + + /** ++ * rt_mutex_lock_killable - lock a rt_mutex killable ++ * ++ * @lock: the rt_mutex to be locked ++ * @detect_deadlock: deadlock detection on/off ++ * ++ * Returns: ++ * 0 on success ++ * -EINTR when interrupted by a signal ++ * -EDEADLK when the lock would deadlock (when deadlock detection is on) ++ */ ++int __sched rt_mutex_lock_killable(struct rt_mutex *lock) ++{ ++ might_sleep(); ++ ++ return rt_mutex_fastlock(lock, TASK_KILLABLE, rt_mutex_slowlock); ++} ++EXPORT_SYMBOL_GPL(rt_mutex_lock_killable); ++ ++/** + * rt_mutex_timed_lock - lock a rt_mutex interruptible + * the timeout structure is provided + * by the caller diff --git a/debian/patches/features/all/rt/rtmutex-trylock-is-okay-on-RT.patch b/debian/patches/features/all/rt/rtmutex-trylock-is-okay-on-RT.patch new file mode 100644 index 000000000..9c4ede808 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-trylock-is-okay-on-RT.patch @@ -0,0 +1,28 @@ +From: Sebastian Andrzej Siewior +Date: Wed 02 Dec 2015 11:34:07 +0100 +Subject: rtmutex: trylock is okay on -RT +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +non-RT kernel could deadlock on rt_mutex_trylock() in softirq context. On +-RT we don't run softirqs in IRQ context but in thread context so it is +not a issue here. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/locking/rtmutex.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/kernel/locking/rtmutex.c ++++ b/kernel/locking/rtmutex.c +@@ -1583,7 +1583,11 @@ int __sched rt_mutex_trylock(struct rt_m + { + int ret; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (WARN_ON_ONCE(in_irq() || in_nmi())) ++#else + if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq())) ++#endif + return 0; + + ret = rt_mutex_fasttrylock(lock, rt_mutex_slowtrylock); diff --git a/debian/patches/features/all/rt/rtmutex-wire-up-RT-s-locking.patch b/debian/patches/features/all/rt/rtmutex-wire-up-RT-s-locking.patch new file mode 100644 index 000000000..fe047e9c2 --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex-wire-up-RT-s-locking.patch @@ -0,0 +1,251 @@ +From: Thomas Gleixner +Date: Thu, 12 Oct 2017 17:31:14 +0200 +Subject: rtmutex: wire up RT's locking +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/mutex.h | 20 +++++++++++++------- + include/linux/rwsem.h | 11 +++++++++++ + include/linux/spinlock.h | 12 +++++++++++- + include/linux/spinlock_api_smp.h | 4 +++- + include/linux/spinlock_types.h | 11 ++++++++--- + kernel/locking/Makefile | 9 ++++++++- + kernel/locking/spinlock.c | 7 +++++++ + kernel/locking/spinlock_debug.c | 5 +++++ + 8 files changed, 66 insertions(+), 13 deletions(-) + +--- a/include/linux/mutex.h ++++ b/include/linux/mutex.h +@@ -22,6 +22,17 @@ + + struct ww_acquire_ctx; + ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ ++ , .dep_map = { .name = #lockname } ++#else ++# define __DEP_MAP_MUTEX_INITIALIZER(lockname) ++#endif ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++ + /* + * Simple, straightforward mutexes with strict semantics: + * +@@ -118,13 +129,6 @@ do { \ + __mutex_init((mutex), #mutex, &__key); \ + } while (0) + +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) \ +- , .dep_map = { .name = #lockname } +-#else +-# define __DEP_MAP_MUTEX_INITIALIZER(lockname) +-#endif +- + #define __MUTEX_INITIALIZER(lockname) \ + { .owner = ATOMIC_LONG_INIT(0) \ + , .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \ +@@ -229,4 +233,6 @@ mutex_trylock_recursive(struct mutex *lo + return mutex_trylock(lock); + } + ++#endif /* !PREEMPT_RT_FULL */ ++ + #endif /* __LINUX_MUTEX_H */ +--- a/include/linux/rwsem.h ++++ b/include/linux/rwsem.h +@@ -20,6 +20,10 @@ + #include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++#include ++#else /* PREEMPT_RT_FULL */ ++ + struct rw_semaphore; + + #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK +@@ -114,6 +118,13 @@ static inline int rwsem_is_contended(str + return !list_empty(&sem->wait_list); + } + ++#endif /* !PREEMPT_RT_FULL */ ++ ++/* ++ * The functions below are the same for all rwsem implementations including ++ * the RT specific variant. ++ */ ++ + /* + * lock for reading + */ +--- a/include/linux/spinlock.h ++++ b/include/linux/spinlock.h +@@ -279,7 +279,11 @@ static inline void do_raw_spin_unlock(ra + }) + + /* Include rwlock functions */ +-#include ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else ++# include ++#endif + + /* + * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: +@@ -290,6 +294,10 @@ static inline void do_raw_spin_unlock(ra + # include + #endif + ++#ifdef CONFIG_PREEMPT_RT_FULL ++# include ++#else /* PREEMPT_RT_FULL */ ++ + /* + * Map the spin_lock functions to the raw variants for PREEMPT_RT=n + */ +@@ -410,6 +418,8 @@ static __always_inline int spin_is_conte + + #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) + ++#endif /* !PREEMPT_RT_FULL */ ++ + /* + * Pull the atomic_t declaration: + * (asm-mips/atomic.h needs above definitions) +--- a/include/linux/spinlock_api_smp.h ++++ b/include/linux/spinlock_api_smp.h +@@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh( + return 0; + } + +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_API_SMP_H */ +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -11,8 +11,13 @@ + + #include + +-#include +- +-#include ++#ifndef CONFIG_PREEMPT_RT_FULL ++# include ++# include ++#else ++# include ++# include ++# include ++#endif + + #endif /* __LINUX_SPINLOCK_TYPES_H */ +--- a/kernel/locking/Makefile ++++ b/kernel/locking/Makefile +@@ -3,7 +3,7 @@ + # and is generally not a function of system call inputs. + KCOV_INSTRUMENT := n + +-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o ++obj-y += semaphore.o percpu-rwsem.o + + ifdef CONFIG_FUNCTION_TRACER + CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE) +@@ -12,7 +12,11 @@ CFLAGS_REMOVE_mutex-debug.o = $(CC_FLAGS + CFLAGS_REMOVE_rtmutex-debug.o = $(CC_FLAGS_FTRACE) + endif + ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) ++obj-y += mutex.o + obj-$(CONFIG_DEBUG_MUTEXES) += mutex-debug.o ++endif ++obj-y += rwsem.o + obj-$(CONFIG_LOCKDEP) += lockdep.o + ifeq ($(CONFIG_PROC_FS),y) + obj-$(CONFIG_LOCKDEP) += lockdep_proc.o +@@ -25,8 +29,11 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o + obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o + obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o ++ifneq ($(CONFIG_PREEMPT_RT_FULL),y) + obj-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o + obj-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem-xadd.o ++endif ++obj-$(CONFIG_PREEMPT_RT_FULL) += mutex-rt.o rwsem-rt.o rwlock-rt.o + obj-$(CONFIG_QUEUED_RWLOCKS) += qrwlock.o + obj-$(CONFIG_LOCK_TORTURE_TEST) += locktorture.o + obj-$(CONFIG_WW_MUTEX_SELFTEST) += test-ww_mutex.o +--- a/kernel/locking/spinlock.c ++++ b/kernel/locking/spinlock.c +@@ -117,8 +117,11 @@ void __lockfunc __raw_##op##_lock_bh(loc + * __[spin|read|write]_lock_bh() + */ + BUILD_LOCK_OPS(spin, raw_spinlock); ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + BUILD_LOCK_OPS(read, rwlock); + BUILD_LOCK_OPS(write, rwlock); ++#endif + + #endif + +@@ -202,6 +205,8 @@ void __lockfunc _raw_spin_unlock_bh(raw_ + EXPORT_SYMBOL(_raw_spin_unlock_bh); + #endif + ++#ifndef CONFIG_PREEMPT_RT_FULL ++ + #ifndef CONFIG_INLINE_READ_TRYLOCK + int __lockfunc _raw_read_trylock(rwlock_t *lock) + { +@@ -346,6 +351,8 @@ void __lockfunc _raw_write_unlock_bh(rwl + EXPORT_SYMBOL(_raw_write_unlock_bh); + #endif + ++#endif /* !PREEMPT_RT_FULL */ ++ + #ifdef CONFIG_DEBUG_LOCK_ALLOC + + void __lockfunc _raw_spin_lock_nested(raw_spinlock_t *lock, int subclass) +--- a/kernel/locking/spinlock_debug.c ++++ b/kernel/locking/spinlock_debug.c +@@ -31,6 +31,7 @@ void __raw_spin_lock_init(raw_spinlock_t + + EXPORT_SYMBOL(__raw_spin_lock_init); + ++#ifndef CONFIG_PREEMPT_RT_FULL + void __rwlock_init(rwlock_t *lock, const char *name, + struct lock_class_key *key) + { +@@ -48,6 +49,7 @@ void __rwlock_init(rwlock_t *lock, const + } + + EXPORT_SYMBOL(__rwlock_init); ++#endif + + static void spin_dump(raw_spinlock_t *lock, const char *msg) + { +@@ -135,6 +137,7 @@ void do_raw_spin_unlock(raw_spinlock_t * + arch_spin_unlock(&lock->raw_lock); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + static void rwlock_bug(rwlock_t *lock, const char *msg) + { + if (!debug_locks_off()) +@@ -224,3 +227,5 @@ void do_raw_write_unlock(rwlock_t *lock) + debug_write_unlock(lock); + arch_write_unlock(&lock->raw_lock); + } ++ ++#endif diff --git a/debian/patches/features/all/rt/rtmutex_dont_include_rcu.patch b/debian/patches/features/all/rt/rtmutex_dont_include_rcu.patch new file mode 100644 index 000000000..f31380dcd --- /dev/null +++ b/debian/patches/features/all/rt/rtmutex_dont_include_rcu.patch @@ -0,0 +1,159 @@ +From: Sebastian Andrzej Siewior +Subject: rbtree: don't include the rcu header +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The RCU header pulls in spinlock.h and fails due not yet defined types: + +|In file included from include/linux/spinlock.h:275:0, +| from include/linux/rcupdate.h:38, +| from include/linux/rbtree.h:34, +| from include/linux/rtmutex.h:17, +| from include/linux/spinlock_types.h:18, +| from kernel/bounds.c:13: +|include/linux/rwlock_rt.h:16:38: error: unknown type name ‘rwlock_t’ +| extern void __lockfunc rt_write_lock(rwlock_t *rwlock); +| ^ + +This patch moves the required RCU function from the rcupdate.h header file into +a new header file which can be included by both users. + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/rbtree.h | 2 - + include/linux/rcu_assign_pointer.h | 54 +++++++++++++++++++++++++++++++++++++ + include/linux/rcupdate.h | 49 --------------------------------- + 3 files changed, 56 insertions(+), 49 deletions(-) + +--- a/include/linux/rbtree.h ++++ b/include/linux/rbtree.h +@@ -31,7 +31,7 @@ + + #include + #include +-#include ++#include + + struct rb_node { + unsigned long __rb_parent_color; +--- /dev/null ++++ b/include/linux/rcu_assign_pointer.h +@@ -0,0 +1,54 @@ ++#ifndef __LINUX_RCU_ASSIGN_POINTER_H__ ++#define __LINUX_RCU_ASSIGN_POINTER_H__ ++#include ++#include ++ ++/** ++ * RCU_INITIALIZER() - statically initialize an RCU-protected global variable ++ * @v: The value to statically initialize with. ++ */ ++#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) ++ ++/** ++ * rcu_assign_pointer() - assign to RCU-protected pointer ++ * @p: pointer to assign to ++ * @v: value to assign (publish) ++ * ++ * Assigns the specified value to the specified RCU-protected ++ * pointer, ensuring that any concurrent RCU readers will see ++ * any prior initialization. ++ * ++ * Inserts memory barriers on architectures that require them ++ * (which is most of them), and also prevents the compiler from ++ * reordering the code that initializes the structure after the pointer ++ * assignment. More importantly, this call documents which pointers ++ * will be dereferenced by RCU read-side code. ++ * ++ * In some special cases, you may use RCU_INIT_POINTER() instead ++ * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due ++ * to the fact that it does not constrain either the CPU or the compiler. ++ * That said, using RCU_INIT_POINTER() when you should have used ++ * rcu_assign_pointer() is a very bad thing that results in ++ * impossible-to-diagnose memory corruption. So please be careful. ++ * See the RCU_INIT_POINTER() comment header for details. ++ * ++ * Note that rcu_assign_pointer() evaluates each of its arguments only ++ * once, appearances notwithstanding. One of the "extra" evaluations ++ * is in typeof() and the other visible only to sparse (__CHECKER__), ++ * neither of which actually execute the argument. As with most cpp ++ * macros, this execute-arguments-only-once property is important, so ++ * please be careful when making changes to rcu_assign_pointer() and the ++ * other macros that it invokes. ++ */ ++#define rcu_assign_pointer(p, v) \ ++({ \ ++ uintptr_t _r_a_p__v = (uintptr_t)(v); \ ++ \ ++ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ ++ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ ++ else \ ++ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ ++ _r_a_p__v; \ ++}) ++ ++#endif +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -42,6 +42,7 @@ + #include + #include + #include ++#include + + #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) + #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) +@@ -373,54 +374,6 @@ static inline void rcu_preempt_sleep_che + }) + + /** +- * RCU_INITIALIZER() - statically initialize an RCU-protected global variable +- * @v: The value to statically initialize with. +- */ +-#define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) +- +-/** +- * rcu_assign_pointer() - assign to RCU-protected pointer +- * @p: pointer to assign to +- * @v: value to assign (publish) +- * +- * Assigns the specified value to the specified RCU-protected +- * pointer, ensuring that any concurrent RCU readers will see +- * any prior initialization. +- * +- * Inserts memory barriers on architectures that require them +- * (which is most of them), and also prevents the compiler from +- * reordering the code that initializes the structure after the pointer +- * assignment. More importantly, this call documents which pointers +- * will be dereferenced by RCU read-side code. +- * +- * In some special cases, you may use RCU_INIT_POINTER() instead +- * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due +- * to the fact that it does not constrain either the CPU or the compiler. +- * That said, using RCU_INIT_POINTER() when you should have used +- * rcu_assign_pointer() is a very bad thing that results in +- * impossible-to-diagnose memory corruption. So please be careful. +- * See the RCU_INIT_POINTER() comment header for details. +- * +- * Note that rcu_assign_pointer() evaluates each of its arguments only +- * once, appearances notwithstanding. One of the "extra" evaluations +- * is in typeof() and the other visible only to sparse (__CHECKER__), +- * neither of which actually execute the argument. As with most cpp +- * macros, this execute-arguments-only-once property is important, so +- * please be careful when making changes to rcu_assign_pointer() and the +- * other macros that it invokes. +- */ +-#define rcu_assign_pointer(p, v) \ +-({ \ +- uintptr_t _r_a_p__v = (uintptr_t)(v); \ +- \ +- if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ +- WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ +- else \ +- smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ +- _r_a_p__v; \ +-}) +- +-/** + * rcu_swap_protected() - swap an RCU and a regular pointer + * @rcu_ptr: RCU pointer + * @ptr: regular pointer diff --git a/debian/patches/features/all/rt/sched-core-Remove-get_cpu-from-sched_fork.patch b/debian/patches/features/all/rt/sched-core-Remove-get_cpu-from-sched_fork.patch new file mode 100644 index 000000000..9af98350b --- /dev/null +++ b/debian/patches/features/all/rt/sched-core-Remove-get_cpu-from-sched_fork.patch @@ -0,0 +1,88 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 6 Jul 2018 15:06:15 +0200 +Subject: [PATCH] sched/core: Remove get_cpu() from sched_fork() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +[ Upstream commit af0fffd9300b97d8875aa745bc78e2f6fdb3c1f0 ] + +get_cpu() disables preemption for the entire sched_fork() function. +This get_cpu() was introduced in commit: + + dd41f596cda0 ("sched: cfs core code") + +... which also invoked sched_balance_self() and this function +required preemption do be off. + +Today, sched_balance_self() seems to be moved to ->task_fork callback +which is invoked while the ->pi_lock is held. + +set_load_weight() could invoke reweight_task() which then via $callchain +might end up in smp_processor_id() but since `update_load' is false +this won't happen. + +I didn't find any this_cpu*() or similar usage during the initialisation +of the task_struct. + +The `cpu' value (from get_cpu()) is only used later in __set_task_cpu() +while the ->pi_lock lock is held. + +Based on this it is possible to remove get_cpu() and use +smp_processor_id() for the `cpu' variable without breaking anything. + +Signed-off-by: Sebastian Andrzej Siewior +Signed-off-by: Peter Zijlstra (Intel) +Cc: Linus Torvalds +Cc: Peter Zijlstra +Cc: Thomas Gleixner +Link: http://lkml.kernel.org/r/20180706130615.g2ex2kmfu5kcvlq6@linutronix.de +Signed-off-by: Ingo Molnar +--- + kernel/sched/core.c | 13 ++++--------- + 1 file changed, 4 insertions(+), 9 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2317,7 +2317,6 @@ static inline void init_schedstats(void) + int sched_fork(unsigned long clone_flags, struct task_struct *p) + { + unsigned long flags; +- int cpu = get_cpu(); + + __sched_fork(clone_flags, p); + /* +@@ -2353,14 +2352,12 @@ int sched_fork(unsigned long clone_flags + p->sched_reset_on_fork = 0; + } + +- if (dl_prio(p->prio)) { +- put_cpu(); ++ if (dl_prio(p->prio)) + return -EAGAIN; +- } else if (rt_prio(p->prio)) { ++ else if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; +- } else { ++ else + p->sched_class = &fair_sched_class; +- } + + init_entity_runnable_average(&p->se); + +@@ -2376,7 +2373,7 @@ int sched_fork(unsigned long clone_flags + * We're setting the CPU for the first time, we don't migrate, + * so use __set_task_cpu(). + */ +- __set_task_cpu(p, cpu); ++ __set_task_cpu(p, smp_processor_id()); + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); +@@ -2393,8 +2390,6 @@ int sched_fork(unsigned long clone_flags + plist_node_init(&p->pushable_tasks, MAX_PRIO); + RB_CLEAR_NODE(&p->pushable_dl_tasks); + #endif +- +- put_cpu(); + return 0; + } + diff --git a/debian/patches/features/all/rt/sched-delay-put-task.patch b/debian/patches/features/all/rt/sched-delay-put-task.patch new file mode 100644 index 000000000..c6ce581a9 --- /dev/null +++ b/debian/patches/features/all/rt/sched-delay-put-task.patch @@ -0,0 +1,86 @@ +Subject: sched: Move task_struct cleanup to RCU +From: Thomas Gleixner +Date: Tue, 31 May 2011 16:59:16 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +__put_task_struct() does quite some expensive work. We don't want to +burden random tasks with that. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 3 +++ + include/linux/sched/task.h | 11 ++++++++++- + kernel/fork.c | 15 ++++++++++++++- + 3 files changed, 27 insertions(+), 2 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1173,6 +1173,9 @@ struct task_struct { + unsigned int sequential_io; + unsigned int sequential_io_avg; + #endif ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head put_rcu; ++#endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; + #endif +--- a/include/linux/sched/task.h ++++ b/include/linux/sched/task.h +@@ -88,6 +88,15 @@ extern void sched_exec(void); + + #define get_task_struct(tsk) do { atomic_inc(&(tsk)->usage); } while(0) + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __put_task_struct_cb(struct rcu_head *rhp); ++ ++static inline void put_task_struct(struct task_struct *t) ++{ ++ if (atomic_dec_and_test(&t->usage)) ++ call_rcu(&t->put_rcu, __put_task_struct_cb); ++} ++#else + extern void __put_task_struct(struct task_struct *t); + + static inline void put_task_struct(struct task_struct *t) +@@ -95,7 +104,7 @@ static inline void put_task_struct(struc + if (atomic_dec_and_test(&t->usage)) + __put_task_struct(t); + } +- ++#endif + struct task_struct *task_rcu_dereference(struct task_struct **ptask); + + #ifdef CONFIG_ARCH_WANTS_DYNAMIC_TASK_STRUCT +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -671,7 +671,9 @@ static inline void put_signal_struct(str + if (atomic_dec_and_test(&sig->sigcnt)) + free_signal_struct(sig); + } +- ++#ifdef CONFIG_PREEMPT_RT_BASE ++static ++#endif + void __put_task_struct(struct task_struct *tsk) + { + WARN_ON(!tsk->exit_state); +@@ -688,7 +690,18 @@ void __put_task_struct(struct task_struc + if (!profile_handoff_task(tsk)) + free_task(tsk); + } ++#ifndef CONFIG_PREEMPT_RT_BASE + EXPORT_SYMBOL_GPL(__put_task_struct); ++#else ++void __put_task_struct_cb(struct rcu_head *rhp) ++{ ++ struct task_struct *tsk = container_of(rhp, struct task_struct, put_rcu); ++ ++ __put_task_struct(tsk); ++ ++} ++EXPORT_SYMBOL_GPL(__put_task_struct_cb); ++#endif + + void __init __weak arch_task_cache_init(void) { } + diff --git a/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch b/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch new file mode 100644 index 000000000..9ae98b7e6 --- /dev/null +++ b/debian/patches/features/all/rt/sched-disable-rt-group-sched-on-rt.patch @@ -0,0 +1,29 @@ +Subject: sched: Disable CONFIG_RT_GROUP_SCHED on RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 17:03:52 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Carsten reported problems when running: + + taskset 01 chrt -f 1 sleep 1 + +from within rc.local on a F15 machine. The task stays running and +never gets on the run queue because some of the run queues have +rt_throttled=1 which does not go away. Works nice from a ssh login +shell. Disabling CONFIG_RT_GROUP_SCHED solves that as well. + +Signed-off-by: Thomas Gleixner +--- + init/Kconfig | 1 + + 1 file changed, 1 insertion(+) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -741,6 +741,7 @@ config CFS_BANDWIDTH + config RT_GROUP_SCHED + bool "Group scheduling for SCHED_RR/FIFO" + depends on CGROUP_SCHED ++ depends on !PREEMPT_RT_FULL + default n + help + This feature lets you explicitly allocate real CPU bandwidth diff --git a/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch b/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch new file mode 100644 index 000000000..a4831598b --- /dev/null +++ b/debian/patches/features/all/rt/sched-disable-ttwu-queue.patch @@ -0,0 +1,32 @@ +Subject: sched: Disable TTWU_QUEUE on RT +From: Thomas Gleixner +Date: Tue, 13 Sep 2011 16:42:35 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The queued remote wakeup mechanism can introduce rather large +latencies if the number of migrated tasks is high. Disable it for RT. + +Signed-off-by: Thomas Gleixner +--- + kernel/sched/features.h | 5 +++++ + 1 file changed, 5 insertions(+) + +--- a/kernel/sched/features.h ++++ b/kernel/sched/features.h +@@ -46,11 +46,16 @@ SCHED_FEAT(LB_BIAS, true) + */ + SCHED_FEAT(NONTASK_CAPACITY, true) + ++#ifdef CONFIG_PREEMPT_RT_FULL ++SCHED_FEAT(TTWU_QUEUE, false) ++#else ++ + /* + * Queue remote wakeups on the target CPU and process them + * using the scheduler IPI. Reduces rq->lock contention/bounces. + */ + SCHED_FEAT(TTWU_QUEUE, true) ++#endif + + /* + * When doing wakeups, attempt to limit superfluous scans of the LLC domain. diff --git a/debian/patches/features/all/rt/sched-limit-nr-migrate.patch b/debian/patches/features/all/rt/sched-limit-nr-migrate.patch new file mode 100644 index 000000000..693b016b9 --- /dev/null +++ b/debian/patches/features/all/rt/sched-limit-nr-migrate.patch @@ -0,0 +1,27 @@ +Subject: sched: Limit the number of task migrations per batch +From: Thomas Gleixner +Date: Mon, 06 Jun 2011 12:12:51 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Put an upper limit on the number of tasks which are migrated per batch +to avoid large latencies. + +Signed-off-by: Thomas Gleixner +--- + kernel/sched/core.c | 4 ++++ + 1 file changed, 4 insertions(+) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -42,7 +42,11 @@ const_debug unsigned int sysctl_sched_fe + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + const_debug unsigned int sysctl_sched_nr_migrate = 32; ++#else ++const_debug unsigned int sysctl_sched_nr_migrate = 8; ++#endif + + /* + * period over which we average the RT time consumption, measured diff --git a/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch b/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch new file mode 100644 index 000000000..9bff36c6a --- /dev/null +++ b/debian/patches/features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch @@ -0,0 +1,48 @@ +Subject: sched: Do not account rcu_preempt_depth on RT in might_sleep() +From: Thomas Gleixner +Date: Tue, 07 Jun 2011 09:19:06 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +RT changes the rcu_preempt_depth semantics, so we cannot check for it +in might_sleep(). + +Signed-off-by: Thomas Gleixner +--- + include/linux/rcupdate.h | 7 +++++++ + kernel/sched/core.c | 2 +- + 2 files changed, 8 insertions(+), 1 deletion(-) + +--- a/include/linux/rcupdate.h ++++ b/include/linux/rcupdate.h +@@ -74,6 +74,11 @@ void synchronize_rcu(void); + * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. + */ + #define rcu_preempt_depth() (current->rcu_read_lock_nesting) ++#ifndef CONFIG_PREEMPT_RT_FULL ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++#else ++static inline int sched_rcu_preempt_depth(void) { return 0; } ++#endif + + #else /* #ifdef CONFIG_PREEMPT_RCU */ + +@@ -99,6 +104,8 @@ static inline int rcu_preempt_depth(void + return 0; + } + ++#define sched_rcu_preempt_depth() rcu_preempt_depth() ++ + #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ + + /* Internal to kernel */ +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -6187,7 +6187,7 @@ void __init sched_init(void) + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + static inline int preempt_count_equals(int preempt_offset) + { +- int nested = preempt_count() + rcu_preempt_depth(); ++ int nested = preempt_count() + sched_rcu_preempt_depth(); + + return (nested == preempt_offset); + } diff --git a/debian/patches/features/all/rt/sched-migrate_disable-fallback-to-preempt_disable-in.patch b/debian/patches/features/all/rt/sched-migrate_disable-fallback-to-preempt_disable-in.patch new file mode 100644 index 000000000..74bf5261b --- /dev/null +++ b/debian/patches/features/all/rt/sched-migrate_disable-fallback-to-preempt_disable-in.patch @@ -0,0 +1,192 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 5 Jul 2018 14:44:51 +0200 +Subject: [PATCH] sched/migrate_disable: fallback to preempt_disable() instead + barrier() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On SMP + !RT migrate_disable() is still around. It is not part of spin_lock() +anymore so it has almost no users. However the futex code has a workaround for +the !in_atomic() part of migrate disable which fails because the matching +migrade_disable() is no longer part of spin_lock(). + +On !SMP + !RT migrate_disable() is reduced to barrier(). This is not optimal +because we few spots where a "preempt_disable()" statement was replaced with +"migrate_disable()". + +We also used the migration_disable counter to figure out if a sleeping lock is +acquired so RCU does not complain about schedule() during rcu_read_lock() while +a sleeping lock is held. This changed, we no longer use it, we have now a +sleeping_lock counter for the RCU purpose. + +This means we can now: +- for SMP + RT_BASE + full migration program, nothing changes here + +- for !SMP + RT_BASE + the migration counting is no longer required. It used to ensure that the task + is not migrated to another CPU and that this CPU remains online. !SMP ensures + that already. + Move it to CONFIG_SCHED_DEBUG so the counting is done for debugging purpose + only. + +- for all other cases including !RT + fallback to preempt_disable(). The only remaining users of migrate_disable() + are those which were converted from preempt_disable() and the futex + workaround which is already in the preempt_disable() section due to the + spin_lock that is held. + +Cc: stable-rt@vger.kernel.org +Reported-by: joe.korty@concurrent-rt.com +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/preempt.h | 6 +++--- + include/linux/sched.h | 4 ++-- + kernel/sched/core.c | 23 +++++++++++------------ + kernel/sched/debug.c | 2 +- + 4 files changed, 17 insertions(+), 18 deletions(-) + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -204,7 +204,7 @@ do { \ + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + + extern void migrate_disable(void); + extern void migrate_enable(void); +@@ -221,8 +221,8 @@ static inline int __migrate_disabled(str + } + + #else +-#define migrate_disable() barrier() +-#define migrate_enable() barrier() ++#define migrate_disable() preempt_disable() ++#define migrate_enable() preempt_enable() + static inline int __migrate_disabled(struct task_struct *p) + { + return 0; +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -667,7 +667,7 @@ struct task_struct { + int nr_cpus_allowed; + const cpumask_t *cpus_ptr; + cpumask_t cpus_mask; +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int migrate_disable; + int migrate_disable_update; + # ifdef CONFIG_SCHED_DEBUG +@@ -675,8 +675,8 @@ struct task_struct { + # endif + + #elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) +- int migrate_disable; + # ifdef CONFIG_SCHED_DEBUG ++ int migrate_disable; + int migrate_disable_atomic; + # endif + #endif +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1053,7 +1053,7 @@ void set_cpus_allowed_common(struct task + p->nr_cpus_allowed = cpumask_weight(new_mask); + } + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + int __migrate_disabled(struct task_struct *p) + { + return p->migrate_disable; +@@ -1092,7 +1092,7 @@ static void __do_set_cpus_allowed_tail(s + + void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) + { +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + lockdep_assert_held(&p->pi_lock); + +@@ -1165,7 +1165,7 @@ static int __set_cpus_allowed_ptr(struct + if (cpumask_test_cpu(task_cpu(p), new_mask) || __migrate_disabled(p)) + goto out; + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + if (__migrate_disabled(p)) { + p->migrate_disable_update = 1; + goto out; +@@ -7186,7 +7186,7 @@ const u32 sched_prio_to_wmult[40] = { + + #undef CREATE_TRACE_POINTS + +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + + static inline void + update_nr_migratory(struct task_struct *p, long delta) +@@ -7334,45 +7334,44 @@ EXPORT_SYMBOL(migrate_enable); + #elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + void migrate_disable(void) + { ++#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +-#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic++; +-#endif + return; + } +-#ifdef CONFIG_SCHED_DEBUG ++ + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +-#endif + + p->migrate_disable++; ++#endif ++ barrier(); + } + EXPORT_SYMBOL(migrate_disable); + + void migrate_enable(void) + { ++#ifdef CONFIG_SCHED_DEBUG + struct task_struct *p = current; + + if (in_atomic() || irqs_disabled()) { +-#ifdef CONFIG_SCHED_DEBUG + p->migrate_disable_atomic--; +-#endif + return; + } + +-#ifdef CONFIG_SCHED_DEBUG + if (unlikely(p->migrate_disable_atomic)) { + tracing_off(); + WARN_ON_ONCE(1); + } +-#endif + + WARN_ON_ONCE(p->migrate_disable <= 0); + p->migrate_disable--; ++#endif ++ barrier(); + } + EXPORT_SYMBOL(migrate_enable); + #endif +--- a/kernel/sched/debug.c ++++ b/kernel/sched/debug.c +@@ -979,7 +979,7 @@ void proc_sched_show_task(struct task_st + P(dl.runtime); + P(dl.deadline); + } +-#if defined(CONFIG_PREEMPT_COUNT) && defined(CONFIG_SMP) ++#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE) + P(migrate_disable); + #endif + P(nr_cpus_allowed); diff --git a/debian/patches/features/all/rt/sched-mmdrop-delayed.patch b/debian/patches/features/all/rt/sched-mmdrop-delayed.patch new file mode 100644 index 000000000..e2099b557 --- /dev/null +++ b/debian/patches/features/all/rt/sched-mmdrop-delayed.patch @@ -0,0 +1,128 @@ +Subject: sched: Move mmdrop to RCU on RT +From: Thomas Gleixner +Date: Mon, 06 Jun 2011 12:20:33 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Takes sleeping locks and calls into the memory allocator, so nothing +we want to do in task switch and oder atomic contexts. + +Signed-off-by: Thomas Gleixner +--- + include/linux/mm_types.h | 4 ++++ + include/linux/sched/mm.h | 11 +++++++++++ + kernel/fork.c | 13 +++++++++++++ + kernel/sched/core.c | 18 ++++++++++++++++-- + 4 files changed, 44 insertions(+), 2 deletions(-) + +--- a/include/linux/mm_types.h ++++ b/include/linux/mm_types.h +@@ -12,6 +12,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -480,6 +481,9 @@ struct mm_struct { + bool tlb_flush_batched; + #endif + struct uprobes_state uprobes_state; ++#ifdef CONFIG_PREEMPT_RT_BASE ++ struct rcu_head delayed_drop; ++#endif + #ifdef CONFIG_HUGETLB_PAGE + atomic_long_t hugetlb_usage; + #endif +--- a/include/linux/sched/mm.h ++++ b/include/linux/sched/mm.h +@@ -49,6 +49,17 @@ static inline void mmdrop(struct mm_stru + __mmdrop(mm); + } + ++#ifdef CONFIG_PREEMPT_RT_BASE ++extern void __mmdrop_delayed(struct rcu_head *rhp); ++static inline void mmdrop_delayed(struct mm_struct *mm) ++{ ++ if (atomic_dec_and_test(&mm->mm_count)) ++ call_rcu(&mm->delayed_drop, __mmdrop_delayed); ++} ++#else ++# define mmdrop_delayed(mm) mmdrop(mm) ++#endif ++ + /** + * mmget() - Pin the address space associated with a &struct mm_struct. + * @mm: The address space to pin. +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -637,6 +637,19 @@ void __mmdrop(struct mm_struct *mm) + } + EXPORT_SYMBOL_GPL(__mmdrop); + ++#ifdef CONFIG_PREEMPT_RT_BASE ++/* ++ * RCU callback for delayed mm drop. Not strictly rcu, but we don't ++ * want another facility to make this work. ++ */ ++void __mmdrop_delayed(struct rcu_head *rhp) ++{ ++ struct mm_struct *mm = container_of(rhp, struct mm_struct, delayed_drop); ++ ++ __mmdrop(mm); ++} ++#endif ++ + static void mmdrop_async_fn(struct work_struct *work) + { + struct mm_struct *mm; +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2752,9 +2752,13 @@ static struct rq *finish_task_switch(str + * provided by mmdrop(), + * - a sync_core for SYNC_CORE. + */ ++ /* ++ * We use mmdrop_delayed() here so we don't have to do the ++ * full __mmdrop() when we are the last user. ++ */ + if (mm) { + membarrier_mm_sync_core_before_usermode(mm); +- mmdrop(mm); ++ mmdrop_delayed(mm); + } + if (unlikely(prev_state == TASK_DEAD)) { + if (prev->sched_class->task_dead) +@@ -5580,6 +5584,8 @@ void sched_setnuma(struct task_struct *p + #endif /* CONFIG_NUMA_BALANCING */ + + #ifdef CONFIG_HOTPLUG_CPU ++static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm); ++ + /* + * Ensure that the idle task is using init_mm right before its CPU goes + * offline. +@@ -5595,7 +5601,11 @@ void idle_task_exit(void) + current->active_mm = &init_mm; + finish_arch_post_lock_switch(); + } +- mmdrop(mm); ++ /* ++ * Defer the cleanup to an alive cpu. On RT we can neither ++ * call mmdrop() nor mmdrop_delayed() from here. ++ */ ++ per_cpu(idle_last_mm, smp_processor_id()) = mm; + } + + /* +@@ -5900,6 +5910,10 @@ int sched_cpu_dying(unsigned int cpu) + update_max_interval(); + nohz_balance_exit_idle(rq); + hrtick_clear(rq); ++ if (per_cpu(idle_last_mm, cpu)) { ++ mmdrop_delayed(per_cpu(idle_last_mm, cpu)); ++ per_cpu(idle_last_mm, cpu) = NULL; ++ } + return 0; + } + #endif diff --git a/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch b/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch new file mode 100644 index 000000000..82f819fdd --- /dev/null +++ b/debian/patches/features/all/rt/sched-rt-mutex-wakeup.patch @@ -0,0 +1,97 @@ +Subject: sched: Add saved_state for tasks blocked on sleeping locks +From: Thomas Gleixner +Date: Sat, 25 Jun 2011 09:21:04 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Spinlocks are state preserving in !RT. RT changes the state when a +task gets blocked on a lock. So we need to remember the state before +the lock contention. If a regular wakeup (not a RTmutex related +wakeup) happens, the saved_state is updated to running. When the lock +sleep is done, the saved state is restored. + +Signed-off-by: Thomas Gleixner +--- + include/linux/sched.h | 3 +++ + kernel/sched/core.c | 33 ++++++++++++++++++++++++++++++++- + kernel/sched/sched.h | 1 + + 3 files changed, 36 insertions(+), 1 deletion(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -600,6 +600,8 @@ struct task_struct { + #endif + /* -1 unrunnable, 0 runnable, >0 stopped: */ + volatile long state; ++ /* saved state for "spinlock sleepers" */ ++ volatile long saved_state; + + /* + * This begins the randomizable portion of task_struct. Only +@@ -1611,6 +1613,7 @@ extern struct task_struct *find_get_task + + extern int wake_up_state(struct task_struct *tsk, unsigned int state); + extern int wake_up_process(struct task_struct *tsk); ++extern int wake_up_lock_sleeper(struct task_struct *tsk); + extern void wake_up_new_task(struct task_struct *tsk); + + #ifdef CONFIG_SMP +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -2022,8 +2022,27 @@ try_to_wake_up(struct task_struct *p, un + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + smp_mb__after_spinlock(); +- if (!(p->state & state)) ++ if (!(p->state & state)) { ++ /* ++ * The task might be running due to a spinlock sleeper ++ * wakeup. Check the saved state and set it to running ++ * if the wakeup condition is true. ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) { ++ if (p->saved_state & state) { ++ p->saved_state = TASK_RUNNING; ++ success = 1; ++ } ++ } + goto out; ++ } ++ ++ /* ++ * If this is a regular wakeup, then we can unconditionally ++ * clear the saved state of a "lock sleeper". ++ */ ++ if (!(wake_flags & WF_LOCK_SLEEPER)) ++ p->saved_state = TASK_RUNNING; + + trace_sched_waking(p); + +@@ -2187,6 +2206,18 @@ int wake_up_process(struct task_struct * + } + EXPORT_SYMBOL(wake_up_process); + ++/** ++ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock" ++ * @p: The process to be woken up. ++ * ++ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate ++ * the nature of the wakeup. ++ */ ++int wake_up_lock_sleeper(struct task_struct *p) ++{ ++ return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER); ++} ++ + int wake_up_state(struct task_struct *p, unsigned int state) + { + return try_to_wake_up(p, state, 0); +--- a/kernel/sched/sched.h ++++ b/kernel/sched/sched.h +@@ -1418,6 +1418,7 @@ static inline int task_on_rq_migrating(s + #define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */ + #define WF_FORK 0x02 /* Child wakeup after fork */ + #define WF_MIGRATED 0x4 /* Internal use, task got migrated */ ++#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */ + + /* + * To aid in avoiding the subversion of "niceness" due to uneven distribution diff --git a/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch b/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch new file mode 100644 index 000000000..47edd60ad --- /dev/null +++ b/debian/patches/features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch @@ -0,0 +1,38 @@ +From: Steven Rostedt +Date: Mon, 18 Mar 2013 15:12:49 -0400 +Subject: sched/workqueue: Only wake up idle workers if not blocked on sleeping spin lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +In -rt, most spin_locks() turn into mutexes. One of these spin_lock +conversions is performed on the workqueue gcwq->lock. When the idle +worker is worken, the first thing it will do is grab that same lock and +it too will block, possibly jumping into the same code, but because +nr_running would already be decremented it prevents an infinite loop. + +But this is still a waste of CPU cycles, and it doesn't follow the method +of mainline, as new workers should only be woken when a worker thread is +truly going to sleep, and not just blocked on a spin_lock(). + +Check the saved_state too before waking up new workers. + + +Signed-off-by: Steven Rostedt +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/sched/core.c | 4 +++- + 1 file changed, 3 insertions(+), 1 deletion(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3519,8 +3519,10 @@ static void __sched notrace __schedule(b + * If a worker went to sleep, notify and ask workqueue + * whether it wants to wake up a task to maintain + * concurrency. ++ * Only call wake up if prev isn't blocked on a sleeping ++ * spin lock. + */ +- if (prev->flags & PF_WQ_WORKER) { ++ if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev); diff --git a/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch b/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch new file mode 100644 index 000000000..26d0b076e --- /dev/null +++ b/debian/patches/features/all/rt/scsi-fcoe-rt-aware.patch @@ -0,0 +1,106 @@ +Subject: scsi/fcoe: Make RT aware. +From: Thomas Gleixner +Date: Sat, 12 Nov 2011 14:00:48 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Do not disable preemption while taking sleeping locks. All user look safe +for migrate_diable() only. + +Signed-off-by: Thomas Gleixner +--- + drivers/scsi/fcoe/fcoe.c | 16 ++++++++-------- + drivers/scsi/fcoe/fcoe_ctlr.c | 4 ++-- + drivers/scsi/libfc/fc_exch.c | 4 ++-- + 3 files changed, 12 insertions(+), 12 deletions(-) + +--- a/drivers/scsi/fcoe/fcoe.c ++++ b/drivers/scsi/fcoe/fcoe.c +@@ -1459,11 +1459,11 @@ static int fcoe_rcv(struct sk_buff *skb, + static int fcoe_alloc_paged_crc_eof(struct sk_buff *skb, int tlen) + { + struct fcoe_percpu_s *fps; +- int rc; ++ int rc, cpu = get_cpu_light(); + +- fps = &get_cpu_var(fcoe_percpu); ++ fps = &per_cpu(fcoe_percpu, cpu); + rc = fcoe_get_paged_crc_eof(skb, tlen, fps); +- put_cpu_var(fcoe_percpu); ++ put_cpu_light(); + + return rc; + } +@@ -1650,11 +1650,11 @@ static inline int fcoe_filter_frames(str + return 0; + } + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + stats->InvalidCRCCount++; + if (stats->InvalidCRCCount < 5) + printk(KERN_WARNING "fcoe: dropping frame with CRC error\n"); +- put_cpu(); ++ put_cpu_light(); + return -EINVAL; + } + +@@ -1697,7 +1697,7 @@ static void fcoe_recv_frame(struct sk_bu + */ + hp = (struct fcoe_hdr *) skb_network_header(skb); + +- stats = per_cpu_ptr(lport->stats, get_cpu()); ++ stats = per_cpu_ptr(lport->stats, get_cpu_light()); + if (unlikely(FC_FCOE_DECAPS_VER(hp) != FC_FCOE_VER)) { + if (stats->ErrorFrames < 5) + printk(KERN_WARNING "fcoe: FCoE version " +@@ -1729,13 +1729,13 @@ static void fcoe_recv_frame(struct sk_bu + goto drop; + + if (!fcoe_filter_frames(lport, fp)) { +- put_cpu(); ++ put_cpu_light(); + fc_exch_recv(lport, fp); + return; + } + drop: + stats->ErrorFrames++; +- put_cpu(); ++ put_cpu_light(); + kfree_skb(skb); + } + +--- a/drivers/scsi/fcoe/fcoe_ctlr.c ++++ b/drivers/scsi/fcoe/fcoe_ctlr.c +@@ -835,7 +835,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + + INIT_LIST_HEAD(&del_list); + +- stats = per_cpu_ptr(fip->lp->stats, get_cpu()); ++ stats = per_cpu_ptr(fip->lp->stats, get_cpu_light()); + + list_for_each_entry_safe(fcf, next, &fip->fcfs, list) { + deadline = fcf->time + fcf->fka_period + fcf->fka_period / 2; +@@ -871,7 +871,7 @@ static unsigned long fcoe_ctlr_age_fcfs( + sel_time = fcf->time; + } + } +- put_cpu(); ++ put_cpu_light(); + + list_for_each_entry_safe(fcf, next, &del_list, list) { + /* Removes fcf from current list */ +--- a/drivers/scsi/libfc/fc_exch.c ++++ b/drivers/scsi/libfc/fc_exch.c +@@ -833,10 +833,10 @@ static struct fc_exch *fc_exch_em_alloc( + } + memset(ep, 0, sizeof(*ep)); + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = per_cpu_ptr(mp->pool, cpu); + spin_lock_bh(&pool->lock); +- put_cpu(); ++ put_cpu_light(); + + /* peek cache of free slot */ + if (pool->left != FC_XID_UNKNOWN) { diff --git a/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch b/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch new file mode 100644 index 000000000..360951129 --- /dev/null +++ b/debian/patches/features/all/rt/seqlock-prevent-rt-starvation.patch @@ -0,0 +1,189 @@ +Subject: seqlock: Prevent rt starvation +From: Thomas Gleixner +Date: Wed, 22 Feb 2012 12:03:30 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +If a low prio writer gets preempted while holding the seqlock write +locked, a high prio reader spins forever on RT. + +To prevent this let the reader grab the spinlock, so it blocks and +eventually boosts the writer. This way the writer can proceed and +endless spinning is prevented. + +For seqcount writers we disable preemption over the update code +path. Thanks to Al Viro for distangling some VFS code to make that +possible. + +Nicholas Mc Guire: +- spin_lock+unlock => spin_unlock_wait +- __write_seqcount_begin => __raw_write_seqcount_begin + +Signed-off-by: Thomas Gleixner + + +--- + include/linux/seqlock.h | 57 +++++++++++++++++++++++++++++++++++++----------- + include/net/neighbour.h | 6 ++--- + 2 files changed, 48 insertions(+), 15 deletions(-) + +--- a/include/linux/seqlock.h ++++ b/include/linux/seqlock.h +@@ -221,20 +221,30 @@ static inline int read_seqcount_retry(co + return __read_seqcount_retry(s, start); + } + +- +- +-static inline void raw_write_seqcount_begin(seqcount_t *s) ++static inline void __raw_write_seqcount_begin(seqcount_t *s) + { + s->sequence++; + smp_wmb(); + } + +-static inline void raw_write_seqcount_end(seqcount_t *s) ++static inline void raw_write_seqcount_begin(seqcount_t *s) ++{ ++ preempt_disable_rt(); ++ __raw_write_seqcount_begin(s); ++} ++ ++static inline void __raw_write_seqcount_end(seqcount_t *s) + { + smp_wmb(); + s->sequence++; + } + ++static inline void raw_write_seqcount_end(seqcount_t *s) ++{ ++ __raw_write_seqcount_end(s); ++ preempt_enable_rt(); ++} ++ + /** + * raw_write_seqcount_barrier - do a seq write barrier + * @s: pointer to seqcount_t +@@ -428,10 +438,33 @@ typedef struct { + /* + * Read side functions for starting and finalizing a read side section. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + static inline unsigned read_seqbegin(const seqlock_t *sl) + { + return read_seqcount_begin(&sl->seqcount); + } ++#else ++/* ++ * Starvation safe read side for RT ++ */ ++static inline unsigned read_seqbegin(seqlock_t *sl) ++{ ++ unsigned ret; ++ ++repeat: ++ ret = READ_ONCE(sl->seqcount.sequence); ++ if (unlikely(ret & 1)) { ++ /* ++ * Take the lock and let the writer proceed (i.e. evtl ++ * boost it), otherwise we could loop here forever. ++ */ ++ spin_unlock_wait(&sl->lock); ++ goto repeat; ++ } ++ smp_rmb(); ++ return ret; ++} ++#endif + + static inline unsigned read_seqretry(const seqlock_t *sl, unsigned start) + { +@@ -446,36 +479,36 @@ static inline unsigned read_seqretry(con + static inline void write_seqlock(seqlock_t *sl) + { + spin_lock(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock(&sl->lock); + } + + static inline void write_seqlock_bh(seqlock_t *sl) + { + spin_lock_bh(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_bh(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_bh(&sl->lock); + } + + static inline void write_seqlock_irq(seqlock_t *sl) + { + spin_lock_irq(&sl->lock); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + } + + static inline void write_sequnlock_irq(seqlock_t *sl) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irq(&sl->lock); + } + +@@ -484,7 +517,7 @@ static inline unsigned long __write_seql + unsigned long flags; + + spin_lock_irqsave(&sl->lock, flags); +- write_seqcount_begin(&sl->seqcount); ++ __raw_write_seqcount_begin(&sl->seqcount); + return flags; + } + +@@ -494,7 +527,7 @@ static inline unsigned long __write_seql + static inline void + write_sequnlock_irqrestore(seqlock_t *sl, unsigned long flags) + { +- write_seqcount_end(&sl->seqcount); ++ __raw_write_seqcount_end(&sl->seqcount); + spin_unlock_irqrestore(&sl->lock, flags); + } + +--- a/include/net/neighbour.h ++++ b/include/net/neighbour.h +@@ -451,7 +451,7 @@ static inline int neigh_hh_bridge(struct + } + #endif + +-static inline int neigh_hh_output(const struct hh_cache *hh, struct sk_buff *skb) ++static inline int neigh_hh_output(struct hh_cache *hh, struct sk_buff *skb) + { + unsigned int seq; + unsigned int hh_len; +@@ -475,7 +475,7 @@ static inline int neigh_hh_output(const + + static inline int neigh_output(struct neighbour *n, struct sk_buff *skb) + { +- const struct hh_cache *hh = &n->hh; ++ struct hh_cache *hh = &n->hh; + + if ((n->nud_state & NUD_CONNECTED) && hh->hh_len) + return neigh_hh_output(hh, skb); +@@ -516,7 +516,7 @@ struct neighbour_cb { + + #define NEIGH_CB(skb) ((struct neighbour_cb *)(skb)->cb) + +-static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, ++static inline void neigh_ha_snapshot(char *dst, struct neighbour *n, + const struct net_device *dev) + { + unsigned int seq; diff --git a/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch b/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch new file mode 100644 index 000000000..247d88005 --- /dev/null +++ b/debian/patches/features/all/rt/signal-revert-ptrace-preempt-magic.patch @@ -0,0 +1,32 @@ +Subject: signal: Revert ptrace preempt magic +From: Thomas Gleixner +Date: Wed, 21 Sep 2011 19:57:12 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Upstream commit '53da1d9456fe7f8 fix ptrace slowness' is nothing more +than a bandaid around the ptrace design trainwreck. It's not a +correctness issue, it's merily a cosmetic bandaid. + +Signed-off-by: Thomas Gleixner +--- + kernel/signal.c | 8 -------- + 1 file changed, 8 deletions(-) + +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -2007,15 +2007,7 @@ static void ptrace_stop(int exit_code, i + if (gstop_done && ptrace_reparented(current)) + do_notify_parent_cldstop(current, false, why); + +- /* +- * Don't want to allow preemption here, because +- * sys_ptrace() needs this task to be inactive. +- * +- * XXX: implement read_unlock_no_resched(). +- */ +- preempt_disable(); + read_unlock(&tasklist_lock); +- preempt_enable_no_resched(); + freezable_schedule(); + } else { + /* diff --git a/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch b/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch new file mode 100644 index 000000000..c05e3b5f8 --- /dev/null +++ b/debian/patches/features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch @@ -0,0 +1,200 @@ +From: Thomas Gleixner +Date: Fri, 3 Jul 2009 08:44:56 -0500 +Subject: signals: Allow rt tasks to cache one sigqueue struct +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +To avoid allocation allow rt tasks to cache one sigqueue struct in +task struct. + +Signed-off-by: Thomas Gleixner + +--- + include/linux/sched.h | 2 + + include/linux/signal.h | 1 + kernel/exit.c | 2 - + kernel/fork.c | 1 + kernel/signal.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++--- + 5 files changed, 70 insertions(+), 5 deletions(-) + +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -889,6 +889,8 @@ struct task_struct { + /* Signal handlers: */ + struct signal_struct *signal; + struct sighand_struct *sighand; ++ struct sigqueue *sigqueue_cache; ++ + sigset_t blocked; + sigset_t real_blocked; + /* Restored if set_restore_sigmask() was used: */ +--- a/include/linux/signal.h ++++ b/include/linux/signal.h +@@ -245,6 +245,7 @@ static inline void init_sigpending(struc + } + + extern void flush_sigqueue(struct sigpending *queue); ++extern void flush_task_sigqueue(struct task_struct *tsk); + + /* Test if 'sig' is valid signal. Use this instead of testing _NSIG directly */ + static inline int valid_signal(unsigned long sig) +--- a/kernel/exit.c ++++ b/kernel/exit.c +@@ -159,7 +159,7 @@ static void __exit_signal(struct task_st + * Do this under ->siglock, we can race with another thread + * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. + */ +- flush_sigqueue(&tsk->pending); ++ flush_task_sigqueue(tsk); + tsk->sighand = NULL; + spin_unlock(&sighand->siglock); + +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -1759,6 +1759,7 @@ static __latent_entropy struct task_stru + spin_lock_init(&p->alloc_lock); + + init_sigpending(&p->pending); ++ p->sigqueue_cache = NULL; + + p->utime = p->stime = p->gtime = 0; + #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME +--- a/kernel/signal.c ++++ b/kernel/signal.c +@@ -19,6 +19,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -362,13 +363,30 @@ static bool task_participate_group_stop( + return false; + } + ++static inline struct sigqueue *get_task_cache(struct task_struct *t) ++{ ++ struct sigqueue *q = t->sigqueue_cache; ++ ++ if (cmpxchg(&t->sigqueue_cache, q, NULL) != q) ++ return NULL; ++ return q; ++} ++ ++static inline int put_task_cache(struct task_struct *t, struct sigqueue *q) ++{ ++ if (cmpxchg(&t->sigqueue_cache, NULL, q) == NULL) ++ return 0; ++ return 1; ++} ++ + /* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appropriate lock must be held to stop the target task from exiting + */ + static struct sigqueue * +-__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, int override_rlimit) ++__sigqueue_do_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit, int fromslab) + { + struct sigqueue *q = NULL; + struct user_struct *user; +@@ -385,7 +403,10 @@ static struct sigqueue * + if (override_rlimit || + atomic_read(&user->sigpending) <= + task_rlimit(t, RLIMIT_SIGPENDING)) { +- q = kmem_cache_alloc(sigqueue_cachep, flags); ++ if (!fromslab) ++ q = get_task_cache(t); ++ if (!q) ++ q = kmem_cache_alloc(sigqueue_cachep, flags); + } else { + print_dropped_signal(sig); + } +@@ -402,6 +423,13 @@ static struct sigqueue * + return q; + } + ++static struct sigqueue * ++__sigqueue_alloc(int sig, struct task_struct *t, gfp_t flags, ++ int override_rlimit) ++{ ++ return __sigqueue_do_alloc(sig, t, flags, override_rlimit, 0); ++} ++ + static void __sigqueue_free(struct sigqueue *q) + { + if (q->flags & SIGQUEUE_PREALLOC) +@@ -411,6 +439,21 @@ static void __sigqueue_free(struct sigqu + kmem_cache_free(sigqueue_cachep, q); + } + ++static void sigqueue_free_current(struct sigqueue *q) ++{ ++ struct user_struct *up; ++ ++ if (q->flags & SIGQUEUE_PREALLOC) ++ return; ++ ++ up = q->user; ++ if (rt_prio(current->normal_prio) && !put_task_cache(current, q)) { ++ atomic_dec(&up->sigpending); ++ free_uid(up); ++ } else ++ __sigqueue_free(q); ++} ++ + void flush_sigqueue(struct sigpending *queue) + { + struct sigqueue *q; +@@ -424,6 +467,21 @@ void flush_sigqueue(struct sigpending *q + } + + /* ++ * Called from __exit_signal. Flush tsk->pending and ++ * tsk->sigqueue_cache ++ */ ++void flush_task_sigqueue(struct task_struct *tsk) ++{ ++ struct sigqueue *q; ++ ++ flush_sigqueue(&tsk->pending); ++ ++ q = get_task_cache(tsk); ++ if (q) ++ kmem_cache_free(sigqueue_cachep, q); ++} ++ ++/* + * Flush all pending signals for this kthread. + */ + void flush_signals(struct task_struct *t) +@@ -544,7 +602,7 @@ static void collect_signal(int sig, stru + (info->si_code == SI_TIMER) && + (info->si_sys_private); + +- __sigqueue_free(first); ++ sigqueue_free_current(first); + } else { + /* + * Ok, it wasn't in the queue. This must be +@@ -581,6 +639,8 @@ int dequeue_signal(struct task_struct *t + bool resched_timer = false; + int signr; + ++ WARN_ON_ONCE(tsk != current); ++ + /* We only dequeue private signals from ourselves, we don't let + * signalfd steal them + */ +@@ -1664,7 +1724,8 @@ EXPORT_SYMBOL(kill_pid); + */ + struct sigqueue *sigqueue_alloc(void) + { +- struct sigqueue *q = __sigqueue_alloc(-1, current, GFP_KERNEL, 0); ++ /* Preallocated sigqueue objects always from the slabcache ! */ ++ struct sigqueue *q = __sigqueue_do_alloc(-1, current, GFP_KERNEL, 0, 1); + + if (q) + q->flags |= SIGQUEUE_PREALLOC; diff --git a/debian/patches/features/all/rt/skbufhead-raw-lock.patch b/debian/patches/features/all/rt/skbufhead-raw-lock.patch new file mode 100644 index 000000000..d686de19c --- /dev/null +++ b/debian/patches/features/all/rt/skbufhead-raw-lock.patch @@ -0,0 +1,163 @@ +From: Thomas Gleixner +Date: Tue, 12 Jul 2011 15:38:34 +0200 +Subject: net: Use skbufhead with raw lock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Use the rps lock as rawlock so we can keep irq-off regions. It looks low +latency. However we can't kfree() from this context therefore we defer this +to the softirq and use the tofree_queue list for it (similar to process_queue). + +Signed-off-by: Thomas Gleixner +--- + include/linux/netdevice.h | 1 + + include/linux/skbuff.h | 7 +++++++ + net/core/dev.c | 33 +++++++++++++++++++++++++-------- + 3 files changed, 33 insertions(+), 8 deletions(-) + +--- a/include/linux/netdevice.h ++++ b/include/linux/netdevice.h +@@ -2916,6 +2916,7 @@ struct softnet_data { + unsigned int dropped; + struct sk_buff_head input_pkt_queue; + struct napi_struct backlog; ++ struct sk_buff_head tofree_queue; + + }; + +--- a/include/linux/skbuff.h ++++ b/include/linux/skbuff.h +@@ -287,6 +287,7 @@ struct sk_buff_head { + + __u32 qlen; + spinlock_t lock; ++ raw_spinlock_t raw_lock; + }; + + struct sk_buff; +@@ -1666,6 +1667,12 @@ static inline void skb_queue_head_init(s + __skb_queue_head_init(list); + } + ++static inline void skb_queue_head_init_raw(struct sk_buff_head *list) ++{ ++ raw_spin_lock_init(&list->raw_lock); ++ __skb_queue_head_init(list); ++} ++ + static inline void skb_queue_head_init_class(struct sk_buff_head *list, + struct lock_class_key *class) + { +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -219,14 +219,14 @@ static inline struct hlist_head *dev_ind + static inline void rps_lock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_lock(&sd->input_pkt_queue.lock); ++ raw_spin_lock(&sd->input_pkt_queue.raw_lock); + #endif + } + + static inline void rps_unlock(struct softnet_data *sd) + { + #ifdef CONFIG_RPS +- spin_unlock(&sd->input_pkt_queue.lock); ++ raw_spin_unlock(&sd->input_pkt_queue.raw_lock); + #endif + } + +@@ -4809,7 +4809,7 @@ static void flush_backlog(struct work_st + skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { + if (skb->dev->reg_state == NETREG_UNREGISTERING) { + __skb_unlink(skb, &sd->input_pkt_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } +@@ -4819,11 +4819,14 @@ static void flush_backlog(struct work_st + skb_queue_walk_safe(&sd->process_queue, skb, tmp) { + if (skb->dev->reg_state == NETREG_UNREGISTERING) { + __skb_unlink(skb, &sd->process_queue); +- kfree_skb(skb); ++ __skb_queue_tail(&sd->tofree_queue, skb); + input_queue_head_incr(sd); + } + } ++ if (!skb_queue_empty(&sd->tofree_queue)) ++ raise_softirq_irqoff(NET_RX_SOFTIRQ); + local_bh_enable(); ++ + } + + static void flush_all_backlogs(void) +@@ -5371,7 +5374,9 @@ static int process_backlog(struct napi_s + while (again) { + struct sk_buff *skb; + ++ local_irq_disable(); + while ((skb = __skb_dequeue(&sd->process_queue))) { ++ local_irq_enable(); + rcu_read_lock(); + __netif_receive_skb(skb); + rcu_read_unlock(); +@@ -5379,9 +5384,9 @@ static int process_backlog(struct napi_s + if (++work >= quota) + return work; + ++ local_irq_disable(); + } + +- local_irq_disable(); + rps_lock(sd); + if (skb_queue_empty(&sd->input_pkt_queue)) { + /* +@@ -5821,13 +5826,21 @@ static __latent_entropy void net_rx_acti + unsigned long time_limit = jiffies + + usecs_to_jiffies(netdev_budget_usecs); + int budget = netdev_budget; ++ struct sk_buff_head tofree_q; ++ struct sk_buff *skb; + LIST_HEAD(list); + LIST_HEAD(repoll); + ++ __skb_queue_head_init(&tofree_q); ++ + local_irq_disable(); ++ skb_queue_splice_init(&sd->tofree_queue, &tofree_q); + list_splice_init(&sd->poll_list, &list); + local_irq_enable(); + ++ while ((skb = __skb_dequeue(&tofree_q))) ++ kfree_skb(skb); ++ + for (;;) { + struct napi_struct *n; + +@@ -8790,10 +8803,13 @@ static int dev_cpu_dead(unsigned int old + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } +- while ((skb = skb_dequeue(&oldsd->input_pkt_queue))) { ++ while ((skb = __skb_dequeue(&oldsd->input_pkt_queue))) { + netif_rx_ni(skb); + input_queue_head_incr(oldsd); + } ++ while ((skb = __skb_dequeue(&oldsd->tofree_queue))) { ++ kfree_skb(skb); ++ } + + return 0; + } +@@ -9099,8 +9115,9 @@ static int __init net_dev_init(void) + + INIT_WORK(flush, flush_backlog); + +- skb_queue_head_init(&sd->input_pkt_queue); +- skb_queue_head_init(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->input_pkt_queue); ++ skb_queue_head_init_raw(&sd->process_queue); ++ skb_queue_head_init_raw(&sd->tofree_queue); + #ifdef CONFIG_XFRM_OFFLOAD + skb_queue_head_init(&sd->xfrm_backlog); + #endif diff --git a/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch b/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch new file mode 100644 index 000000000..482e1a10e --- /dev/null +++ b/debian/patches/features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch @@ -0,0 +1,48 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 15 Apr 2015 19:00:47 +0200 +Subject: slub: Disable SLUB_CPU_PARTIAL +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 87, name: rcuop/7 +|1 lock held by rcuop/7/87: +| #0: (rcu_callback){......}, at: [] rcu_nocb_kthread+0x1ca/0x5d0 +|Preemption disabled at:[] put_cpu_partial+0x29/0x220 +| +|CPU: 0 PID: 87 Comm: rcuop/7 Tainted: G W 4.0.0-rt0+ #477 +|Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.7.5-20140531_083030-gandalf 04/01/2014 +| 000000000007a9fc ffff88013987baf8 ffffffff817441c7 0000000000000007 +| 0000000000000000 ffff88013987bb18 ffffffff810eee51 0000000000000000 +| ffff88013fc10200 ffff88013987bb48 ffffffff8174a1c4 000000000007a9fc +|Call Trace: +| [] dump_stack+0x4f/0x90 +| [] ___might_sleep+0x121/0x1b0 +| [] rt_spin_lock+0x24/0x60 +| [] __free_pages_ok+0xaa/0x540 +| [] __free_pages+0x1d/0x30 +| [] __free_slab+0xc5/0x1e0 +| [] free_delayed+0x56/0x70 +| [] put_cpu_partial+0x14d/0x220 +| [] __slab_free+0x158/0x2c0 +| [] kmem_cache_free+0x221/0x2d0 +| [] file_free_rcu+0x2c/0x40 +| [] rcu_nocb_kthread+0x243/0x5d0 +| [] kthread+0xfc/0x120 +| [] ret_from_fork+0x58/0x90 + +Signed-off-by: Sebastian Andrzej Siewior +--- + init/Kconfig | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1655,7 +1655,7 @@ config SLAB_FREELIST_HARDENED + + config SLUB_CPU_PARTIAL + default y +- depends on SLUB && SMP ++ depends on SLUB && SMP && !PREEMPT_RT_FULL + bool "SLUB per cpu partial cache" + help + Per cpu partial caches accellerate objects allocation and freeing diff --git a/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch b/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch new file mode 100644 index 000000000..9c0135503 --- /dev/null +++ b/debian/patches/features/all/rt/slub-enable-irqs-for-no-wait.patch @@ -0,0 +1,42 @@ +Subject: slub: Enable irqs for __GFP_WAIT +From: Thomas Gleixner +Date: Wed, 09 Jan 2013 12:08:15 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +SYSTEM_RUNNING might be too late for enabling interrupts. Allocations +with GFP_WAIT can happen before that. So use this as an indicator. + +Signed-off-by: Thomas Gleixner +--- + mm/slub.c | 9 ++++++++- + 1 file changed, 8 insertions(+), 1 deletion(-) + +--- a/mm/slub.c ++++ b/mm/slub.c +@@ -1572,10 +1572,17 @@ static struct page *allocate_slab(struct + void *start, *p; + int idx, order; + bool shuffle; ++ bool enableirqs = false; + + flags &= gfp_allowed_mask; + + if (gfpflags_allow_blocking(flags)) ++ enableirqs = true; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (system_state > SYSTEM_BOOTING) ++ enableirqs = true; ++#endif ++ if (enableirqs) + local_irq_enable(); + + flags |= s->allocflags; +@@ -1634,7 +1641,7 @@ static struct page *allocate_slab(struct + page->frozen = 1; + + out: +- if (gfpflags_allow_blocking(flags)) ++ if (enableirqs) + local_irq_disable(); + if (!page) + return NULL; diff --git a/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch b/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch new file mode 100644 index 000000000..1816fd876 --- /dev/null +++ b/debian/patches/features/all/rt/softirq-disable-softirq-stacks-for-rt.patch @@ -0,0 +1,157 @@ +Subject: softirq: Disable softirq stacks for RT +From: Thomas Gleixner +Date: Mon, 18 Jul 2011 13:59:17 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Disable extra stacks for softirqs. We want to preempt softirqs and +having them on special IRQ-stack does not make this easier. + +Signed-off-by: Thomas Gleixner +--- + arch/powerpc/kernel/irq.c | 2 ++ + arch/powerpc/kernel/misc_32.S | 2 ++ + arch/powerpc/kernel/misc_64.S | 2 ++ + arch/sh/kernel/irq.c | 2 ++ + arch/sparc/kernel/irq_64.c | 2 ++ + arch/x86/entry/entry_64.S | 2 ++ + arch/x86/kernel/irq_32.c | 2 ++ + include/linux/interrupt.h | 2 +- + 8 files changed, 15 insertions(+), 1 deletion(-) + +--- a/arch/powerpc/kernel/irq.c ++++ b/arch/powerpc/kernel/irq.c +@@ -745,6 +745,7 @@ void irq_ctx_init(void) + } + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curtp, *irqtp; +@@ -762,6 +763,7 @@ void do_softirq_own_stack(void) + if (irqtp->flags) + set_bits(irqtp->flags, &curtp->flags); + } ++#endif + + irq_hw_number_t virq_to_hw(unsigned int virq) + { +--- a/arch/powerpc/kernel/misc_32.S ++++ b/arch/powerpc/kernel/misc_32.S +@@ -41,6 +41,7 @@ + * We store the saved ksp_limit in the unused part + * of the STACK_FRAME_OVERHEAD + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + stw r0,4(r1) +@@ -57,6 +58,7 @@ + stw r10,THREAD+KSP_LIMIT(r2) + mtlr r0 + blr ++#endif + + /* + * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp); +--- a/arch/powerpc/kernel/misc_64.S ++++ b/arch/powerpc/kernel/misc_64.S +@@ -31,6 +31,7 @@ + + .text + ++#ifndef CONFIG_PREEMPT_RT_FULL + _GLOBAL(call_do_softirq) + mflr r0 + std r0,16(r1) +@@ -41,6 +42,7 @@ + ld r0,16(r1) + mtlr r0 + blr ++#endif + + _GLOBAL(call_do_irq) + mflr r0 +--- a/arch/sh/kernel/irq.c ++++ b/arch/sh/kernel/irq.c +@@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu) + hardirq_ctx[cpu] = NULL; + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct thread_info *curctx; +@@ -175,6 +176,7 @@ void do_softirq_own_stack(void) + "r5", "r6", "r7", "r8", "r9", "r15", "t", "pr" + ); + } ++#endif + #else + static inline void handle_one_irq(unsigned int irq) + { +--- a/arch/sparc/kernel/irq_64.c ++++ b/arch/sparc/kernel/irq_64.c +@@ -854,6 +854,7 @@ void __irq_entry handler_irq(int pil, st + set_irq_regs(old_regs); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + void *orig_sp, *sp = softirq_stack[smp_processor_id()]; +@@ -868,6 +869,7 @@ void do_softirq_own_stack(void) + __asm__ __volatile__("mov %0, %%sp" + : : "r" (orig_sp)); + } ++#endif + + #ifdef CONFIG_HOTPLUG_CPU + void fixup_irqs(void) +--- a/arch/x86/entry/entry_64.S ++++ b/arch/x86/entry/entry_64.S +@@ -1038,6 +1038,7 @@ EXPORT_SYMBOL(native_load_gs_index) + jmp 2b + .previous + ++#ifndef CONFIG_PREEMPT_RT_FULL + /* Call softirq on interrupt stack. Interrupts are off. */ + ENTRY(do_softirq_own_stack) + pushq %rbp +@@ -1048,6 +1049,7 @@ ENTRY(do_softirq_own_stack) + leaveq + ret + ENDPROC(do_softirq_own_stack) ++#endif + + #ifdef CONFIG_XEN + idtentry hypervisor_callback xen_do_hypervisor_callback has_error_code=0 +--- a/arch/x86/kernel/irq_32.c ++++ b/arch/x86/kernel/irq_32.c +@@ -129,6 +129,7 @@ void irq_ctx_init(int cpu) + cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu)); + } + ++#ifndef CONFIG_PREEMPT_RT_FULL + void do_softirq_own_stack(void) + { + struct irq_stack *irqstk; +@@ -145,6 +146,7 @@ void do_softirq_own_stack(void) + + call_on_stack(__do_softirq, isp); + } ++#endif + + bool handle_irq(struct irq_desc *desc, struct pt_regs *regs) + { +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -506,7 +506,7 @@ struct softirq_action + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); + +-#ifdef __ARCH_HAS_DO_SOFTIRQ ++#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) diff --git a/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch b/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch new file mode 100644 index 000000000..e3c0a6be2 --- /dev/null +++ b/debian/patches/features/all/rt/softirq-preempt-fix-3-re.patch @@ -0,0 +1,169 @@ +Subject: softirq: Check preemption after reenabling interrupts +From: Thomas Gleixner +Date: Sun, 13 Nov 2011 17:17:09 +0100 (CET) +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +raise_softirq_irqoff() disables interrupts and wakes the softirq +daemon, but after reenabling interrupts there is no preemption check, +so the execution of the softirq thread might be delayed arbitrarily. + +In principle we could add that check to local_irq_enable/restore, but +that's overkill as the rasie_softirq_irqoff() sections are the only +ones which show this behaviour. + +Reported-by: Carsten Emde +Signed-off-by: Thomas Gleixner + +--- + block/blk-softirq.c | 3 +++ + include/linux/preempt.h | 3 +++ + lib/irq_poll.c | 5 +++++ + net/core/dev.c | 7 +++++++ + 4 files changed, 18 insertions(+) + +--- a/block/blk-softirq.c ++++ b/block/blk-softirq.c +@@ -53,6 +53,7 @@ static void trigger_softirq(void *data) + raise_softirq_irqoff(BLOCK_SOFTIRQ); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + /* +@@ -91,6 +92,7 @@ static int blk_softirq_cpu_dead(unsigned + this_cpu_ptr(&blk_cpu_done)); + raise_softirq_irqoff(BLOCK_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + return 0; + } +@@ -143,6 +145,7 @@ void __blk_complete_request(struct reque + goto do_local; + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__blk_complete_request); + +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -187,8 +187,10 @@ do { \ + + #ifdef CONFIG_PREEMPT_RT_BASE + # define preempt_enable_no_resched() sched_preempt_enable_no_resched() ++# define preempt_check_resched_rt() preempt_check_resched() + #else + # define preempt_enable_no_resched() preempt_enable() ++# define preempt_check_resched_rt() barrier(); + #endif + + #define preemptible() (preempt_count() == 0 && !irqs_disabled()) +@@ -275,6 +277,7 @@ do { \ + #define preempt_disable_notrace() barrier() + #define preempt_enable_no_resched_notrace() barrier() + #define preempt_enable_notrace() barrier() ++#define preempt_check_resched_rt() barrier() + #define preemptible() 0 + + #define migrate_disable() barrier() +--- a/lib/irq_poll.c ++++ b/lib/irq_poll.c +@@ -37,6 +37,7 @@ void irq_poll_sched(struct irq_poll *iop + list_add_tail(&iop->list, this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(irq_poll_sched); + +@@ -72,6 +73,7 @@ void irq_poll_complete(struct irq_poll * + local_irq_save(flags); + __irq_poll_complete(iop); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(irq_poll_complete); + +@@ -96,6 +98,7 @@ static void __latent_entropy irq_poll_so + } + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Even though interrupts have been re-enabled, this + * access is safe because interrupts can only add new +@@ -133,6 +136,7 @@ static void __latent_entropy irq_poll_so + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + /** +@@ -196,6 +200,7 @@ static int irq_poll_cpu_dead(unsigned in + this_cpu_ptr(&blk_cpu_iopoll)); + __raise_softirq_irqoff(IRQ_POLL_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + return 0; + } +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -2505,6 +2505,7 @@ static void __netif_reschedule(struct Qd + sd->output_queue_tailp = &q->next_sched; + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + + void __netif_schedule(struct Qdisc *q) +@@ -2567,6 +2568,7 @@ void __dev_kfree_skb_irq(struct sk_buff + __this_cpu_write(softnet_data.completion_queue, skb); + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__dev_kfree_skb_irq); + +@@ -3986,6 +3988,7 @@ static int enqueue_to_backlog(struct sk_ + rps_unlock(sd); + + local_irq_restore(flags); ++ preempt_check_resched_rt(); + + atomic_long_inc(&skb->dev->rx_dropped); + kfree_skb(skb); +@@ -5333,12 +5336,14 @@ static void net_rps_action_and_irq_enabl + sd->rps_ipi_list = NULL; + + local_irq_enable(); ++ preempt_check_resched_rt(); + + /* Send pending IPI's to kick RPS processing on remote cpus. */ + net_rps_send_ipi(remsd); + } else + #endif + local_irq_enable(); ++ preempt_check_resched_rt(); + } + + static bool sd_has_rps_ipi_waiting(struct softnet_data *sd) +@@ -5416,6 +5421,7 @@ void __napi_schedule(struct napi_struct + local_irq_save(flags); + ____napi_schedule(this_cpu_ptr(&softnet_data), n); + local_irq_restore(flags); ++ preempt_check_resched_rt(); + } + EXPORT_SYMBOL(__napi_schedule); + +@@ -8772,6 +8778,7 @@ static int dev_cpu_dead(unsigned int old + + raise_softirq_irqoff(NET_TX_SOFTIRQ); + local_irq_enable(); ++ preempt_check_resched_rt(); + + #ifdef CONFIG_RPS + remsd = oldsd->rps_ipi_list; diff --git a/debian/patches/features/all/rt/softirq-split-locks.patch b/debian/patches/features/all/rt/softirq-split-locks.patch new file mode 100644 index 000000000..16d96d533 --- /dev/null +++ b/debian/patches/features/all/rt/softirq-split-locks.patch @@ -0,0 +1,816 @@ +From: Thomas Gleixner +Date: Thu, 04 Oct 2012 14:20:47 +0100 +Subject: softirq: Split softirq locks +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The 3.x RT series removed the split softirq implementation in favour +of pushing softirq processing into the context of the thread which +raised it. Though this prevents us from handling the various softirqs +at different priorities. Now instead of reintroducing the split +softirq threads we split the locks which serialize the softirq +processing. + +If a softirq is raised in context of a thread, then the softirq is +noted on a per thread field, if the thread is in a bh disabled +region. If the softirq is raised from hard interrupt context, then the +bit is set in the flag field of ksoftirqd and ksoftirqd is invoked. +When a thread leaves a bh disabled region, then it tries to execute +the softirqs which have been raised in its own context. It acquires +the per softirq / per cpu lock for the softirq and then checks, +whether the softirq is still pending in the per cpu +local_softirq_pending() field. If yes, it runs the softirq. If no, +then some other task executed it already. This allows for zero config +softirq elevation in the context of user space tasks or interrupt +threads. + +Signed-off-by: Thomas Gleixner +[bwh: Adjust context to apply after commit b5b1404d0815 + "init: rename and re-order boot_cpu_state_init()"] +--- + include/linux/bottom_half.h | 34 +++ + include/linux/interrupt.h | 15 + + include/linux/preempt.h | 15 + + include/linux/sched.h | 3 + init/main.c | 1 + kernel/softirq.c | 491 +++++++++++++++++++++++++++++++++++++------- + kernel/time/tick-sched.c | 9 + 7 files changed, 478 insertions(+), 90 deletions(-) + +--- a/include/linux/bottom_half.h ++++ b/include/linux/bottom_half.h +@@ -4,6 +4,39 @@ + + #include + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ ++extern void __local_bh_disable(void); ++extern void _local_bh_enable(void); ++extern void __local_bh_enable(void); ++ ++static inline void local_bh_disable(void) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_disable(); ++} ++ ++static inline void local_bh_enable(void) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void __local_bh_enable_ip(unsigned long ip, unsigned int cnt) ++{ ++ __local_bh_enable(); ++} ++ ++static inline void local_bh_enable_ip(unsigned long ip) ++{ ++ __local_bh_enable(); ++} ++ ++#else ++ + #ifdef CONFIG_TRACE_IRQFLAGS + extern void __local_bh_disable_ip(unsigned long ip, unsigned int cnt); + #else +@@ -31,5 +64,6 @@ static inline void local_bh_enable(void) + { + __local_bh_enable_ip(_THIS_IP_, SOFTIRQ_DISABLE_OFFSET); + } ++#endif + + #endif /* _LINUX_BH_H */ +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -503,10 +503,11 @@ struct softirq_action + void (*action)(struct softirq_action *); + }; + ++#ifndef CONFIG_PREEMPT_RT_FULL + asmlinkage void do_softirq(void); + asmlinkage void __do_softirq(void); +- +-#if defined(__ARCH_HAS_DO_SOFTIRQ) && !defined(CONFIG_PREEMPT_RT_FULL) ++static inline void thread_do_softirq(void) { do_softirq(); } ++#ifdef __ARCH_HAS_DO_SOFTIRQ + void do_softirq_own_stack(void); + #else + static inline void do_softirq_own_stack(void) +@@ -514,6 +515,9 @@ static inline void do_softirq_own_stack( + __do_softirq(); + } + #endif ++#else ++extern void thread_do_softirq(void); ++#endif + + extern void open_softirq(int nr, void (*action)(struct softirq_action *)); + extern void softirq_init(void); +@@ -521,6 +525,7 @@ extern void __raise_softirq_irqoff(unsig + + extern void raise_softirq_irqoff(unsigned int nr); + extern void raise_softirq(unsigned int nr); ++extern void softirq_check_pending_idle(void); + + DECLARE_PER_CPU(struct task_struct *, ksoftirqd); + +@@ -638,6 +643,12 @@ extern void tasklet_kill_immediate(struc + extern void tasklet_init(struct tasklet_struct *t, + void (*func)(unsigned long), unsigned long data); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++extern void softirq_early_init(void); ++#else ++static inline void softirq_early_init(void) { } ++#endif ++ + struct tasklet_hrtimer { + struct hrtimer timer; + struct tasklet_struct tasklet; +--- a/include/linux/preempt.h ++++ b/include/linux/preempt.h +@@ -51,7 +51,11 @@ + #define HARDIRQ_OFFSET (1UL << HARDIRQ_SHIFT) + #define NMI_OFFSET (1UL << NMI_SHIFT) + +-#define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define SOFTIRQ_DISABLE_OFFSET (2 * SOFTIRQ_OFFSET) ++#else ++# define SOFTIRQ_DISABLE_OFFSET (0) ++#endif + + /* We use the MSB mostly because its available */ + #define PREEMPT_NEED_RESCHED 0x80000000 +@@ -81,9 +85,15 @@ + #include + + #define hardirq_count() (preempt_count() & HARDIRQ_MASK) +-#define softirq_count() (preempt_count() & SOFTIRQ_MASK) + #define irq_count() (preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \ + | NMI_MASK)) ++#ifndef CONFIG_PREEMPT_RT_FULL ++# define softirq_count() (preempt_count() & SOFTIRQ_MASK) ++# define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) ++#else ++# define softirq_count() ((unsigned long)current->softirq_nestcnt) ++extern int in_serving_softirq(void); ++#endif + + /* + * Are we doing bottom half or hardware interrupt processing? +@@ -101,7 +111,6 @@ + #define in_irq() (hardirq_count()) + #define in_softirq() (softirq_count()) + #define in_interrupt() (irq_count()) +-#define in_serving_softirq() (softirq_count() & SOFTIRQ_OFFSET) + #define in_nmi() (preempt_count() & NMI_MASK) + #define in_task() (!(preempt_count() & \ + (NMI_MASK | HARDIRQ_MASK | SOFTIRQ_OFFSET))) +--- a/include/linux/sched.h ++++ b/include/linux/sched.h +@@ -1177,6 +1177,8 @@ struct task_struct { + #endif + #ifdef CONFIG_PREEMPT_RT_BASE + struct rcu_head put_rcu; ++ int softirq_nestcnt; ++ unsigned int softirqs_raised; + #endif + #ifdef CONFIG_DEBUG_ATOMIC_SLEEP + unsigned long task_state_change; +@@ -1394,6 +1396,7 @@ extern struct pid *cad_pid; + /* + * Per process flags + */ ++#define PF_IN_SOFTIRQ 0x00000001 /* Task is serving softirq */ + #define PF_IDLE 0x00000002 /* I am an IDLE thread */ + #define PF_EXITING 0x00000004 /* Getting shut down */ + #define PF_EXITPIDONE 0x00000008 /* PI exit done on shut down */ +--- a/init/main.c ++++ b/init/main.c +@@ -561,6 +561,7 @@ asmlinkage __visible void __init start_k + setup_command_line(command_line); + setup_nr_cpu_ids(); + setup_per_cpu_areas(); ++ softirq_early_init(); + smp_prepare_boot_cpu(); /* arch-specific boot-cpu hooks */ + boot_cpu_hotplug_init(); + +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -26,7 +26,9 @@ + #include + #include + #include ++#include + #include ++#include + + #define CREATE_TRACE_POINTS + #include +@@ -63,6 +65,98 @@ const char * const softirq_to_name[NR_SO + "TASKLET", "SCHED", "HRTIMER", "RCU" + }; + ++#ifdef CONFIG_NO_HZ_COMMON ++# ifdef CONFIG_PREEMPT_RT_FULL ++ ++struct softirq_runner { ++ struct task_struct *runner[NR_SOFTIRQS]; ++}; ++ ++static DEFINE_PER_CPU(struct softirq_runner, softirq_runners); ++ ++static inline void softirq_set_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = current; ++} ++ ++static inline void softirq_clr_runner(unsigned int sirq) ++{ ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ ++ sr->runner[sirq] = NULL; ++} ++ ++/* ++ * On preempt-rt a softirq running context might be blocked on a ++ * lock. There might be no other runnable task on this CPU because the ++ * lock owner runs on some other CPU. So we have to go into idle with ++ * the pending bit set. Therefor we need to check this otherwise we ++ * warn about false positives which confuses users and defeats the ++ * whole purpose of this test. ++ * ++ * This code is called with interrupts disabled. ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ struct softirq_runner *sr = this_cpu_ptr(&softirq_runners); ++ u32 warnpending; ++ int i; ++ ++ if (rate_limit >= 10) ++ return; ++ ++ warnpending = local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK; ++ for (i = 0; i < NR_SOFTIRQS; i++) { ++ struct task_struct *tsk = sr->runner[i]; ++ ++ /* ++ * The wakeup code in rtmutex.c wakes up the task ++ * _before_ it sets pi_blocked_on to NULL under ++ * tsk->pi_lock. So we need to check for both: state ++ * and pi_blocked_on. ++ */ ++ if (tsk) { ++ raw_spin_lock(&tsk->pi_lock); ++ if (tsk->pi_blocked_on || tsk->state == TASK_RUNNING) { ++ /* Clear all bits pending in that task */ ++ warnpending &= ~(tsk->softirqs_raised); ++ warnpending &= ~(1 << i); ++ } ++ raw_spin_unlock(&tsk->pi_lock); ++ } ++ } ++ ++ if (warnpending) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ warnpending); ++ rate_limit++; ++ } ++} ++# else ++/* ++ * On !PREEMPT_RT we just printk rate limited: ++ */ ++void softirq_check_pending_idle(void) ++{ ++ static int rate_limit; ++ ++ if (rate_limit < 10 && ++ (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { ++ printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n", ++ local_softirq_pending()); ++ rate_limit++; ++ } ++} ++# endif ++ ++#else /* !CONFIG_NO_HZ_COMMON */ ++static inline void softirq_set_runner(unsigned int sirq) { } ++static inline void softirq_clr_runner(unsigned int sirq) { } ++#endif ++ + /* + * we cannot loop indefinitely here to avoid userspace starvation, + * but we also don't want to introduce a worst case 1/HZ latency +@@ -78,6 +172,27 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++static void handle_softirq(unsigned int vec_nr) ++{ ++ struct softirq_action *h = softirq_vec + vec_nr; ++ int prev_count; ++ ++ prev_count = preempt_count(); ++ ++ kstat_incr_softirqs_this_cpu(vec_nr); ++ ++ trace_softirq_entry(vec_nr); ++ h->action(h); ++ trace_softirq_exit(vec_nr); ++ if (unlikely(prev_count != preempt_count())) { ++ pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", ++ vec_nr, softirq_to_name[vec_nr], h->action, ++ prev_count, preempt_count()); ++ preempt_count_set(prev_count); ++ } ++} ++ ++#ifndef CONFIG_PREEMPT_RT_FULL + /* + * If ksoftirqd is scheduled, we do not want to process pending softirqs + * right now. Let ksoftirqd handle this at its own rate, to get fairness, +@@ -93,6 +208,47 @@ static bool ksoftirqd_running(unsigned l + return tsk && (tsk->state == TASK_RUNNING); + } + ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return local_softirq_pending(); ++} ++ ++static void handle_pending_softirqs(u32 pending) ++{ ++ struct softirq_action *h = softirq_vec; ++ int softirq_bit; ++ ++ local_irq_enable(); ++ ++ h = softirq_vec; ++ ++ while ((softirq_bit = ffs(pending))) { ++ unsigned int vec_nr; ++ ++ h += softirq_bit - 1; ++ vec_nr = h - softirq_vec; ++ handle_softirq(vec_nr); ++ ++ h++; ++ pending >>= softirq_bit; ++ } ++ ++ rcu_bh_qs(); ++ local_irq_disable(); ++} ++ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ if (ksoftirqd_softirq_pending()) { ++ __do_softirq(); ++ local_irq_enable(); ++ cond_resched(); ++ return; ++ } ++ local_irq_enable(); ++} ++ + /* + * preempt_count and SOFTIRQ_OFFSET usage: + * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving +@@ -252,10 +408,8 @@ asmlinkage __visible void __softirq_entr + unsigned long end = jiffies + MAX_SOFTIRQ_TIME; + unsigned long old_flags = current->flags; + int max_restart = MAX_SOFTIRQ_RESTART; +- struct softirq_action *h; + bool in_hardirq; + __u32 pending; +- int softirq_bit; + + /* + * Mask out PF_MEMALLOC s current task context is borrowed for the +@@ -274,36 +428,7 @@ asmlinkage __visible void __softirq_entr + /* Reset the pending bitmask before enabling irqs */ + set_softirq_pending(0); + +- local_irq_enable(); +- +- h = softirq_vec; +- +- while ((softirq_bit = ffs(pending))) { +- unsigned int vec_nr; +- int prev_count; +- +- h += softirq_bit - 1; +- +- vec_nr = h - softirq_vec; +- prev_count = preempt_count(); +- +- kstat_incr_softirqs_this_cpu(vec_nr); +- +- trace_softirq_entry(vec_nr); +- h->action(h); +- trace_softirq_exit(vec_nr); +- if (unlikely(prev_count != preempt_count())) { +- pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", +- vec_nr, softirq_to_name[vec_nr], h->action, +- prev_count, preempt_count()); +- preempt_count_set(prev_count); +- } +- h++; +- pending >>= softirq_bit; +- } +- +- rcu_bh_qs(); +- local_irq_disable(); ++ handle_pending_softirqs(pending); + + pending = local_softirq_pending(); + if (pending) { +@@ -340,6 +465,248 @@ asmlinkage __visible void do_softirq(voi + } + + /* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ __raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an interrupt or softirq, we're done ++ * (this also catches softirq-disabled code). We will ++ * actually run the softirq once we return from ++ * the irq or softirq. ++ * ++ * Otherwise we wake up ksoftirqd to make sure we ++ * schedule the softirq soon. ++ */ ++ if (!in_interrupt()) ++ wakeup_softirqd(); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++} ++ ++static inline void local_bh_disable_nort(void) { local_bh_disable(); } ++static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } ++static void ksoftirqd_set_sched_params(unsigned int cpu) { } ++static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } ++ ++#else /* !PREEMPT_RT_FULL */ ++ ++/* ++ * On RT we serialize softirq execution with a cpu local lock per softirq ++ */ ++static DEFINE_PER_CPU(struct local_irq_lock [NR_SOFTIRQS], local_softirq_locks); ++ ++void __init softirq_early_init(void) ++{ ++ int i; ++ ++ for (i = 0; i < NR_SOFTIRQS; i++) ++ local_irq_lock_init(local_softirq_locks[i]); ++} ++ ++static void lock_softirq(int which) ++{ ++ local_lock(local_softirq_locks[which]); ++} ++ ++static void unlock_softirq(int which) ++{ ++ local_unlock(local_softirq_locks[which]); ++} ++ ++static void do_single_softirq(int which) ++{ ++ unsigned long old_flags = current->flags; ++ ++ current->flags &= ~PF_MEMALLOC; ++ vtime_account_irq_enter(current); ++ current->flags |= PF_IN_SOFTIRQ; ++ lockdep_softirq_enter(); ++ local_irq_enable(); ++ handle_softirq(which); ++ local_irq_disable(); ++ lockdep_softirq_exit(); ++ current->flags &= ~PF_IN_SOFTIRQ; ++ vtime_account_irq_enter(current); ++ current_restore_flags(old_flags, PF_MEMALLOC); ++} ++ ++/* ++ * Called with interrupts disabled. Process softirqs which were raised ++ * in current context (or on behalf of ksoftirqd). ++ */ ++static void do_current_softirqs(void) ++{ ++ while (current->softirqs_raised) { ++ int i = __ffs(current->softirqs_raised); ++ unsigned int pending, mask = (1U << i); ++ ++ current->softirqs_raised &= ~mask; ++ local_irq_enable(); ++ ++ /* ++ * If the lock is contended, we boost the owner to ++ * process the softirq or leave the critical section ++ * now. ++ */ ++ lock_softirq(i); ++ local_irq_disable(); ++ softirq_set_runner(i); ++ /* ++ * Check with the local_softirq_pending() bits, ++ * whether we need to process this still or if someone ++ * else took care of it. ++ */ ++ pending = local_softirq_pending(); ++ if (pending & mask) { ++ set_softirq_pending(pending & ~mask); ++ do_single_softirq(i); ++ } ++ softirq_clr_runner(i); ++ WARN_ON(current->softirq_nestcnt != 1); ++ local_irq_enable(); ++ unlock_softirq(i); ++ local_irq_disable(); ++ } ++} ++ ++void __local_bh_disable(void) ++{ ++ if (++current->softirq_nestcnt == 1) ++ migrate_disable(); ++} ++EXPORT_SYMBOL(__local_bh_disable); ++ ++void __local_bh_enable(void) ++{ ++ if (WARN_ON(current->softirq_nestcnt == 0)) ++ return; ++ ++ local_irq_disable(); ++ if (current->softirq_nestcnt == 1 && current->softirqs_raised) ++ do_current_softirqs(); ++ local_irq_enable(); ++ ++ if (--current->softirq_nestcnt == 0) ++ migrate_enable(); ++} ++EXPORT_SYMBOL(__local_bh_enable); ++ ++int in_serving_softirq(void) ++{ ++ return current->flags & PF_IN_SOFTIRQ; ++} ++EXPORT_SYMBOL(in_serving_softirq); ++ ++/* Called with preemption disabled */ ++static void run_ksoftirqd(unsigned int cpu) ++{ ++ local_irq_disable(); ++ current->softirq_nestcnt++; ++ ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ local_irq_enable(); ++ cond_resched(); ++} ++ ++/* ++ * Called from netif_rx_ni(). Preemption enabled, but migration ++ * disabled. So the cpu can't go away under us. ++ */ ++void thread_do_softirq(void) ++{ ++ if (!in_serving_softirq() && current->softirqs_raised) { ++ current->softirq_nestcnt++; ++ do_current_softirqs(); ++ current->softirq_nestcnt--; ++ } ++} ++ ++static void do_raise_softirq_irqoff(unsigned int nr) ++{ ++ trace_softirq_raise(nr); ++ or_softirq_pending(1UL << nr); ++ ++ /* ++ * If we are not in a hard interrupt and inside a bh disabled ++ * region, we simply raise the flag on current. local_bh_enable() ++ * will make sure that the softirq is executed. Otherwise we ++ * delegate it to ksoftirqd. ++ */ ++ if (!in_irq() && current->softirq_nestcnt) ++ current->softirqs_raised |= (1U << nr); ++ else if (__this_cpu_read(ksoftirqd)) ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); ++} ++ ++void __raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ if (!in_irq() && !current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++/* ++ * This function must run with irqs disabled! ++ */ ++void raise_softirq_irqoff(unsigned int nr) ++{ ++ do_raise_softirq_irqoff(nr); ++ ++ /* ++ * If we're in an hard interrupt we let irq return code deal ++ * with the wakeup of ksoftirqd. ++ */ ++ if (in_irq()) ++ return; ++ /* ++ * If we are in thread context but outside of a bh disabled ++ * region, we need to wake ksoftirqd as well. ++ * ++ * CHECKME: Some of the places which do that could be wrapped ++ * into local_bh_disable/enable pairs. Though it's unclear ++ * whether this is worth the effort. To find those places just ++ * raise a WARN() if the condition is met. ++ */ ++ if (!current->softirq_nestcnt) ++ wakeup_softirqd(); ++} ++ ++static inline int ksoftirqd_softirq_pending(void) ++{ ++ return current->softirqs_raised; ++} ++ ++static inline void local_bh_disable_nort(void) { } ++static inline void _local_bh_enable_nort(void) { } ++ ++static inline void ksoftirqd_set_sched_params(unsigned int cpu) ++{ ++ struct sched_param param = { .sched_priority = 1 }; ++ ++ sched_setscheduler(current, SCHED_FIFO, ¶m); ++ /* Take over all pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending(); ++ local_irq_enable(); ++} ++ ++static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) ++{ ++ struct sched_param param = { .sched_priority = 0 }; ++ ++ sched_setscheduler(current, SCHED_NORMAL, ¶m); ++} ++ ++#endif /* PREEMPT_RT_FULL */ ++/* + * Enter an interrupt context. + */ + void irq_enter(void) +@@ -350,9 +717,9 @@ void irq_enter(void) + * Prevent raise_softirq from needlessly waking up ksoftirqd + * here, as softirq will be serviced on return from interrupt. + */ +- local_bh_disable(); ++ local_bh_disable_nort(); + tick_irq_enter(); +- _local_bh_enable(); ++ _local_bh_enable_nort(); + } + + __irq_enter(); +@@ -360,6 +727,7 @@ void irq_enter(void) + + static inline void invoke_softirq(void) + { ++#ifndef CONFIG_PREEMPT_RT_FULL + if (ksoftirqd_running(local_softirq_pending())) + return; + +@@ -382,6 +750,15 @@ static inline void invoke_softirq(void) + } else { + wakeup_softirqd(); + } ++#else /* PREEMPT_RT_FULL */ ++ unsigned long flags; ++ ++ local_irq_save(flags); ++ if (__this_cpu_read(ksoftirqd) && ++ __this_cpu_read(ksoftirqd)->softirqs_raised) ++ wakeup_softirqd(); ++ local_irq_restore(flags); ++#endif + } + + static inline void tick_irq_exit(void) +@@ -417,26 +794,6 @@ void irq_exit(void) + trace_hardirq_exit(); /* must be last! */ + } + +-/* +- * This function must run with irqs disabled! +- */ +-inline void raise_softirq_irqoff(unsigned int nr) +-{ +- __raise_softirq_irqoff(nr); +- +- /* +- * If we're in an interrupt or softirq, we're done +- * (this also catches softirq-disabled code). We will +- * actually run the softirq once we return from +- * the irq or softirq. +- * +- * Otherwise we wake up ksoftirqd to make sure we +- * schedule the softirq soon. +- */ +- if (!in_interrupt()) +- wakeup_softirqd(); +-} +- + void raise_softirq(unsigned int nr) + { + unsigned long flags; +@@ -446,12 +803,6 @@ void raise_softirq(unsigned int nr) + local_irq_restore(flags); + } + +-void __raise_softirq_irqoff(unsigned int nr) +-{ +- trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); +-} +- + void open_softirq(int nr, void (*action)(struct softirq_action *)) + { + softirq_vec[nr].action = action; +@@ -725,23 +1076,7 @@ EXPORT_SYMBOL(tasklet_unlock_wait); + + static int ksoftirqd_should_run(unsigned int cpu) + { +- return local_softirq_pending(); +-} +- +-static void run_ksoftirqd(unsigned int cpu) +-{ +- local_irq_disable(); +- if (local_softirq_pending()) { +- /* +- * We can safely run softirq on inline stack, as we are not deep +- * in the task stack here. +- */ +- __do_softirq(); +- local_irq_enable(); +- cond_resched(); +- return; +- } +- local_irq_enable(); ++ return ksoftirqd_softirq_pending(); + } + + #ifdef CONFIG_HOTPLUG_CPU +@@ -808,6 +1143,8 @@ static int takeover_tasklets(unsigned in + + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, ++ .setup = ksoftirqd_set_sched_params, ++ .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -891,14 +891,7 @@ static bool can_stop_idle_tick(int cpu, + return false; + + if (unlikely(local_softirq_pending() && cpu_online(cpu))) { +- static int ratelimit; +- +- if (ratelimit < 10 && +- (local_softirq_pending() & SOFTIRQ_STOP_IDLE_MASK)) { +- pr_warn("NOHZ: local_softirq_pending %02x\n", +- (unsigned int) local_softirq_pending()); +- ratelimit++; +- } ++ softirq_check_pending_idle(); + return false; + } + diff --git a/debian/patches/features/all/rt/softirq-split-timer-softirqs-out-of-ksoftirqd.patch b/debian/patches/features/all/rt/softirq-split-timer-softirqs-out-of-ksoftirqd.patch new file mode 100644 index 000000000..da9c60f3c --- /dev/null +++ b/debian/patches/features/all/rt/softirq-split-timer-softirqs-out-of-ksoftirqd.patch @@ -0,0 +1,208 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 20 Jan 2016 16:34:17 +0100 +Subject: softirq: split timer softirqs out of ksoftirqd +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The softirqd runs in -RT with SCHED_FIFO (prio 1) and deals mostly with +timer wakeup which can not happen in hardirq context. The prio has been +risen from the normal SCHED_OTHER so the timer wakeup does not happen +too late. +With enough networking load it is possible that the system never goes +idle and schedules ksoftirqd and everything else with a higher priority. +One of the tasks left behind is one of RCU's threads and so we see stalls +and eventually run out of memory. +This patch moves the TIMER and HRTIMER softirqs out of the `ksoftirqd` +thread into its own `ktimersoftd`. The former can now run SCHED_OTHER +(same as mainline) and the latter at SCHED_FIFO due to the wakeups. + +From networking point of view: The NAPI callback runs after the network +interrupt thread completes. If its run time takes too long the NAPI code +itself schedules the `ksoftirqd`. Here in the thread it can run at +SCHED_OTHER priority and it won't defer RCU anymore. + +Cc: stable-rt@vger.kernel.org +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/softirq.c | 85 +++++++++++++++++++++++++++++++++++++++++++++++-------- + 1 file changed, 73 insertions(+), 12 deletions(-) + +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -59,6 +59,10 @@ EXPORT_PER_CPU_SYMBOL(irq_stat); + static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; + + DEFINE_PER_CPU(struct task_struct *, ksoftirqd); ++#ifdef CONFIG_PREEMPT_RT_FULL ++#define TIMER_SOFTIRQS ((1 << TIMER_SOFTIRQ) | (1 << HRTIMER_SOFTIRQ)) ++DEFINE_PER_CPU(struct task_struct *, ktimer_softirqd); ++#endif + + const char * const softirq_to_name[NR_SOFTIRQS] = { + "HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL", +@@ -172,6 +176,17 @@ static void wakeup_softirqd(void) + wake_up_process(tsk); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static void wakeup_timer_softirqd(void) ++{ ++ /* Interrupts are disabled: no need to stop preemption */ ++ struct task_struct *tsk = __this_cpu_read(ktimer_softirqd); ++ ++ if (tsk && tsk->state != TASK_RUNNING) ++ wake_up_process(tsk); ++} ++#endif ++ + static void handle_softirq(unsigned int vec_nr) + { + struct softirq_action *h = softirq_vec + vec_nr; +@@ -493,7 +508,6 @@ void __raise_softirq_irqoff(unsigned int + static inline void local_bh_disable_nort(void) { local_bh_disable(); } + static inline void _local_bh_enable_nort(void) { _local_bh_enable(); } + static void ksoftirqd_set_sched_params(unsigned int cpu) { } +-static void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) { } + + #else /* !PREEMPT_RT_FULL */ + +@@ -640,8 +654,12 @@ void thread_do_softirq(void) + + static void do_raise_softirq_irqoff(unsigned int nr) + { ++ unsigned int mask; ++ ++ mask = 1UL << nr; ++ + trace_softirq_raise(nr); +- or_softirq_pending(1UL << nr); ++ or_softirq_pending(mask); + + /* + * If we are not in a hard interrupt and inside a bh disabled +@@ -650,16 +668,29 @@ static void do_raise_softirq_irqoff(unsi + * delegate it to ksoftirqd. + */ + if (!in_irq() && current->softirq_nestcnt) +- current->softirqs_raised |= (1U << nr); +- else if (__this_cpu_read(ksoftirqd)) +- __this_cpu_read(ksoftirqd)->softirqs_raised |= (1U << nr); ++ current->softirqs_raised |= mask; ++ else if (!__this_cpu_read(ksoftirqd) || !__this_cpu_read(ktimer_softirqd)) ++ return; ++ ++ if (mask & TIMER_SOFTIRQS) ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised |= mask; ++ else ++ __this_cpu_read(ksoftirqd)->softirqs_raised |= mask; ++} ++ ++static void wakeup_proper_softirq(unsigned int nr) ++{ ++ if ((1UL << nr) & TIMER_SOFTIRQS) ++ wakeup_timer_softirqd(); ++ else ++ wakeup_softirqd(); + } + + void __raise_softirq_irqoff(unsigned int nr) + { + do_raise_softirq_irqoff(nr); + if (!in_irq() && !current->softirq_nestcnt) +- wakeup_softirqd(); ++ wakeup_proper_softirq(nr); + } + + /* +@@ -685,7 +716,7 @@ void raise_softirq_irqoff(unsigned int n + * raise a WARN() if the condition is met. + */ + if (!current->softirq_nestcnt) +- wakeup_softirqd(); ++ wakeup_proper_softirq(nr); + } + + static inline int ksoftirqd_softirq_pending(void) +@@ -698,22 +729,37 @@ static inline void _local_bh_enable_nort + + static inline void ksoftirqd_set_sched_params(unsigned int cpu) + { ++ /* Take over all but timer pending softirqs when starting */ ++ local_irq_disable(); ++ current->softirqs_raised = local_softirq_pending() & ~TIMER_SOFTIRQS; ++ local_irq_enable(); ++} ++ ++static inline void ktimer_softirqd_set_sched_params(unsigned int cpu) ++{ + struct sched_param param = { .sched_priority = 1 }; + + sched_setscheduler(current, SCHED_FIFO, ¶m); +- /* Take over all pending softirqs when starting */ ++ ++ /* Take over timer pending softirqs when starting */ + local_irq_disable(); +- current->softirqs_raised = local_softirq_pending(); ++ current->softirqs_raised = local_softirq_pending() & TIMER_SOFTIRQS; + local_irq_enable(); + } + +-static inline void ksoftirqd_clr_sched_params(unsigned int cpu, bool online) ++static inline void ktimer_softirqd_clr_sched_params(unsigned int cpu, ++ bool online) + { + struct sched_param param = { .sched_priority = 0 }; + + sched_setscheduler(current, SCHED_NORMAL, ¶m); + } + ++static int ktimer_softirqd_should_run(unsigned int cpu) ++{ ++ return current->softirqs_raised; ++} ++ + #endif /* PREEMPT_RT_FULL */ + /* + * Enter an interrupt context. +@@ -766,6 +812,9 @@ static inline void invoke_softirq(void) + if (__this_cpu_read(ksoftirqd) && + __this_cpu_read(ksoftirqd)->softirqs_raised) + wakeup_softirqd(); ++ if (__this_cpu_read(ktimer_softirqd) && ++ __this_cpu_read(ktimer_softirqd)->softirqs_raised) ++ wakeup_timer_softirqd(); + local_irq_restore(flags); + #endif + } +@@ -1153,18 +1202,30 @@ static int takeover_tasklets(unsigned in + static struct smp_hotplug_thread softirq_threads = { + .store = &ksoftirqd, + .setup = ksoftirqd_set_sched_params, +- .cleanup = ksoftirqd_clr_sched_params, + .thread_should_run = ksoftirqd_should_run, + .thread_fn = run_ksoftirqd, + .thread_comm = "ksoftirqd/%u", + }; + ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct smp_hotplug_thread softirq_timer_threads = { ++ .store = &ktimer_softirqd, ++ .setup = ktimer_softirqd_set_sched_params, ++ .cleanup = ktimer_softirqd_clr_sched_params, ++ .thread_should_run = ktimer_softirqd_should_run, ++ .thread_fn = run_ksoftirqd, ++ .thread_comm = "ktimersoftd/%u", ++}; ++#endif ++ + static __init int spawn_ksoftirqd(void) + { + cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL, + takeover_tasklets); + BUG_ON(smpboot_register_percpu_thread(&softirq_threads)); +- ++#ifdef CONFIG_PREEMPT_RT_FULL ++ BUG_ON(smpboot_register_percpu_thread(&softirq_timer_threads)); ++#endif + return 0; + } + early_initcall(spawn_ksoftirqd); diff --git a/debian/patches/features/all/rt/spinlock-types-separate-raw.patch b/debian/patches/features/all/rt/spinlock-types-separate-raw.patch new file mode 100644 index 000000000..e9a589e50 --- /dev/null +++ b/debian/patches/features/all/rt/spinlock-types-separate-raw.patch @@ -0,0 +1,205 @@ +Subject: spinlock: Split the lock types header +From: Thomas Gleixner +Date: Wed, 29 Jun 2011 19:34:01 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Split raw_spinlock into its own file and the remaining spinlock_t into +its own non-RT header. The non-RT header will be replaced later by sleeping +spinlocks. + +Signed-off-by: Thomas Gleixner +--- + include/linux/rwlock_types.h | 4 ++ + include/linux/spinlock_types.h | 71 +----------------------------------- + include/linux/spinlock_types_nort.h | 33 ++++++++++++++++ + include/linux/spinlock_types_raw.h | 55 +++++++++++++++++++++++++++ + 4 files changed, 94 insertions(+), 69 deletions(-) + +--- a/include/linux/rwlock_types.h ++++ b/include/linux/rwlock_types.h +@@ -1,6 +1,10 @@ + #ifndef __LINUX_RWLOCK_TYPES_H + #define __LINUX_RWLOCK_TYPES_H + ++#if !defined(__LINUX_SPINLOCK_TYPES_H) ++# error "Do not include directly, include spinlock_types.h" ++#endif ++ + /* + * include/linux/rwlock_types.h - generic rwlock type definitions + * and initializers +--- a/include/linux/spinlock_types.h ++++ b/include/linux/spinlock_types.h +@@ -9,76 +9,9 @@ + * Released under the General Public License (GPL). + */ + +-#if defined(CONFIG_SMP) +-# include +-#else +-# include +-#endif ++#include + +-#include +- +-typedef struct raw_spinlock { +- arch_spinlock_t raw_lock; +-#ifdef CONFIG_DEBUG_SPINLOCK +- unsigned int magic, owner_cpu; +- void *owner; +-#endif +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +- struct lockdep_map dep_map; +-#endif +-} raw_spinlock_t; +- +-#define SPINLOCK_MAGIC 0xdead4ead +- +-#define SPINLOCK_OWNER_INIT ((void *)-1L) +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } +-#else +-# define SPIN_DEP_MAP_INIT(lockname) +-#endif +- +-#ifdef CONFIG_DEBUG_SPINLOCK +-# define SPIN_DEBUG_INIT(lockname) \ +- .magic = SPINLOCK_MAGIC, \ +- .owner_cpu = -1, \ +- .owner = SPINLOCK_OWNER_INIT, +-#else +-# define SPIN_DEBUG_INIT(lockname) +-#endif +- +-#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ +- { \ +- .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ +- SPIN_DEBUG_INIT(lockname) \ +- SPIN_DEP_MAP_INIT(lockname) } +- +-#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ +- (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) +- +-typedef struct spinlock { +- union { +- struct raw_spinlock rlock; +- +-#ifdef CONFIG_DEBUG_LOCK_ALLOC +-# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) +- struct { +- u8 __padding[LOCK_PADSIZE]; +- struct lockdep_map dep_map; +- }; +-#endif +- }; +-} spinlock_t; +- +-#define __SPIN_LOCK_INITIALIZER(lockname) \ +- { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } +- +-#define __SPIN_LOCK_UNLOCKED(lockname) \ +- (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) +- +-#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++#include + + #include + +--- /dev/null ++++ b/include/linux/spinlock_types_nort.h +@@ -0,0 +1,33 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_NORT_H ++#define __LINUX_SPINLOCK_TYPES_NORT_H ++ ++#ifndef __LINUX_SPINLOCK_TYPES_H ++#error "Do not include directly. Include spinlock_types.h instead" ++#endif ++ ++/* ++ * The non RT version maps spinlocks to raw_spinlocks ++ */ ++typedef struct spinlock { ++ union { ++ struct raw_spinlock rlock; ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define LOCK_PADSIZE (offsetof(struct raw_spinlock, dep_map)) ++ struct { ++ u8 __padding[LOCK_PADSIZE]; ++ struct lockdep_map dep_map; ++ }; ++#endif ++ }; ++} spinlock_t; ++ ++#define __SPIN_LOCK_INITIALIZER(lockname) \ ++ { { .rlock = __RAW_SPIN_LOCK_INITIALIZER(lockname) } } ++ ++#define __SPIN_LOCK_UNLOCKED(lockname) \ ++ (spinlock_t ) __SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_SPINLOCK(x) spinlock_t x = __SPIN_LOCK_UNLOCKED(x) ++ ++#endif +--- /dev/null ++++ b/include/linux/spinlock_types_raw.h +@@ -0,0 +1,55 @@ ++#ifndef __LINUX_SPINLOCK_TYPES_RAW_H ++#define __LINUX_SPINLOCK_TYPES_RAW_H ++ ++#include ++ ++#if defined(CONFIG_SMP) ++# include ++#else ++# include ++#endif ++ ++#include ++ ++typedef struct raw_spinlock { ++ arch_spinlock_t raw_lock; ++#ifdef CONFIG_DEBUG_SPINLOCK ++ unsigned int magic, owner_cpu; ++ void *owner; ++#endif ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++ struct lockdep_map dep_map; ++#endif ++} raw_spinlock_t; ++ ++#define SPINLOCK_MAGIC 0xdead4ead ++ ++#define SPINLOCK_OWNER_INIT ((void *)-1L) ++ ++#ifdef CONFIG_DEBUG_LOCK_ALLOC ++# define SPIN_DEP_MAP_INIT(lockname) .dep_map = { .name = #lockname } ++#else ++# define SPIN_DEP_MAP_INIT(lockname) ++#endif ++ ++#ifdef CONFIG_DEBUG_SPINLOCK ++# define SPIN_DEBUG_INIT(lockname) \ ++ .magic = SPINLOCK_MAGIC, \ ++ .owner_cpu = -1, \ ++ .owner = SPINLOCK_OWNER_INIT, ++#else ++# define SPIN_DEBUG_INIT(lockname) ++#endif ++ ++#define __RAW_SPIN_LOCK_INITIALIZER(lockname) \ ++ { \ ++ .raw_lock = __ARCH_SPIN_LOCK_UNLOCKED, \ ++ SPIN_DEBUG_INIT(lockname) \ ++ SPIN_DEP_MAP_INIT(lockname) } ++ ++#define __RAW_SPIN_LOCK_UNLOCKED(lockname) \ ++ (raw_spinlock_t) __RAW_SPIN_LOCK_INITIALIZER(lockname) ++ ++#define DEFINE_RAW_SPINLOCK(x) raw_spinlock_t x = __RAW_SPIN_LOCK_UNLOCKED(x) ++ ++#endif diff --git a/debian/patches/features/all/rt/squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch b/debian/patches/features/all/rt/squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch new file mode 100644 index 000000000..aee0bc64b --- /dev/null +++ b/debian/patches/features/all/rt/squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch @@ -0,0 +1,66 @@ +From: Julia Cartwright +Date: Mon, 7 May 2018 08:58:57 -0500 +Subject: [PATCH] squashfs: make use of local lock in multi_cpu + decompressor +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Currently, the squashfs multi_cpu decompressor makes use of +get_cpu_ptr()/put_cpu_ptr(), which unconditionally disable preemption +during decompression. + +Because the workload is distributed across CPUs, all CPUs can observe a +very high wakeup latency, which has been seen to be as much as 8000us. + +Convert this decompressor to make use of a local lock, which will allow +execution of the decompressor with preemption-enabled, but also ensure +concurrent accesses to the percpu compressor data on the local CPU will +be serialized. + +Cc: stable-rt@vger.kernel.org +Reported-by: Alexander Stein +Tested-by: Alexander Stein +Signed-off-by: Julia Cartwright +Signed-off-by: Sebastian Andrzej Siewior +--- + fs/squashfs/decompressor_multi_percpu.c | 16 ++++++++++++---- + 1 file changed, 12 insertions(+), 4 deletions(-) + +--- a/fs/squashfs/decompressor_multi_percpu.c ++++ b/fs/squashfs/decompressor_multi_percpu.c +@@ -10,6 +10,7 @@ + #include + #include + #include ++#include + + #include "squashfs_fs.h" + #include "squashfs_fs_sb.h" +@@ -25,6 +26,8 @@ struct squashfs_stream { + void *stream; + }; + ++static DEFINE_LOCAL_IRQ_LOCK(stream_lock); ++ + void *squashfs_decompressor_create(struct squashfs_sb_info *msblk, + void *comp_opts) + { +@@ -79,10 +82,15 @@ int squashfs_decompress(struct squashfs_ + { + struct squashfs_stream __percpu *percpu = + (struct squashfs_stream __percpu *) msblk->stream; +- struct squashfs_stream *stream = get_cpu_ptr(percpu); +- int res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, +- offset, length, output); +- put_cpu_ptr(stream); ++ struct squashfs_stream *stream; ++ int res; ++ ++ stream = get_locked_ptr(stream_lock, percpu); ++ ++ res = msblk->decompressor->decompress(msblk, stream->stream, bh, b, ++ offset, length, output); ++ ++ put_locked_ptr(stream_lock, stream); + + if (res < 0) + ERROR("%s decompression failed, data probably corrupt\n", diff --git a/debian/patches/features/all/rt/srcu-replace-local_irqsave-with-a-locallock.patch b/debian/patches/features/all/rt/srcu-replace-local_irqsave-with-a-locallock.patch new file mode 100644 index 000000000..0f0174d15 --- /dev/null +++ b/debian/patches/features/all/rt/srcu-replace-local_irqsave-with-a-locallock.patch @@ -0,0 +1,71 @@ +From: Sebastian Andrzej Siewior +Date: Thu, 12 Oct 2017 18:37:12 +0200 +Subject: [PATCH] srcu: replace local_irqsave() with a locallock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There are two instances which disable interrupts in order to become a +stable this_cpu_ptr() pointer. The restore part is coupled with +spin_unlock_irqrestore() which does not work on RT. +Replace the local_irq_save() call with the appropriate local_lock() +version of it. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/srcutree.c | 14 +++++++++----- + 1 file changed, 9 insertions(+), 5 deletions(-) + +--- a/kernel/rcu/srcutree.c ++++ b/kernel/rcu/srcutree.c +@@ -37,6 +37,7 @@ + #include + #include + #include ++#include + + #include "rcu.h" + #include "rcu_segcblist.h" +@@ -752,6 +753,8 @@ static void srcu_flip(struct srcu_struct + * negligible when amoritized over that time period, and the extra latency + * of a needlessly non-expedited grace period is similarly negligible. + */ ++static DEFINE_LOCAL_IRQ_LOCK(sp_llock); ++ + static bool srcu_might_be_idle(struct srcu_struct *sp) + { + unsigned long curseq; +@@ -760,13 +763,13 @@ static bool srcu_might_be_idle(struct sr + unsigned long t; + + /* If the local srcu_data structure has callbacks, not idle. */ +- local_irq_save(flags); ++ local_lock_irqsave(sp_llock, flags); + sdp = this_cpu_ptr(sp->sda); + if (rcu_segcblist_pend_cbs(&sdp->srcu_cblist)) { +- local_irq_restore(flags); ++ local_unlock_irqrestore(sp_llock, flags); + return false; /* Callbacks already present, so not idle. */ + } +- local_irq_restore(flags); ++ local_unlock_irqrestore(sp_llock, flags); + + /* + * No local callbacks, so probabalistically probe global state. +@@ -844,7 +847,7 @@ void __call_srcu(struct srcu_struct *sp, + return; + } + rhp->func = func; +- local_irq_save(flags); ++ local_lock_irqsave(sp_llock, flags); + sdp = this_cpu_ptr(sp->sda); + spin_lock_rcu_node(sdp); + rcu_segcblist_enqueue(&sdp->srcu_cblist, rhp, false); +@@ -860,7 +863,8 @@ void __call_srcu(struct srcu_struct *sp, + sdp->srcu_gp_seq_needed_exp = s; + needexp = true; + } +- spin_unlock_irqrestore_rcu_node(sdp, flags); ++ spin_unlock_rcu_node(sdp); ++ local_unlock_irqrestore(sp_llock, flags); + if (needgp) + srcu_funnel_gp_start(sp, sdp, s, do_norm); + else if (needexp) diff --git a/debian/patches/features/all/rt/srcu-use-cpu_online-instead-custom-check.patch b/debian/patches/features/all/rt/srcu-use-cpu_online-instead-custom-check.patch new file mode 100644 index 000000000..cb9fbbf1a --- /dev/null +++ b/debian/patches/features/all/rt/srcu-use-cpu_online-instead-custom-check.patch @@ -0,0 +1,91 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 13 Sep 2017 14:43:41 +0200 +Subject: [PATCH] srcu: use cpu_online() instead custom check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The current check via srcu_online is slightly racy because after looking +at srcu_online there could be an interrupt that interrupted us long +enough until the CPU we checked against went offline. +An alternative would be to hold the hotplug rwsem (so the CPUs don't +change their state) and then check based on cpu_online() if we queue it +on a specific CPU or not. queue_work_on() itself can handle if something +is enqueued on an offline CPU but a timer which is enqueued on an offline +CPU won't fire until the CPU is back online. + +I am not sure if the removal in rcu_init() is okay or not. I assume that +SRCU won't enqueue a work item before SRCU is up and ready. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/rcu/srcutree.c | 22 ++++------------------ + kernel/rcu/tree.c | 4 ---- + 2 files changed, 4 insertions(+), 22 deletions(-) + +--- a/kernel/rcu/srcutree.c ++++ b/kernel/rcu/srcutree.c +@@ -36,6 +36,7 @@ + #include + #include + #include ++#include + + #include "rcu.h" + #include "rcu_segcblist.h" +@@ -456,21 +457,6 @@ static void srcu_gp_start(struct srcu_st + } + + /* +- * Track online CPUs to guide callback workqueue placement. +- */ +-DEFINE_PER_CPU(bool, srcu_online); +- +-void srcu_online_cpu(unsigned int cpu) +-{ +- WRITE_ONCE(per_cpu(srcu_online, cpu), true); +-} +- +-void srcu_offline_cpu(unsigned int cpu) +-{ +- WRITE_ONCE(per_cpu(srcu_online, cpu), false); +-} +- +-/* + * Place the workqueue handler on the specified CPU if online, otherwise + * just run it whereever. This is useful for placing workqueue handlers + * that are to invoke the specified CPU's callbacks. +@@ -481,12 +467,12 @@ static bool srcu_queue_delayed_work_on(i + { + bool ret; + +- preempt_disable(); +- if (READ_ONCE(per_cpu(srcu_online, cpu))) ++ cpus_read_lock(); ++ if (cpu_online(cpu)) + ret = queue_delayed_work_on(cpu, wq, dwork, delay); + else + ret = queue_delayed_work(wq, dwork, delay); +- preempt_enable(); ++ cpus_read_unlock(); + return ret; + } + +--- a/kernel/rcu/tree.c ++++ b/kernel/rcu/tree.c +@@ -3732,8 +3732,6 @@ int rcutree_online_cpu(unsigned int cpu) + rnp->ffmask |= rdp->grpmask; + raw_spin_unlock_irqrestore_rcu_node(rnp, flags); + } +- if (IS_ENABLED(CONFIG_TREE_SRCU)) +- srcu_online_cpu(cpu); + if (rcu_scheduler_active == RCU_SCHEDULER_INACTIVE) + return 0; /* Too early in boot for scheduler work. */ + sync_sched_exp_online_cleanup(cpu); +@@ -3761,8 +3759,6 @@ int rcutree_offline_cpu(unsigned int cpu + } + + rcutree_affinity_setting(cpu, cpu); +- if (IS_ENABLED(CONFIG_TREE_SRCU)) +- srcu_offline_cpu(cpu); + return 0; + } + diff --git a/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch b/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch new file mode 100644 index 000000000..d42112cf9 --- /dev/null +++ b/debian/patches/features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch @@ -0,0 +1,54 @@ +From: Mike Galbraith +Date: Wed, 18 Feb 2015 16:05:28 +0100 +Subject: sunrpc: Make svc_xprt_do_enqueue() use get_cpu_light() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +|BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:915 +|in_atomic(): 1, irqs_disabled(): 0, pid: 3194, name: rpc.nfsd +|Preemption disabled at:[] svc_xprt_received+0x4b/0xc0 [sunrpc] +|CPU: 6 PID: 3194 Comm: rpc.nfsd Not tainted 3.18.7-rt1 #9 +|Hardware name: MEDION MS-7848/MS-7848, BIOS M7848W08.404 11/06/2014 +| ffff880409630000 ffff8800d9a33c78 ffffffff815bdeb5 0000000000000002 +| 0000000000000000 ffff8800d9a33c98 ffffffff81073c86 ffff880408dd6008 +| ffff880408dd6000 ffff8800d9a33cb8 ffffffff815c3d84 ffff88040b3ac000 +|Call Trace: +| [] dump_stack+0x4f/0x9e +| [] __might_sleep+0xe6/0x150 +| [] rt_spin_lock+0x24/0x50 +| [] svc_xprt_do_enqueue+0x80/0x230 [sunrpc] +| [] svc_xprt_received+0x4b/0xc0 [sunrpc] +| [] svc_add_new_perm_xprt+0x6d/0x80 [sunrpc] +| [] svc_addsock+0x143/0x200 [sunrpc] +| [] write_ports+0x28c/0x340 [nfsd] +| [] nfsctl_transaction_write+0x4c/0x80 [nfsd] +| [] vfs_write+0xb3/0x1d0 +| [] SyS_write+0x49/0xb0 +| [] system_call_fastpath+0x16/0x1b + + +Signed-off-by: Mike Galbraith +Signed-off-by: Sebastian Andrzej Siewior +--- + net/sunrpc/svc_xprt.c | 4 ++-- + 1 file changed, 2 insertions(+), 2 deletions(-) + +--- a/net/sunrpc/svc_xprt.c ++++ b/net/sunrpc/svc_xprt.c +@@ -393,7 +393,7 @@ void svc_xprt_do_enqueue(struct svc_xprt + if (test_and_set_bit(XPT_BUSY, &xprt->xpt_flags)) + return; + +- cpu = get_cpu(); ++ cpu = get_cpu_light(); + pool = svc_pool_for_cpu(xprt->xpt_server, cpu); + + atomic_long_inc(&pool->sp_stats.packets); +@@ -417,7 +417,7 @@ void svc_xprt_do_enqueue(struct svc_xprt + rqstp = NULL; + out_unlock: + rcu_read_unlock(); +- put_cpu(); ++ put_cpu_light(); + trace_svc_xprt_do_enqueue(xprt, rqstp); + } + EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue); diff --git a/debian/patches/features/all/rt/sysfs-realtime-entry.patch b/debian/patches/features/all/rt/sysfs-realtime-entry.patch new file mode 100644 index 000000000..51b4f9d88 --- /dev/null +++ b/debian/patches/features/all/rt/sysfs-realtime-entry.patch @@ -0,0 +1,48 @@ +Subject: sysfs: Add /sys/kernel/realtime entry +From: Clark Williams +Date: Sat Jul 30 21:55:53 2011 -0500 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Add a /sys/kernel entry to indicate that the kernel is a +realtime kernel. + +Clark says that he needs this for udev rules, udev needs to evaluate +if its a PREEMPT_RT kernel a few thousand times and parsing uname +output is too slow or so. + +Are there better solutions? Should it exist and return 0 on !-rt? + +Signed-off-by: Clark Williams +Signed-off-by: Peter Zijlstra +--- + kernel/ksysfs.c | 12 ++++++++++++ + 1 file changed, 12 insertions(+) + +--- a/kernel/ksysfs.c ++++ b/kernel/ksysfs.c +@@ -140,6 +140,15 @@ KERNEL_ATTR_RO(vmcoreinfo); + + #endif /* CONFIG_CRASH_CORE */ + ++#if defined(CONFIG_PREEMPT_RT_FULL) ++static ssize_t realtime_show(struct kobject *kobj, ++ struct kobj_attribute *attr, char *buf) ++{ ++ return sprintf(buf, "%d\n", 1); ++} ++KERNEL_ATTR_RO(realtime); ++#endif ++ + /* whether file capabilities are enabled */ + static ssize_t fscaps_show(struct kobject *kobj, + struct kobj_attribute *attr, char *buf) +@@ -231,6 +240,9 @@ static struct attribute * kernel_attrs[] + &rcu_expedited_attr.attr, + &rcu_normal_attr.attr, + #endif ++#ifdef CONFIG_PREEMPT_RT_FULL ++ &realtime_attr.attr, ++#endif + NULL + }; + diff --git a/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch b/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch new file mode 100644 index 000000000..924480203 --- /dev/null +++ b/debian/patches/features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch @@ -0,0 +1,295 @@ +Subject: tasklet: Prevent tasklets from going into infinite spin in RT +From: Ingo Molnar +Date: Tue Nov 29 20:18:22 2011 -0500 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When CONFIG_PREEMPT_RT_FULL is enabled, tasklets run as threads, +and spinlocks turn are mutexes. But this can cause issues with +tasks disabling tasklets. A tasklet runs under ksoftirqd, and +if a tasklets are disabled with tasklet_disable(), the tasklet +count is increased. When a tasklet runs, it checks this counter +and if it is set, it adds itself back on the softirq queue and +returns. + +The problem arises in RT because ksoftirq will see that a softirq +is ready to run (the tasklet softirq just re-armed itself), and will +not sleep, but instead run the softirqs again. The tasklet softirq +will still see that the count is non-zero and will not execute +the tasklet and requeue itself on the softirq again, which will +cause ksoftirqd to run it again and again and again. + +It gets worse because ksoftirqd runs as a real-time thread. +If it preempted the task that disabled tasklets, and that task +has migration disabled, or can't run for other reasons, the tasklet +softirq will never run because the count will never be zero, and +ksoftirqd will go into an infinite loop. As an RT task, it this +becomes a big problem. + +This is a hack solution to have tasklet_disable stop tasklets, and +when a tasklet runs, instead of requeueing the tasklet softirqd +it delays it. When tasklet_enable() is called, and tasklets are +waiting, then the tasklet_enable() will kick the tasklets to continue. +This prevents the lock up from ksoftirq going into an infinite loop. + +[ rostedt@goodmis.org: ported to 3.0-rt ] + +Signed-off-by: Ingo Molnar +Signed-off-by: Steven Rostedt +Signed-off-by: Thomas Gleixner + +--- + include/linux/interrupt.h | 33 ++++++------ + kernel/softirq.c | 126 ++++++++++++++++++++++++++++++++++++++-------- + 2 files changed, 125 insertions(+), 34 deletions(-) + +--- a/include/linux/interrupt.h ++++ b/include/linux/interrupt.h +@@ -542,8 +542,9 @@ static inline struct task_struct *this_c + to be executed on some cpu at least once after this. + * If the tasklet is already scheduled, but its execution is still not + started, it will be executed only once. +- * If this tasklet is already running on another CPU (or schedule is called +- from tasklet itself), it is rescheduled for later. ++ * If this tasklet is already running on another CPU, it is rescheduled ++ for later. ++ * Schedule must not be called from the tasklet itself (a lockup occurs) + * Tasklet is strictly serialized wrt itself, but not + wrt another tasklets. If client needs some intertask synchronization, + he makes it with spinlocks. +@@ -568,27 +569,36 @@ struct tasklet_struct name = { NULL, 0, + enum + { + TASKLET_STATE_SCHED, /* Tasklet is scheduled for execution */ +- TASKLET_STATE_RUN /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_RUN, /* Tasklet is running (SMP only) */ ++ TASKLET_STATE_PENDING /* Tasklet is pending */ + }; + +-#ifdef CONFIG_SMP ++#define TASKLET_STATEF_SCHED (1 << TASKLET_STATE_SCHED) ++#define TASKLET_STATEF_RUN (1 << TASKLET_STATE_RUN) ++#define TASKLET_STATEF_PENDING (1 << TASKLET_STATE_PENDING) ++ ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + static inline int tasklet_trylock(struct tasklet_struct *t) + { + return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state); + } + ++static inline int tasklet_tryunlock(struct tasklet_struct *t) ++{ ++ return cmpxchg(&t->state, TASKLET_STATEF_RUN, 0) == TASKLET_STATEF_RUN; ++} ++ + static inline void tasklet_unlock(struct tasklet_struct *t) + { + smp_mb__before_atomic(); + clear_bit(TASKLET_STATE_RUN, &(t)->state); + } + +-static inline void tasklet_unlock_wait(struct tasklet_struct *t) +-{ +- while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { barrier(); } +-} ++extern void tasklet_unlock_wait(struct tasklet_struct *t); ++ + #else + #define tasklet_trylock(t) 1 ++#define tasklet_tryunlock(t) 1 + #define tasklet_unlock_wait(t) do { } while (0) + #define tasklet_unlock(t) do { } while (0) + #endif +@@ -622,12 +632,7 @@ static inline void tasklet_disable(struc + smp_mb(); + } + +-static inline void tasklet_enable(struct tasklet_struct *t) +-{ +- smp_mb__before_atomic(); +- atomic_dec(&t->count); +-} +- ++extern void tasklet_enable(struct tasklet_struct *t); + extern void tasklet_kill(struct tasklet_struct *t); + extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu); + extern void tasklet_init(struct tasklet_struct *t, +--- a/kernel/softirq.c ++++ b/kernel/softirq.c +@@ -21,6 +21,7 @@ + #include + #include + #include ++#include + #include + #include + #include +@@ -475,11 +476,38 @@ static void __tasklet_schedule_common(st + unsigned long flags; + + local_irq_save(flags); ++ if (!tasklet_trylock(t)) { ++ local_irq_restore(flags); ++ return; ++ } ++ + head = this_cpu_ptr(headp); +- t->next = NULL; +- *head->tail = t; +- head->tail = &(t->next); +- raise_softirq_irqoff(softirq_nr); ++again: ++ /* We may have been preempted before tasklet_trylock ++ * and __tasklet_action may have already run. ++ * So double check the sched bit while the takslet ++ * is locked before adding it to the list. ++ */ ++ if (test_bit(TASKLET_STATE_SCHED, &t->state)) { ++ t->next = NULL; ++ *head->tail = t; ++ head->tail = &(t->next); ++ raise_softirq_irqoff(softirq_nr); ++ tasklet_unlock(t); ++ } else { ++ /* This is subtle. If we hit the corner case above ++ * It is possible that we get preempted right here, ++ * and another task has successfully called ++ * tasklet_schedule(), then this function, and ++ * failed on the trylock. Thus we must be sure ++ * before releasing the tasklet lock, that the ++ * SCHED_BIT is clear. Otherwise the tasklet ++ * may get its SCHED_BIT set, but not added to the ++ * list ++ */ ++ if (!tasklet_tryunlock(t)) ++ goto again; ++ } + local_irq_restore(flags); + } + +@@ -497,11 +525,21 @@ void __tasklet_hi_schedule(struct taskle + } + EXPORT_SYMBOL(__tasklet_hi_schedule); + ++void tasklet_enable(struct tasklet_struct *t) ++{ ++ if (!atomic_dec_and_test(&t->count)) ++ return; ++ if (test_and_clear_bit(TASKLET_STATE_PENDING, &t->state)) ++ tasklet_schedule(t); ++} ++EXPORT_SYMBOL(tasklet_enable); ++ + static void tasklet_action_common(struct softirq_action *a, + struct tasklet_head *tl_head, + unsigned int softirq_nr) + { + struct tasklet_struct *list; ++ int loops = 1000000; + + local_irq_disable(); + list = tl_head->head; +@@ -513,25 +551,56 @@ static void tasklet_action_common(struct + struct tasklet_struct *t = list; + + list = list->next; ++ /* ++ * Should always succeed - after a tasklist got on the ++ * list (after getting the SCHED bit set from 0 to 1), ++ * nothing but the tasklet softirq it got queued to can ++ * lock it: ++ */ ++ if (!tasklet_trylock(t)) { ++ WARN_ON(1); ++ continue; ++ } + +- if (tasklet_trylock(t)) { +- if (!atomic_read(&t->count)) { +- if (!test_and_clear_bit(TASKLET_STATE_SCHED, +- &t->state)) +- BUG(); +- t->func(t->data); ++ t->next = NULL; ++ ++ if (unlikely(atomic_read(&t->count))) { ++out_disabled: ++ /* implicit unlock: */ ++ wmb(); ++ t->state = TASKLET_STATEF_PENDING; ++ continue; ++ } ++ /* ++ * After this point on the tasklet might be rescheduled ++ * on another CPU, but it can only be added to another ++ * CPU's tasklet list if we unlock the tasklet (which we ++ * dont do yet). ++ */ ++ if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ WARN_ON(1); ++again: ++ t->func(t->data); ++ ++ while (!tasklet_tryunlock(t)) { ++ /* ++ * If it got disabled meanwhile, bail out: ++ */ ++ if (atomic_read(&t->count)) ++ goto out_disabled; ++ /* ++ * If it got scheduled meanwhile, re-execute ++ * the tasklet function: ++ */ ++ if (test_and_clear_bit(TASKLET_STATE_SCHED, &t->state)) ++ goto again; ++ if (!--loops) { ++ printk("hm, tasklet state: %08lx\n", t->state); ++ WARN_ON(1); + tasklet_unlock(t); +- continue; ++ break; + } +- tasklet_unlock(t); + } +- +- local_irq_disable(); +- t->next = NULL; +- *tl_head->tail = t; +- tl_head->tail = &t->next; +- __raise_softirq_irqoff(softirq_nr); +- local_irq_enable(); + } + } + +@@ -563,7 +632,7 @@ void tasklet_kill(struct tasklet_struct + + while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + do { +- yield(); ++ msleep(1); + } while (test_bit(TASKLET_STATE_SCHED, &t->state)); + } + tasklet_unlock_wait(t); +@@ -637,6 +706,23 @@ void __init softirq_init(void) + open_softirq(HI_SOFTIRQ, tasklet_hi_action); + } + ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) ++void tasklet_unlock_wait(struct tasklet_struct *t) ++{ ++ while (test_bit(TASKLET_STATE_RUN, &(t)->state)) { ++ /* ++ * Hack for now to avoid this busy-loop: ++ */ ++#ifdef CONFIG_PREEMPT_RT_FULL ++ msleep(1); ++#else ++ barrier(); ++#endif ++ } ++} ++EXPORT_SYMBOL(tasklet_unlock_wait); ++#endif ++ + static int ksoftirqd_should_run(unsigned int cpu) + { + return local_softirq_pending(); diff --git a/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch b/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch new file mode 100644 index 000000000..af1cf0529 --- /dev/null +++ b/debian/patches/features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch @@ -0,0 +1,131 @@ +From: Daniel Wagner +Date: Tue, 17 Feb 2015 09:37:44 +0100 +Subject: thermal: Defer thermal wakups to threads +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +On RT the spin lock in pkg_temp_thermal_platfrom_thermal_notify will +call schedule while we run in irq context. + +[] dump_stack+0x4e/0x8f +[] __schedule_bug+0xa6/0xb4 +[] __schedule+0x5b4/0x700 +[] schedule+0x2a/0x90 +[] rt_spin_lock_slowlock+0xe5/0x2d0 +[] rt_spin_lock+0x25/0x30 +[] pkg_temp_thermal_platform_thermal_notify+0x45/0x134 [x86_pkg_temp_thermal] +[] ? therm_throt_process+0x1b/0x160 +[] intel_thermal_interrupt+0x211/0x250 +[] smp_thermal_interrupt+0x21/0x40 +[] thermal_interrupt+0x6d/0x80 + +Let's defer the work to a kthread. + +Signed-off-by: Daniel Wagner +[bigeasy: reoder init/denit position. TODO: flush swork on exit] +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/thermal/x86_pkg_temp_thermal.c | 52 +++++++++++++++++++++++++++++++-- + 1 file changed, 49 insertions(+), 3 deletions(-) + +--- a/drivers/thermal/x86_pkg_temp_thermal.c ++++ b/drivers/thermal/x86_pkg_temp_thermal.c +@@ -29,6 +29,7 @@ + #include + #include + #include ++#include + #include + #include + +@@ -329,7 +330,7 @@ static void pkg_thermal_schedule_work(in + schedule_delayed_work_on(cpu, work, ms); + } + +-static int pkg_thermal_notify(u64 msr_val) ++static void pkg_thermal_notify_work(struct swork_event *event) + { + int cpu = smp_processor_id(); + struct pkg_device *pkgdev; +@@ -348,9 +349,47 @@ static int pkg_thermal_notify(u64 msr_va + } + + spin_unlock_irqrestore(&pkg_temp_lock, flags); ++} ++ ++#ifdef CONFIG_PREEMPT_RT_FULL ++static struct swork_event notify_work; ++ ++static int pkg_thermal_notify_work_init(void) ++{ ++ int err; ++ ++ err = swork_get(); ++ if (err) ++ return err; ++ ++ INIT_SWORK(¬ify_work, pkg_thermal_notify_work); + return 0; + } + ++static void pkg_thermal_notify_work_cleanup(void) ++{ ++ swork_put(); ++} ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ swork_queue(¬ify_work); ++ return 0; ++} ++ ++#else /* !CONFIG_PREEMPT_RT_FULL */ ++ ++static int pkg_thermal_notify_work_init(void) { return 0; } ++ ++static void pkg_thermal_notify_work_cleanup(void) { } ++ ++static int pkg_thermal_notify(u64 msr_val) ++{ ++ pkg_thermal_notify_work(NULL); ++ return 0; ++} ++#endif /* CONFIG_PREEMPT_RT_FULL */ ++ + static int pkg_temp_thermal_device_add(unsigned int cpu) + { + int pkgid = topology_logical_package_id(cpu); +@@ -515,11 +554,16 @@ static int __init pkg_temp_thermal_init( + if (!x86_match_cpu(pkg_temp_thermal_ids)) + return -ENODEV; + ++ if (!pkg_thermal_notify_work_init()) ++ return -ENODEV; ++ + max_packages = topology_max_packages(); + packages = kcalloc(max_packages, sizeof(struct pkg_device *), + GFP_KERNEL); +- if (!packages) +- return -ENOMEM; ++ if (!packages) { ++ ret = -ENOMEM; ++ goto err; ++ } + + ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online", + pkg_thermal_cpu_online, pkg_thermal_cpu_offline); +@@ -537,6 +581,7 @@ static int __init pkg_temp_thermal_init( + return 0; + + err: ++ pkg_thermal_notify_work_cleanup(); + kfree(packages); + return ret; + } +@@ -550,6 +595,7 @@ static void __exit pkg_temp_thermal_exit + cpuhp_remove_state(pkg_thermal_hp_state); + debugfs_remove_recursive(debugfs); + kfree(packages); ++ pkg_thermal_notify_work_cleanup(); + } + module_exit(pkg_temp_thermal_exit) + diff --git a/debian/patches/features/all/rt/time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch b/debian/patches/features/all/rt/time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch new file mode 100644 index 000000000..6606d7fcf --- /dev/null +++ b/debian/patches/features/all/rt/time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch @@ -0,0 +1,53 @@ +From: Sebastian Andrzej Siewior +Date: Wed, 15 Nov 2017 17:29:51 +0100 +Subject: [PATCH] time/hrtimer: avoid schedule_work() with interrupts disabled +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +The NOHZ code tries to schedule a workqueue with interrupts disabled. +Since this does not work -RT I am switching it to swork instead. + +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/time/timer.c | 15 +++++++++++---- + 1 file changed, 11 insertions(+), 4 deletions(-) + +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -217,8 +217,7 @@ static DEFINE_PER_CPU(struct timer_base, + static DEFINE_STATIC_KEY_FALSE(timers_nohz_active); + static DEFINE_MUTEX(timer_keys_mutex); + +-static void timer_update_keys(struct work_struct *work); +-static DECLARE_WORK(timer_update_work, timer_update_keys); ++static struct swork_event timer_update_swork; + + #ifdef CONFIG_SMP + unsigned int sysctl_timer_migration = 1; +@@ -236,7 +235,7 @@ static void timers_update_migration(void + static inline void timers_update_migration(void) { } + #endif /* !CONFIG_SMP */ + +-static void timer_update_keys(struct work_struct *work) ++static void timer_update_keys(struct swork_event *event) + { + mutex_lock(&timer_keys_mutex); + timers_update_migration(); +@@ -246,9 +245,17 @@ static void timer_update_keys(struct wor + + void timers_update_nohz(void) + { +- schedule_work(&timer_update_work); ++ swork_queue(&timer_update_swork); + } + ++static __init int hrtimer_init_thread(void) ++{ ++ WARN_ON(swork_get()); ++ INIT_SWORK(&timer_update_swork, timer_update_keys); ++ return 0; ++} ++early_initcall(hrtimer_init_thread); ++ + int timer_migration_handler(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) diff --git a/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch b/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch new file mode 100644 index 000000000..462b24aad --- /dev/null +++ b/debian/patches/features/all/rt/timekeeping-split-jiffies-lock.patch @@ -0,0 +1,157 @@ +Subject: timekeeping: Split jiffies seqlock +From: Thomas Gleixner +Date: Thu, 14 Feb 2013 22:36:59 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Replace jiffies_lock seqlock with a simple seqcounter and a rawlock so +it can be taken in atomic context on RT. + +Signed-off-by: Thomas Gleixner +--- + kernel/time/jiffies.c | 7 ++++--- + kernel/time/tick-common.c | 10 ++++++---- + kernel/time/tick-sched.c | 19 ++++++++++++------- + kernel/time/timekeeping.c | 6 ++++-- + kernel/time/timekeeping.h | 3 ++- + 5 files changed, 28 insertions(+), 17 deletions(-) + +--- a/kernel/time/jiffies.c ++++ b/kernel/time/jiffies.c +@@ -74,7 +74,8 @@ static struct clocksource clocksource_ji + .max_cycles = 10, + }; + +-__cacheline_aligned_in_smp DEFINE_SEQLOCK(jiffies_lock); ++__cacheline_aligned_in_smp DEFINE_RAW_SPINLOCK(jiffies_lock); ++__cacheline_aligned_in_smp seqcount_t jiffies_seq; + + #if (BITS_PER_LONG < 64) + u64 get_jiffies_64(void) +@@ -83,9 +84,9 @@ u64 get_jiffies_64(void) + u64 ret; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + ret = jiffies_64; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + return ret; + } + EXPORT_SYMBOL(get_jiffies_64); +--- a/kernel/time/tick-common.c ++++ b/kernel/time/tick-common.c +@@ -79,13 +79,15 @@ int tick_is_oneshot_available(void) + static void tick_periodic(int cpu) + { + if (tick_do_timer_cpu == cpu) { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + /* Keep track of the next tick event */ + tick_next_period = ktime_add(tick_next_period, tick_period); + + do_timer(1); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -157,9 +159,9 @@ void tick_setup_periodic(struct clock_ev + ktime_t next; + + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + next = tick_next_period; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + + clockevents_switch_state(dev, CLOCK_EVT_STATE_ONESHOT); + +--- a/kernel/time/tick-sched.c ++++ b/kernel/time/tick-sched.c +@@ -67,7 +67,8 @@ static void tick_do_update_jiffies64(kti + return; + + /* Reevaluate with jiffies_lock held */ +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + + delta = ktime_sub(now, last_jiffies_update); + if (delta >= tick_period) { +@@ -90,10 +91,12 @@ static void tick_do_update_jiffies64(kti + /* Keep the tick_next_period variable up to date */ + tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return; + } +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } + +@@ -104,12 +107,14 @@ static ktime_t tick_init_jiffy_update(vo + { + ktime_t period; + +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + /* Did we start the jiffies update yet ? */ + if (last_jiffies_update == 0) + last_jiffies_update = tick_next_period; + period = last_jiffies_update; +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + return period; + } + +@@ -652,10 +657,10 @@ static ktime_t tick_nohz_next_event(stru + + /* Read jiffies and the time when jiffies were updated last */ + do { +- seq = read_seqbegin(&jiffies_lock); ++ seq = read_seqcount_begin(&jiffies_seq); + basemono = last_jiffies_update; + basejiff = jiffies; +- } while (read_seqretry(&jiffies_lock, seq)); ++ } while (read_seqcount_retry(&jiffies_seq, seq)); + ts->last_jiffies = basejiff; + ts->timer_expires_base = basemono; + +--- a/kernel/time/timekeeping.c ++++ b/kernel/time/timekeeping.c +@@ -2362,8 +2362,10 @@ EXPORT_SYMBOL(hardpps); + */ + void xtime_update(unsigned long ticks) + { +- write_seqlock(&jiffies_lock); ++ raw_spin_lock(&jiffies_lock); ++ write_seqcount_begin(&jiffies_seq); + do_timer(ticks); +- write_sequnlock(&jiffies_lock); ++ write_seqcount_end(&jiffies_seq); ++ raw_spin_unlock(&jiffies_lock); + update_wall_time(); + } +--- a/kernel/time/timekeeping.h ++++ b/kernel/time/timekeeping.h +@@ -18,7 +18,8 @@ extern void timekeeping_resume(void); + extern void do_timer(unsigned long ticks); + extern void update_wall_time(void); + +-extern seqlock_t jiffies_lock; ++extern raw_spinlock_t jiffies_lock; ++extern seqcount_t jiffies_seq; + + #define CS_NAME_LEN 32 + diff --git a/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch b/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch new file mode 100644 index 000000000..f469db97e --- /dev/null +++ b/debian/patches/features/all/rt/timers-prepare-for-full-preemption.patch @@ -0,0 +1,167 @@ +From: Ingo Molnar +Date: Fri, 3 Jul 2009 08:29:34 -0500 +Subject: timers: Prepare for full preemption +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When softirqs can be preempted we need to make sure that cancelling +the timer from the active thread can not deadlock vs. a running timer +callback. Add a waitqueue to resolve that. + +Signed-off-by: Ingo Molnar +Signed-off-by: Thomas Gleixner + +--- + include/linux/timer.h | 2 +- + kernel/sched/core.c | 9 +++++++-- + kernel/time/timer.c | 45 +++++++++++++++++++++++++++++++++++++++++---- + 3 files changed, 49 insertions(+), 7 deletions(-) + +--- a/include/linux/timer.h ++++ b/include/linux/timer.h +@@ -172,7 +172,7 @@ extern void add_timer(struct timer_list + + extern int try_to_del_timer_sync(struct timer_list *timer); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + extern int del_timer_sync(struct timer_list *timer); + #else + # define del_timer_sync(t) del_timer(t) +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -503,11 +503,14 @@ void resched_cpu(int cpu) + */ + int get_nohz_timer_target(void) + { +- int i, cpu = smp_processor_id(); ++ int i, cpu; + struct sched_domain *sd; + ++ preempt_disable_rt(); ++ cpu = smp_processor_id(); ++ + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) +- return cpu; ++ goto preempt_en_rt; + + rcu_read_lock(); + for_each_domain(cpu, sd) { +@@ -526,6 +529,8 @@ int get_nohz_timer_target(void) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); + unlock: + rcu_read_unlock(); ++preempt_en_rt: ++ preempt_enable_rt(); + return cpu; + } + +--- a/kernel/time/timer.c ++++ b/kernel/time/timer.c +@@ -44,6 +44,7 @@ + #include + #include + #include ++#include + + #include + #include +@@ -197,6 +198,9 @@ EXPORT_SYMBOL(jiffies_64); + struct timer_base { + raw_spinlock_t lock; + struct timer_list *running_timer; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ struct swait_queue_head wait_for_running_timer; ++#endif + unsigned long clk; + unsigned long next_expiry; + unsigned int cpu; +@@ -1178,6 +1182,33 @@ void add_timer_on(struct timer_list *tim + } + EXPORT_SYMBOL_GPL(add_timer_on); + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Wait for a running timer ++ */ ++static void wait_for_running_timer(struct timer_list *timer) ++{ ++ struct timer_base *base; ++ u32 tf = timer->flags; ++ ++ if (tf & TIMER_MIGRATING) ++ return; ++ ++ base = get_timer_base(tf); ++ swait_event(base->wait_for_running_timer, ++ base->running_timer != timer); ++} ++ ++# define wakeup_timer_waiters(b) swake_up_all(&(b)->wait_for_running_timer) ++#else ++static inline void wait_for_running_timer(struct timer_list *timer) ++{ ++ cpu_relax(); ++} ++ ++# define wakeup_timer_waiters(b) do { } while (0) ++#endif ++ + /** + * del_timer - deactivate a timer. + * @timer: the timer to be deactivated +@@ -1233,7 +1264,7 @@ int try_to_del_timer_sync(struct timer_l + } + EXPORT_SYMBOL(try_to_del_timer_sync); + +-#ifdef CONFIG_SMP ++#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT_RT_FULL) + /** + * del_timer_sync - deactivate a timer and wait for the handler to finish. + * @timer: the timer to be deactivated +@@ -1293,7 +1324,7 @@ int del_timer_sync(struct timer_list *ti + int ret = try_to_del_timer_sync(timer); + if (ret >= 0) + return ret; +- cpu_relax(); ++ wait_for_running_timer(timer); + } + } + EXPORT_SYMBOL(del_timer_sync); +@@ -1354,13 +1385,16 @@ static void expire_timers(struct timer_b + + fn = timer->function; + +- if (timer->flags & TIMER_IRQSAFE) { ++ if (!IS_ENABLED(CONFIG_PREEMPT_RT_FULL) && ++ timer->flags & TIMER_IRQSAFE) { + raw_spin_unlock(&base->lock); + call_timer_fn(timer, fn); ++ base->running_timer = NULL; + raw_spin_lock(&base->lock); + } else { + raw_spin_unlock_irq(&base->lock); + call_timer_fn(timer, fn); ++ base->running_timer = NULL; + raw_spin_lock_irq(&base->lock); + } + } +@@ -1665,8 +1699,8 @@ static inline void __run_timers(struct t + while (levels--) + expire_timers(base, heads + levels); + } +- base->running_timer = NULL; + raw_spin_unlock_irq(&base->lock); ++ wakeup_timer_waiters(base); + } + + /* +@@ -1924,6 +1958,9 @@ static void __init init_timer_cpu(int cp + base->cpu = cpu; + raw_spin_lock_init(&base->lock); + base->clk = jiffies; ++#ifdef CONFIG_PREEMPT_RT_FULL ++ init_swait_queue_head(&base->wait_for_running_timer); ++#endif + } + } + diff --git a/debian/patches/features/all/rt/tpm_tis-fix-stall-after-iowrite-s.patch b/debian/patches/features/all/rt/tpm_tis-fix-stall-after-iowrite-s.patch new file mode 100644 index 000000000..15dea7d70 --- /dev/null +++ b/debian/patches/features/all/rt/tpm_tis-fix-stall-after-iowrite-s.patch @@ -0,0 +1,78 @@ +From: Haris Okanovic +Date: Tue, 15 Aug 2017 15:13:08 -0500 +Subject: [PATCH] tpm_tis: fix stall after iowrite*()s +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +ioread8() operations to TPM MMIO addresses can stall the cpu when +immediately following a sequence of iowrite*()'s to the same region. + +For example, cyclitest measures ~400us latency spikes when a non-RT +usermode application communicates with an SPI-based TPM chip (Intel Atom +E3940 system, PREEMPT_RT_FULL kernel). The spikes are caused by a +stalling ioread8() operation following a sequence of 30+ iowrite8()s to +the same address. I believe this happens because the write sequence is +buffered (in cpu or somewhere along the bus), and gets flushed on the +first LOAD instruction (ioread*()) that follows. + +The enclosed change appears to fix this issue: read the TPM chip's +access register (status code) after every iowrite*() operation to +amortize the cost of flushing data to chip across multiple instructions. + +Signed-off-by: Haris Okanovic +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/char/tpm/tpm_tis.c | 29 +++++++++++++++++++++++++++-- + 1 file changed, 27 insertions(+), 2 deletions(-) + +--- a/drivers/char/tpm/tpm_tis.c ++++ b/drivers/char/tpm/tpm_tis.c +@@ -53,6 +53,31 @@ static inline struct tpm_tis_tcg_phy *to + return container_of(data, struct tpm_tis_tcg_phy, priv); + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++/* ++ * Flushes previous write operations to chip so that a subsequent ++ * ioread*()s won't stall a cpu. ++ */ ++static inline void tpm_tis_flush(void __iomem *iobase) ++{ ++ ioread8(iobase + TPM_ACCESS(0)); ++} ++#else ++#define tpm_tis_flush(iobase) do { } while (0) ++#endif ++ ++static inline void tpm_tis_iowrite8(u8 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite8(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ ++static inline void tpm_tis_iowrite32(u32 b, void __iomem *iobase, u32 addr) ++{ ++ iowrite32(b, iobase + addr); ++ tpm_tis_flush(iobase); ++} ++ + static bool interrupts = true; + module_param(interrupts, bool, 0444); + MODULE_PARM_DESC(interrupts, "Enable interrupts"); +@@ -150,7 +175,7 @@ static int tpm_tcg_write_bytes(struct tp + struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); + + while (len--) +- iowrite8(*value++, phy->iobase + addr); ++ tpm_tis_iowrite8(*value++, phy->iobase, addr); + + return 0; + } +@@ -177,7 +202,7 @@ static int tpm_tcg_write32(struct tpm_ti + { + struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data); + +- iowrite32(value, phy->iobase + addr); ++ tpm_tis_iowrite32(value, phy->iobase, addr); + + return 0; + } diff --git a/debian/patches/features/all/rt/tty-serial-8250-don-t-take-the-trylock-during-oops.patch b/debian/patches/features/all/rt/tty-serial-8250-don-t-take-the-trylock-during-oops.patch new file mode 100644 index 000000000..860caf630 --- /dev/null +++ b/debian/patches/features/all/rt/tty-serial-8250-don-t-take-the-trylock-during-oops.patch @@ -0,0 +1,29 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 11 Apr 2016 16:55:02 +0200 +Subject: [PATCH] tty: serial: 8250: don't take the trylock during oops +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +An oops with irqs off (panic() from irqsafe hrtimer like the watchdog +timer) will lead to a lockdep warning on each invocation and as such +never completes. +Therefore we skip the trylock in the oops case. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/tty/serial/8250/8250_port.c | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +--- a/drivers/tty/serial/8250/8250_port.c ++++ b/drivers/tty/serial/8250/8250_port.c +@@ -3222,10 +3222,8 @@ void serial8250_console_write(struct uar + + serial8250_rpm_get(up); + +- if (port->sysrq) ++ if (port->sysrq || oops_in_progress) + locked = 0; +- else if (oops_in_progress) +- locked = spin_trylock_irqsave(&port->lock, flags); + else + spin_lock_irqsave(&port->lock, flags); + diff --git a/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch b/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch new file mode 100644 index 000000000..93642a564 --- /dev/null +++ b/debian/patches/features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch @@ -0,0 +1,67 @@ +Subject: net: Remove preemption disabling in netif_rx() +From: Priyanka Jain +Date: Thu, 17 May 2012 09:35:11 +0530 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +1)enqueue_to_backlog() (called from netif_rx) should be + bind to a particluar CPU. This can be achieved by + disabling migration. No need to disable preemption + +2)Fixes crash "BUG: scheduling while atomic: ksoftirqd" + in case of RT. + If preemption is disabled, enqueue_to_backog() is called + in atomic context. And if backlog exceeds its count, + kfree_skb() is called. But in RT, kfree_skb() might + gets scheduled out, so it expects non atomic context. + +3)When CONFIG_PREEMPT_RT_FULL is not defined, + migrate_enable(), migrate_disable() maps to + preempt_enable() and preempt_disable(), so no + change in functionality in case of non-RT. + +-Replace preempt_enable(), preempt_disable() with + migrate_enable(), migrate_disable() respectively +-Replace get_cpu(), put_cpu() with get_cpu_light(), + put_cpu_light() respectively + +Signed-off-by: Priyanka Jain +Acked-by: Rajan Srivastava +Cc: +Link: http://lkml.kernel.org/r/1337227511-2271-1-git-send-email-Priyanka.Jain@freescale.com + +Signed-off-by: Thomas Gleixner +--- + Testing: Tested successfully on p4080ds(8-core SMP system) + + net/core/dev.c | 8 ++++---- + 1 file changed, 4 insertions(+), 4 deletions(-) + +--- a/net/core/dev.c ++++ b/net/core/dev.c +@@ -4210,7 +4210,7 @@ static int netif_rx_internal(struct sk_b + struct rps_dev_flow voidflow, *rflow = &voidflow; + int cpu; + +- preempt_disable(); ++ migrate_disable(); + rcu_read_lock(); + + cpu = get_rps_cpu(skb->dev, skb, &rflow); +@@ -4220,14 +4220,14 @@ static int netif_rx_internal(struct sk_b + ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); + + rcu_read_unlock(); +- preempt_enable(); ++ migrate_enable(); + } else + #endif + { + unsigned int qtail; + +- ret = enqueue_to_backlog(skb, get_cpu(), &qtail); +- put_cpu(); ++ ret = enqueue_to_backlog(skb, get_cpu_light(), &qtail); ++ put_cpu_light(); + } + return ret; + } diff --git a/debian/patches/features/all/rt/usb-do-not-disable-interrupts-in-giveback.patch b/debian/patches/features/all/rt/usb-do-not-disable-interrupts-in-giveback.patch new file mode 100644 index 000000000..eb35eb09b --- /dev/null +++ b/debian/patches/features/all/rt/usb-do-not-disable-interrupts-in-giveback.patch @@ -0,0 +1,40 @@ +From: Sebastian Andrzej Siewior +Date: Fri, 8 Nov 2013 17:34:54 +0100 +Subject: usb: do no disable interrupts in giveback +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Since commit 94dfd7ed ("USB: HCD: support giveback of URB in tasklet +context") the USB code disables interrupts before invoking the complete +callback. +This should not be required the HCD completes the URBs either in hard-irq +context or in BH context. Lockdep may report false positives if one has two +HCDs (one completes in IRQ and the other in BH context) and is using the same +USB driver (device) with both HCDs. This is safe since the same URBs are never +mixed with those two HCDs. +Longeterm we should force all HCDs to complete in the same context. + +Signed-off-by: Sebastian Andrzej Siewior +--- + drivers/usb/core/hcd.c | 3 --- + 1 file changed, 3 deletions(-) + +--- a/drivers/usb/core/hcd.c ++++ b/drivers/usb/core/hcd.c +@@ -1738,7 +1738,6 @@ static void __usb_hcd_giveback_urb(struc + struct usb_hcd *hcd = bus_to_hcd(urb->dev->bus); + struct usb_anchor *anchor = urb->anchor; + int status = urb->unlinked; +- unsigned long flags; + + urb->hcpriv = NULL; + if (unlikely((urb->transfer_flags & URB_SHORT_NOT_OK) && +@@ -1766,9 +1765,7 @@ static void __usb_hcd_giveback_urb(struc + * and no one may trigger the above deadlock situation when + * running complete() in tasklet. + */ +- local_irq_save(flags); + urb->complete(urb); +- local_irq_restore(flags); + + usb_anchor_resume_wakeups(anchor); + atomic_dec(&urb->use_count); diff --git a/debian/patches/features/all/rt/wait.h-include-atomic.h.patch b/debian/patches/features/all/rt/wait.h-include-atomic.h.patch new file mode 100644 index 000000000..358fdd08e --- /dev/null +++ b/debian/patches/features/all/rt/wait.h-include-atomic.h.patch @@ -0,0 +1,33 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 28 Oct 2013 12:19:57 +0100 +Subject: wait.h: include atomic.h +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +| CC init/main.o +|In file included from include/linux/mmzone.h:9:0, +| from include/linux/gfp.h:4, +| from include/linux/kmod.h:22, +| from include/linux/module.h:13, +| from init/main.c:15: +|include/linux/wait.h: In function ‘wait_on_atomic_t’: +|include/linux/wait.h:982:2: error: implicit declaration of function ‘atomic_read’ [-Werror=implicit-function-declaration] +| if (atomic_read(val) == 0) +| ^ + +This pops up on ARM. Non-RT gets its atomic.h include from spinlock.h + +Signed-off-by: Sebastian Andrzej Siewior +--- + include/linux/wait.h | 1 + + 1 file changed, 1 insertion(+) + +--- a/include/linux/wait.h ++++ b/include/linux/wait.h +@@ -10,6 +10,7 @@ + + #include + #include ++#include + + typedef struct wait_queue_entry wait_queue_entry_t; + diff --git a/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch b/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch new file mode 100644 index 000000000..2993c2637 --- /dev/null +++ b/debian/patches/features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch @@ -0,0 +1,133 @@ +From: Thomas Gleixner +Date: Mon, 01 Jul 2013 11:02:42 +0200 +Subject: workqueue: Prevent workqueue versus ata-piix livelock +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +An Intel i7 system regularly detected rcu_preempt stalls after the kernel +was upgraded from 3.6-rt to 3.8-rt. When the stall happened, disk I/O was no +longer possible, unless the system was restarted. + +The kernel message was: +INFO: rcu_preempt self-detected stall on CPU { 6} +[..] +NMI backtrace for cpu 6 +CPU 6 +Pid: 119, comm: irq/19-ata_piix Not tainted 3.8.13-rt13 #11 Shuttle Inc. SX58/SX58 +RIP: 0010:[] [] ip_compute_csum+0x30/0x30 +RSP: 0018:ffff880333303cb0 EFLAGS: 00000002 +RAX: 0000000000000006 RBX: 00000000000003e9 RCX: 0000000000000034 +RDX: 0000000000000000 RSI: ffffffff81aa16d0 RDI: 0000000000000001 +RBP: ffff880333303ce8 R08: ffffffff81aa16d0 R09: ffffffff81c1b8cc +R10: 0000000000000000 R11: 0000000000000000 R12: 000000000005161f +R13: 0000000000000006 R14: ffffffff81aa16d0 R15: 0000000000000002 +FS: 0000000000000000(0000) GS:ffff880333300000(0000) knlGS:0000000000000000 +CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b +CR2: 0000003c1b2bb420 CR3: 0000000001a0f000 CR4: 00000000000007e0 +DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 +DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 +Process irq/19-ata_piix (pid: 119, threadinfo ffff88032d88a000, task ffff88032df80000) +Stack: +ffffffff8124cb32 000000000005161e 00000000000003e9 0000000000001000 +0000000000009022 ffffffff81aa16d0 0000000000000002 ffff880333303cf8 +ffffffff8124caa9 ffff880333303d08 ffffffff8124cad2 ffff880333303d28 +Call Trace: + +[] ? delay_tsc+0x33/0xe3 +[] __delay+0xf/0x11 +[] __const_udelay+0x27/0x29 +[] native_safe_apic_wait_icr_idle+0x39/0x45 +[] __default_send_IPI_dest_field.constprop.0+0x1e/0x58 +[] default_send_IPI_mask_sequence_phys+0x49/0x7d +[] physflat_send_IPI_all+0x17/0x19 +[] arch_trigger_all_cpu_backtrace+0x50/0x79 +[] rcu_check_callbacks+0x1cb/0x568 +[] ? raise_softirq+0x2e/0x35 +[] ? tick_sched_do_timer+0x38/0x38 +[] update_process_times+0x44/0x55 +[] tick_sched_handle+0x4a/0x59 +[] tick_sched_timer+0x3c/0x5b +[] __run_hrtimer+0x9b/0x158 +[] hrtimer_interrupt+0x172/0x2aa +[] smp_apic_timer_interrupt+0x76/0x89 +[] apic_timer_interrupt+0x6d/0x80 + +[] ? __local_lock_irqsave+0x17/0x4a +[] try_to_grab_pending+0x42/0x17e +[] mod_delayed_work_on+0x32/0x88 +[] mod_delayed_work+0x1c/0x1e +[] blk_run_queue_async+0x37/0x39 +[] flush_end_io+0xf1/0x107 +[] blk_finish_request+0x21e/0x264 +[] blk_end_bidi_request+0x42/0x60 +[] blk_end_request+0x10/0x12 +[] scsi_io_completion+0x1bf/0x492 +[] ? sd_done+0x298/0x2ef +[] scsi_finish_command+0xe9/0xf2 +[] scsi_softirq_done+0x106/0x10f +[] blk_done_softirq+0x77/0x87 +[] do_current_softirqs+0x172/0x2e1 +[] ? irq_thread_fn+0x3a/0x3a +[] local_bh_enable+0x43/0x72 +[] irq_forced_thread_fn+0x46/0x52 +[] irq_thread+0x8c/0x17c +[] ? irq_thread+0x17c/0x17c +[] ? wake_threads_waitq+0x44/0x44 +[] kthread+0x8d/0x95 +[] ? __kthread_parkme+0x65/0x65 +[] ret_from_fork+0x7c/0xb0 +[] ? __kthread_parkme+0x65/0x65 + +The state of softirqd of this CPU at the time of the crash was: +ksoftirqd/6 R running task 0 53 2 0x00000000 +ffff88032fc39d18 0000000000000046 ffff88033330c4c0 ffff8803303f4710 +ffff88032fc39fd8 ffff88032fc39fd8 0000000000000000 0000000000062500 +ffff88032df88000 ffff8803303f4710 0000000000000000 ffff88032fc38000 +Call Trace: +[] ? __queue_work+0x27c/0x27c +[] preempt_schedule+0x61/0x76 +[] migrate_enable+0xe5/0x1df +[] ? __queue_work+0x27c/0x27c +[] run_timer_softirq+0x161/0x1d6 +[] do_current_softirqs+0x172/0x2e1 +[] run_ksoftirqd+0x2d/0x45 +[] smpboot_thread_fn+0x2ea/0x308 +[] ? test_ti_thread_flag+0xc/0xc +[] ? test_ti_thread_flag+0xc/0xc +[] kthread+0x8d/0x95 +[] ? __kthread_parkme+0x65/0x65 +[] ret_from_fork+0x7c/0xb0 +[] ? __kthread_parkme+0x65/0x65 + +Apparently, the softirq demon and the ata_piix IRQ handler were waiting +for each other to finish ending up in a livelock. After the below patch +was applied, the system no longer crashes. + +Reported-by: Carsten Emde +Proposed-by: Thomas Gleixner +Tested by: Carsten Emde +Signed-off-by: Carsten Emde +Signed-off-by: Thomas Gleixner +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/workqueue.c | 3 ++- + 1 file changed, 2 insertions(+), 1 deletion(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -50,6 +50,7 @@ + #include + #include + #include ++#include + + #include "workqueue_internal.h" + +@@ -1281,7 +1282,7 @@ static int try_to_grab_pending(struct wo + local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; +- cpu_relax(); ++ cpu_chill(); + return -EAGAIN; + } + diff --git a/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch b/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch new file mode 100644 index 000000000..dc9d3ea76 --- /dev/null +++ b/debian/patches/features/all/rt/work-simple-Simple-work-queue-implemenation.patch @@ -0,0 +1,232 @@ +From: Daniel Wagner +Date: Fri, 11 Jul 2014 15:26:11 +0200 +Subject: work-simple: Simple work queue implemenation +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Provides a framework for enqueuing callbacks from irq context +PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. + +Bases on wait-simple. + +Cc: Sebastian Andrzej Siewior +Signed-off-by: Daniel Wagner +--- + include/linux/swork.h | 24 ++++++ + kernel/sched/Makefile | 2 + kernel/sched/swork.c | 173 ++++++++++++++++++++++++++++++++++++++++++++++++++ + 3 files changed, 198 insertions(+), 1 deletion(-) + +--- /dev/null ++++ b/include/linux/swork.h +@@ -0,0 +1,24 @@ ++#ifndef _LINUX_SWORK_H ++#define _LINUX_SWORK_H ++ ++#include ++ ++struct swork_event { ++ struct list_head item; ++ unsigned long flags; ++ void (*func)(struct swork_event *); ++}; ++ ++static inline void INIT_SWORK(struct swork_event *event, ++ void (*func)(struct swork_event *)) ++{ ++ event->flags = 0; ++ event->func = func; ++} ++ ++bool swork_queue(struct swork_event *sev); ++ ++int swork_get(void); ++void swork_put(void); ++ ++#endif /* _LINUX_SWORK_H */ +--- a/kernel/sched/Makefile ++++ b/kernel/sched/Makefile +@@ -18,7 +18,7 @@ endif + + obj-y += core.o loadavg.o clock.o cputime.o + obj-y += idle.o fair.o rt.o deadline.o +-obj-y += wait.o wait_bit.o swait.o completion.o ++obj-y += wait.o wait_bit.o swait.o swork.o completion.o + + obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o + obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o +--- /dev/null ++++ b/kernel/sched/swork.c +@@ -0,0 +1,173 @@ ++/* ++ * Copyright (C) 2014 BMW Car IT GmbH, Daniel Wagner daniel.wagner@bmw-carit.de ++ * ++ * Provides a framework for enqueuing callbacks from irq context ++ * PREEMPT_RT_FULL safe. The callbacks are executed in kthread context. ++ */ ++ ++#include ++#include ++#include ++#include ++#include ++#include ++ ++#define SWORK_EVENT_PENDING (1 << 0) ++ ++static DEFINE_MUTEX(worker_mutex); ++static struct sworker *glob_worker; ++ ++struct sworker { ++ struct list_head events; ++ struct swait_queue_head wq; ++ ++ raw_spinlock_t lock; ++ ++ struct task_struct *task; ++ int refs; ++}; ++ ++static bool swork_readable(struct sworker *worker) ++{ ++ bool r; ++ ++ if (kthread_should_stop()) ++ return true; ++ ++ raw_spin_lock_irq(&worker->lock); ++ r = !list_empty(&worker->events); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ return r; ++} ++ ++static int swork_kthread(void *arg) ++{ ++ struct sworker *worker = arg; ++ ++ for (;;) { ++ swait_event_interruptible(worker->wq, ++ swork_readable(worker)); ++ if (kthread_should_stop()) ++ break; ++ ++ raw_spin_lock_irq(&worker->lock); ++ while (!list_empty(&worker->events)) { ++ struct swork_event *sev; ++ ++ sev = list_first_entry(&worker->events, ++ struct swork_event, item); ++ list_del(&sev->item); ++ raw_spin_unlock_irq(&worker->lock); ++ ++ WARN_ON_ONCE(!test_and_clear_bit(SWORK_EVENT_PENDING, ++ &sev->flags)); ++ sev->func(sev); ++ raw_spin_lock_irq(&worker->lock); ++ } ++ raw_spin_unlock_irq(&worker->lock); ++ } ++ return 0; ++} ++ ++static struct sworker *swork_create(void) ++{ ++ struct sworker *worker; ++ ++ worker = kzalloc(sizeof(*worker), GFP_KERNEL); ++ if (!worker) ++ return ERR_PTR(-ENOMEM); ++ ++ INIT_LIST_HEAD(&worker->events); ++ raw_spin_lock_init(&worker->lock); ++ init_swait_queue_head(&worker->wq); ++ ++ worker->task = kthread_run(swork_kthread, worker, "kswork"); ++ if (IS_ERR(worker->task)) { ++ kfree(worker); ++ return ERR_PTR(-ENOMEM); ++ } ++ ++ return worker; ++} ++ ++static void swork_destroy(struct sworker *worker) ++{ ++ kthread_stop(worker->task); ++ ++ WARN_ON(!list_empty(&worker->events)); ++ kfree(worker); ++} ++ ++/** ++ * swork_queue - queue swork ++ * ++ * Returns %false if @work was already on a queue, %true otherwise. ++ * ++ * The work is queued and processed on a random CPU ++ */ ++bool swork_queue(struct swork_event *sev) ++{ ++ unsigned long flags; ++ ++ if (test_and_set_bit(SWORK_EVENT_PENDING, &sev->flags)) ++ return false; ++ ++ raw_spin_lock_irqsave(&glob_worker->lock, flags); ++ list_add_tail(&sev->item, &glob_worker->events); ++ raw_spin_unlock_irqrestore(&glob_worker->lock, flags); ++ ++ swake_up(&glob_worker->wq); ++ return true; ++} ++EXPORT_SYMBOL_GPL(swork_queue); ++ ++/** ++ * swork_get - get an instance of the sworker ++ * ++ * Returns an negative error code if the initialization if the worker did not ++ * work, %0 otherwise. ++ * ++ */ ++int swork_get(void) ++{ ++ struct sworker *worker; ++ ++ mutex_lock(&worker_mutex); ++ if (!glob_worker) { ++ worker = swork_create(); ++ if (IS_ERR(worker)) { ++ mutex_unlock(&worker_mutex); ++ return -ENOMEM; ++ } ++ ++ glob_worker = worker; ++ } ++ ++ glob_worker->refs++; ++ mutex_unlock(&worker_mutex); ++ ++ return 0; ++} ++EXPORT_SYMBOL_GPL(swork_get); ++ ++/** ++ * swork_put - puts an instance of the sworker ++ * ++ * Will destroy the sworker thread. This function must not be called until all ++ * queued events have been completed. ++ */ ++void swork_put(void) ++{ ++ mutex_lock(&worker_mutex); ++ ++ glob_worker->refs--; ++ if (glob_worker->refs > 0) ++ goto out; ++ ++ swork_destroy(glob_worker); ++ glob_worker = NULL; ++out: ++ mutex_unlock(&worker_mutex); ++} ++EXPORT_SYMBOL_GPL(swork_put); diff --git a/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch b/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch new file mode 100644 index 000000000..8cc2c4861 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-distangle-from-rq-lock.patch @@ -0,0 +1,282 @@ +From: Thomas Gleixner +Date: Wed Jun 22 19:47:03 2011 +0200 +Subject: sched: Distangle worker accounting from rqlock + +The worker accounting for cpu bound workers is plugged into the core +scheduler code and the wakeup code. This is not a hard requirement and +can be avoided by keeping track of the state in the workqueue code +itself. + +Keep track of the sleeping state in the worker itself and call the +notifier before entering the core scheduler. There might be false +positives when the task is woken between that call and actually +scheduling, but that's not really different from scheduling and being +woken immediately after switching away. There is also no harm from +updating nr_running when the task returns from scheduling instead of +accounting it in the wakeup code. + +Signed-off-by: Thomas Gleixner +Cc: Peter Zijlstra +Cc: Tejun Heo +Cc: Jens Axboe +Cc: Linus Torvalds +Link: http://lkml.kernel.org/r/20110622174919.135236139@linutronix.de +Signed-off-by: Thomas Gleixner +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +[bigeasy: preempt_disable() around wq_worker_sleeping() by Daniel Bristot de + Oliveira] +Signed-off-by: Sebastian Andrzej Siewior +--- + kernel/sched/core.c | 90 ++++++++++---------------------------------- + kernel/workqueue.c | 52 +++++++++++-------------- + kernel/workqueue_internal.h | 5 +- + 3 files changed, 47 insertions(+), 100 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -1722,10 +1722,6 @@ static inline void ttwu_activate(struct + { + activate_task(rq, p, en_flags); + p->on_rq = TASK_ON_RQ_QUEUED; +- +- /* If a worker is waking up, notify the workqueue: */ +- if (p->flags & PF_WQ_WORKER) +- wq_worker_waking_up(p, cpu_of(rq)); + } + + /* +@@ -2166,56 +2162,6 @@ try_to_wake_up(struct task_struct *p, un + } + + /** +- * try_to_wake_up_local - try to wake up a local task with rq lock held +- * @p: the thread to be awakened +- * @rf: request-queue flags for pinning +- * +- * Put @p on the run-queue if it's not already there. The caller must +- * ensure that this_rq() is locked, @p is bound to this_rq() and not +- * the current task. +- */ +-static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) +-{ +- struct rq *rq = task_rq(p); +- +- if (WARN_ON_ONCE(rq != this_rq()) || +- WARN_ON_ONCE(p == current)) +- return; +- +- lockdep_assert_held(&rq->lock); +- +- if (!raw_spin_trylock(&p->pi_lock)) { +- /* +- * This is OK, because current is on_cpu, which avoids it being +- * picked for load-balance and preemption/IRQs are still +- * disabled avoiding further scheduler activity on it and we've +- * not yet picked a replacement task. +- */ +- rq_unlock(rq, rf); +- raw_spin_lock(&p->pi_lock); +- rq_relock(rq, rf); +- } +- +- if (!(p->state & TASK_NORMAL)) +- goto out; +- +- trace_sched_waking(p); +- +- if (!task_on_rq_queued(p)) { +- if (p->in_iowait) { +- delayacct_blkio_end(p); +- atomic_dec(&rq->nr_iowait); +- } +- ttwu_activate(rq, p, ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK); +- } +- +- ttwu_do_wakeup(rq, p, 0, rf); +- ttwu_stat(p, smp_processor_id(), 0); +-out: +- raw_spin_unlock(&p->pi_lock); +-} +- +-/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * +@@ -3541,21 +3487,6 @@ static void __sched notrace __schedule(b + atomic_inc(&rq->nr_iowait); + delayacct_blkio_start(); + } +- +- /* +- * If a worker went to sleep, notify and ask workqueue +- * whether it wants to wake up a task to maintain +- * concurrency. +- * Only call wake up if prev isn't blocked on a sleeping +- * spin lock. +- */ +- if (prev->flags & PF_WQ_WORKER && !prev->saved_state) { +- struct task_struct *to_wakeup; +- +- to_wakeup = wq_worker_sleeping(prev); +- if (to_wakeup) +- try_to_wake_up_local(to_wakeup, &rf); +- } + } + switch_count = &prev->nvcsw; + } +@@ -3615,6 +3546,20 @@ static inline void sched_submit_work(str + { + if (!tsk->state || tsk_is_pi_blocked(tsk)) + return; ++ ++ /* ++ * If a worker went to sleep, notify and ask workqueue whether ++ * it wants to wake up a task to maintain concurrency. ++ * As this function is called inside the schedule() context, ++ * we disable preemption to avoid it calling schedule() again ++ * in the possible wakeup of a kworker. ++ */ ++ if (tsk->flags & PF_WQ_WORKER) { ++ preempt_disable(); ++ wq_worker_sleeping(tsk); ++ preempt_enable_no_resched(); ++ } ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +@@ -3623,6 +3568,12 @@ static inline void sched_submit_work(str + blk_schedule_flush_plug(tsk); + } + ++static void sched_update_worker(struct task_struct *tsk) ++{ ++ if (tsk->flags & PF_WQ_WORKER) ++ wq_worker_running(tsk); ++} ++ + asmlinkage __visible void __sched schedule(void) + { + struct task_struct *tsk = current; +@@ -3633,6 +3584,7 @@ asmlinkage __visible void __sched schedu + __schedule(false); + sched_preempt_enable_no_resched(); + } while (need_resched()); ++ sched_update_worker(tsk); + } + EXPORT_SYMBOL(schedule); + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -843,43 +843,32 @@ static void wake_up_worker(struct worker + } + + /** +- * wq_worker_waking_up - a worker is waking up ++ * wq_worker_running - a worker is running again + * @task: task waking up +- * @cpu: CPU @task is waking up to + * +- * This function is called during try_to_wake_up() when a worker is +- * being awoken. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) ++ * This function is called when a worker returns from schedule() + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu) ++void wq_worker_running(struct task_struct *task) + { + struct worker *worker = kthread_data(task); + +- if (!(worker->flags & WORKER_NOT_RUNNING)) { +- WARN_ON_ONCE(worker->pool->cpu != cpu); ++ if (!worker->sleeping) ++ return; ++ if (!(worker->flags & WORKER_NOT_RUNNING)) + atomic_inc(&worker->pool->nr_running); +- } ++ worker->sleeping = 0; + } + + /** + * wq_worker_sleeping - a worker is going to sleep + * @task: task going to sleep + * +- * This function is called during schedule() when a busy worker is +- * going to sleep. Worker on the same cpu can be woken up by +- * returning pointer to its task. +- * +- * CONTEXT: +- * spin_lock_irq(rq->lock) +- * +- * Return: +- * Worker task on @cpu to wake up, %NULL if none. ++ * This function is called from schedule() when a busy worker is ++ * going to sleep. + */ +-struct task_struct *wq_worker_sleeping(struct task_struct *task) ++void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *worker = kthread_data(task), *to_wakeup = NULL; ++ struct worker *next, *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -888,13 +877,15 @@ struct task_struct *wq_worker_sleeping(s + * checking NOT_RUNNING. + */ + if (worker->flags & WORKER_NOT_RUNNING) +- return NULL; ++ return; + + pool = worker->pool; + +- /* this can only happen on the local cpu */ +- if (WARN_ON_ONCE(pool->cpu != raw_smp_processor_id())) +- return NULL; ++ if (WARN_ON_ONCE(worker->sleeping)) ++ return; ++ ++ worker->sleeping = 1; ++ spin_lock_irq(&pool->lock); + + /* + * The counterpart of the following dec_and_test, implied mb, +@@ -908,9 +899,12 @@ struct task_struct *wq_worker_sleeping(s + * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && +- !list_empty(&pool->worklist)) +- to_wakeup = first_idle_worker(pool); +- return to_wakeup ? to_wakeup->task : NULL; ++ !list_empty(&pool->worklist)) { ++ next = first_idle_worker(pool); ++ if (next) ++ wake_up_process(next->task); ++ } ++ spin_unlock_irq(&pool->lock); + } + + /** +--- a/kernel/workqueue_internal.h ++++ b/kernel/workqueue_internal.h +@@ -44,6 +44,7 @@ struct worker { + unsigned long last_active; /* L: last active timestamp */ + unsigned int flags; /* X: flags */ + int id; /* I: worker id */ ++ int sleeping; /* None */ + + /* + * Opaque string set with work_set_desc(). Printed out with task +@@ -69,7 +70,7 @@ static inline struct worker *current_wq_ + * Scheduler hooks for concurrency managed workqueue. Only to be used from + * sched/core.c and workqueue.c. + */ +-void wq_worker_waking_up(struct task_struct *task, int cpu); +-struct task_struct *wq_worker_sleeping(struct task_struct *task); ++void wq_worker_running(struct task_struct *task); ++void wq_worker_sleeping(struct task_struct *task); + + #endif /* _KERNEL_WORKQUEUE_INTERNAL_H */ diff --git a/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch b/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch new file mode 100644 index 000000000..e2cde1c16 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-prevent-deadlock-stall.patch @@ -0,0 +1,200 @@ +Subject: workqueue: Prevent deadlock/stall on RT +From: Thomas Gleixner +Date: Fri, 27 Jun 2014 16:24:52 +0200 (CEST) +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Austin reported a XFS deadlock/stall on RT where scheduled work gets +never exececuted and tasks are waiting for each other for ever. + +The underlying problem is the modification of the RT code to the +handling of workers which are about to go to sleep. In mainline a +worker thread which goes to sleep wakes an idle worker if there is +more work to do. This happens from the guts of the schedule() +function. On RT this must be outside and the accessed data structures +are not protected against scheduling due to the spinlock to rtmutex +conversion. So the naive solution to this was to move the code outside +of the scheduler and protect the data structures by the pool +lock. That approach turned out to be a little naive as we cannot call +into that code when the thread blocks on a lock, as it is not allowed +to block on two locks in parallel. So we dont call into the worker +wakeup magic when the worker is blocked on a lock, which causes the +deadlock/stall observed by Austin and Mike. + +Looking deeper into that worker code it turns out that the only +relevant data structure which needs to be protected is the list of +idle workers which can be woken up. + +So the solution is to protect the list manipulation operations with +preempt_enable/disable pairs on RT and call unconditionally into the +worker code even when the worker is blocked on a lock. The preemption +protection is safe as there is nothing which can fiddle with the list +outside of thread context. + +Reported-and_tested-by: Austin Schuh +Reported-and_tested-by: Mike Galbraith +Signed-off-by: Thomas Gleixner +Link: http://vger.kernel.org/r/alpine.DEB.2.10.1406271249510.5170@nanos +Cc: Richard Weinberger +Cc: Steven Rostedt + +--- + kernel/sched/core.c | 6 +++-- + kernel/workqueue.c | 60 ++++++++++++++++++++++++++++++++++++++++------------ + 2 files changed, 51 insertions(+), 15 deletions(-) + +--- a/kernel/sched/core.c ++++ b/kernel/sched/core.c +@@ -3590,9 +3590,8 @@ void __noreturn do_task_dead(void) + + static inline void sched_submit_work(struct task_struct *tsk) + { +- if (!tsk->state || tsk_is_pi_blocked(tsk)) ++ if (!tsk->state) + return; +- + /* + * If a worker went to sleep, notify and ask workqueue whether + * it wants to wake up a task to maintain concurrency. +@@ -3606,6 +3605,9 @@ static inline void sched_submit_work(str + preempt_enable_no_resched(); + } + ++ if (tsk_is_pi_blocked(tsk)) ++ return; ++ + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -125,6 +125,11 @@ enum { + * cpu or grabbing pool->lock is enough for read access. If + * POOL_DISASSOCIATED is set, it's identical to L. + * ++ * On RT we need the extra protection via rt_lock_idle_list() for ++ * the list manipulations against read access from ++ * wq_worker_sleeping(). All other places are nicely serialized via ++ * pool->lock. ++ * + * A: wq_pool_attach_mutex protected. + * + * PL: wq_pool_mutex protected. +@@ -430,6 +435,31 @@ static void workqueue_sysfs_unregister(s + if (({ assert_rcu_or_wq_mutex(wq); false; })) { } \ + else + ++#ifdef CONFIG_PREEMPT_RT_BASE ++static inline void rt_lock_idle_list(struct worker_pool *pool) ++{ ++ preempt_disable(); ++} ++static inline void rt_unlock_idle_list(struct worker_pool *pool) ++{ ++ preempt_enable(); ++} ++static inline void sched_lock_idle_list(struct worker_pool *pool) { } ++static inline void sched_unlock_idle_list(struct worker_pool *pool) { } ++#else ++static inline void rt_lock_idle_list(struct worker_pool *pool) { } ++static inline void rt_unlock_idle_list(struct worker_pool *pool) { } ++static inline void sched_lock_idle_list(struct worker_pool *pool) ++{ ++ spin_lock_irq(&pool->lock); ++} ++static inline void sched_unlock_idle_list(struct worker_pool *pool) ++{ ++ spin_unlock_irq(&pool->lock); ++} ++#endif ++ ++ + #ifdef CONFIG_DEBUG_OBJECTS_WORK + + static struct debug_obj_descr work_debug_descr; +@@ -836,10 +866,16 @@ static struct worker *first_idle_worker( + */ + static void wake_up_worker(struct worker_pool *pool) + { +- struct worker *worker = first_idle_worker(pool); ++ struct worker *worker; ++ ++ rt_lock_idle_list(pool); ++ ++ worker = first_idle_worker(pool); + + if (likely(worker)) + wake_up_process(worker->task); ++ ++ rt_unlock_idle_list(pool); + } + + /** +@@ -868,7 +904,7 @@ void wq_worker_running(struct task_struc + */ + void wq_worker_sleeping(struct task_struct *task) + { +- struct worker *next, *worker = kthread_data(task); ++ struct worker *worker = kthread_data(task); + struct worker_pool *pool; + + /* +@@ -885,26 +921,18 @@ void wq_worker_sleeping(struct task_stru + return; + + worker->sleeping = 1; +- spin_lock_irq(&pool->lock); + + /* + * The counterpart of the following dec_and_test, implied mb, + * worklist not empty test sequence is in insert_work(). + * Please read comment there. +- * +- * NOT_RUNNING is clear. This means that we're bound to and +- * running on the local cpu w/ rq lock held and preemption +- * disabled, which in turn means that none else could be +- * manipulating idle_list, so dereferencing idle_list without pool +- * lock is safe. + */ + if (atomic_dec_and_test(&pool->nr_running) && + !list_empty(&pool->worklist)) { +- next = first_idle_worker(pool); +- if (next) +- wake_up_process(next->task); ++ sched_lock_idle_list(pool); ++ wake_up_worker(pool); ++ sched_unlock_idle_list(pool); + } +- spin_unlock_irq(&pool->lock); + } + + /** +@@ -1675,7 +1703,9 @@ static void worker_enter_idle(struct wor + worker->last_active = jiffies; + + /* idle_list is LIFO */ ++ rt_lock_idle_list(pool); + list_add(&worker->entry, &pool->idle_list); ++ rt_unlock_idle_list(pool); + + if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) + mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); +@@ -1708,7 +1738,9 @@ static void worker_leave_idle(struct wor + return; + worker_clr_flags(worker, WORKER_IDLE); + pool->nr_idle--; ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + } + + static struct worker *alloc_worker(int node) +@@ -1876,7 +1908,9 @@ static void destroy_worker(struct worker + pool->nr_workers--; + pool->nr_idle--; + ++ rt_lock_idle_list(pool); + list_del_init(&worker->entry); ++ rt_unlock_idle_list(pool); + worker->flags |= WORKER_DIE; + wake_up_process(worker->task); + } diff --git a/debian/patches/features/all/rt/workqueue-use-locallock.patch b/debian/patches/features/all/rt/workqueue-use-locallock.patch new file mode 100644 index 000000000..424c7c5f1 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-use-locallock.patch @@ -0,0 +1,179 @@ +Subject: workqueue: Use local irq lock instead of irq disable regions +From: Thomas Gleixner +Date: Sun, 17 Jul 2011 21:42:26 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Use a local_irq_lock as a replacement for irq off regions. We keep the +semantic of irq-off in regard to the pool->lock and remain preemptible. + +Signed-off-by: Thomas Gleixner +--- + kernel/workqueue.c | 45 ++++++++++++++++++++++++++++++--------------- + 1 file changed, 30 insertions(+), 15 deletions(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -49,6 +49,7 @@ + #include + #include + #include ++#include + + #include "workqueue_internal.h" + +@@ -350,6 +351,8 @@ EXPORT_SYMBOL_GPL(system_power_efficient + struct workqueue_struct *system_freezable_power_efficient_wq __read_mostly; + EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); + ++static DEFINE_LOCAL_IRQ_LOCK(pendingb_lock); ++ + static int worker_thread(void *__worker); + static void workqueue_sysfs_unregister(struct workqueue_struct *wq); + +@@ -1103,9 +1106,11 @@ static void put_pwq_unlocked(struct pool + * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ +- spin_lock_irq(&pwq->pool->lock); ++ rcu_read_lock(); ++ local_spin_lock_irq(pendingb_lock, &pwq->pool->lock); + put_pwq(pwq); +- spin_unlock_irq(&pwq->pool->lock); ++ local_spin_unlock_irq(pendingb_lock, &pwq->pool->lock); ++ rcu_read_unlock(); + } + } + +@@ -1209,7 +1214,7 @@ static int try_to_grab_pending(struct wo + struct worker_pool *pool; + struct pool_workqueue *pwq; + +- local_irq_save(*flags); ++ local_lock_irqsave(pendingb_lock, *flags); + + /* try to steal the timer if it exists */ + if (is_dwork) { +@@ -1273,7 +1278,7 @@ static int try_to_grab_pending(struct wo + spin_unlock(&pool->lock); + fail: + rcu_read_unlock(); +- local_irq_restore(*flags); ++ local_unlock_irqrestore(pendingb_lock, *flags); + if (work_is_canceling(work)) + return -ENOENT; + cpu_relax(); +@@ -1378,7 +1383,13 @@ static void __queue_work(int cpu, struct + * queued or lose PENDING. Grabbing PENDING and queueing should + * happen with IRQ disabled. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL ++ /* ++ * nort: On RT the "interrupts-disabled" rule has been replaced with ++ * pendingb_lock. ++ */ + lockdep_assert_irqs_disabled(); ++#endif + + debug_work_activate(work); + +@@ -1484,14 +1495,14 @@ bool queue_work_on(int cpu, struct workq + bool ret = false; + unsigned long flags; + +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock,flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_work(cpu, wq, work); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_work_on); +@@ -1500,8 +1511,11 @@ void delayed_work_timer_fn(struct timer_ + { + struct delayed_work *dwork = from_timer(dwork, t, timer); + ++ /* XXX */ ++ /* local_lock(pendingb_lock); */ + /* should have been called from irqsafe timer with irq already off */ + __queue_work(dwork->cpu, dwork->wq, &dwork->work); ++ /* local_unlock(pendingb_lock); */ + } + EXPORT_SYMBOL(delayed_work_timer_fn); + +@@ -1556,14 +1570,14 @@ bool queue_delayed_work_on(int cpu, stru + unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_save(flags); ++ local_lock_irqsave(pendingb_lock, flags); + + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) { + __queue_delayed_work(cpu, wq, dwork, delay); + ret = true; + } + +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + EXPORT_SYMBOL(queue_delayed_work_on); +@@ -1598,7 +1612,7 @@ bool mod_delayed_work_on(int cpu, struct + + if (likely(ret >= 0)) { + __queue_delayed_work(cpu, wq, dwork, delay); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /* -ENOENT from try_to_grab_pending() becomes %true */ +@@ -1609,11 +1623,12 @@ EXPORT_SYMBOL_GPL(mod_delayed_work_on); + static void rcu_work_rcufn(struct rcu_head *rcu) + { + struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); ++ unsigned long flags; + + /* read the comment in __queue_work() */ +- local_irq_disable(); ++ local_lock_irqsave(pendingb_lock, flags); + __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); +- local_irq_enable(); ++ local_unlock_irqrestore(pendingb_lock, flags); + } + + /** +@@ -2984,7 +2999,7 @@ static bool __cancel_work_timer(struct w + + /* tell other tasks trying to grab @work to back off */ + mark_work_canceling(work); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + + /* + * This allows canceling during early boot. We know that @work +@@ -3045,10 +3060,10 @@ EXPORT_SYMBOL_GPL(cancel_work_sync); + */ + bool flush_delayed_work(struct delayed_work *dwork) + { +- local_irq_disable(); ++ local_lock_irq(pendingb_lock); + if (del_timer_sync(&dwork->timer)) + __queue_work(dwork->cpu, dwork->wq, &dwork->work); +- local_irq_enable(); ++ local_unlock_irq(pendingb_lock); + return flush_work(&dwork->work); + } + EXPORT_SYMBOL(flush_delayed_work); +@@ -3086,7 +3101,7 @@ static bool __cancel_work(struct work_st + return false; + + set_work_pool_and_clear_pending(work, get_work_pool_id(work)); +- local_irq_restore(flags); ++ local_unlock_irqrestore(pendingb_lock, flags); + return ret; + } + diff --git a/debian/patches/features/all/rt/workqueue-use-rcu.patch b/debian/patches/features/all/rt/workqueue-use-rcu.patch new file mode 100644 index 000000000..a391b7024 --- /dev/null +++ b/debian/patches/features/all/rt/workqueue-use-rcu.patch @@ -0,0 +1,354 @@ +Subject: workqueue: Use normal rcu +From: Thomas Gleixner +Date: Wed, 24 Jul 2013 15:26:54 +0200 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There is no need for sched_rcu. The undocumented reason why sched_rcu +is used is to avoid a few explicit rcu_read_lock()/unlock() pairs by +abusing the fact that sched_rcu reader side critical sections are also +protected by preempt or irq disabled regions. + +Signed-off-by: Thomas Gleixner +--- + kernel/workqueue.c | 95 +++++++++++++++++++++++++++++------------------------ + 1 file changed, 52 insertions(+), 43 deletions(-) + +--- a/kernel/workqueue.c ++++ b/kernel/workqueue.c +@@ -127,7 +127,7 @@ enum { + * + * PL: wq_pool_mutex protected. + * +- * PR: wq_pool_mutex protected for writes. Sched-RCU protected for reads. ++ * PR: wq_pool_mutex protected for writes. RCU protected for reads. + * + * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. + * +@@ -136,7 +136,7 @@ enum { + * + * WQ: wq->mutex protected. + * +- * WR: wq->mutex protected for writes. Sched-RCU protected for reads. ++ * WR: wq->mutex protected for writes. RCU protected for reads. + * + * MD: wq_mayday_lock protected. + */ +@@ -183,7 +183,7 @@ struct worker_pool { + atomic_t nr_running ____cacheline_aligned_in_smp; + + /* +- * Destruction of pool is sched-RCU protected to allow dereferences ++ * Destruction of pool is RCU protected to allow dereferences + * from get_work_pool(). + */ + struct rcu_head rcu; +@@ -212,7 +212,7 @@ struct pool_workqueue { + /* + * Release of unbound pwq is punted to system_wq. See put_pwq() + * and pwq_unbound_release_workfn() for details. pool_workqueue +- * itself is also sched-RCU protected so that the first pwq can be ++ * itself is also RCU protected so that the first pwq can be + * determined without grabbing wq->mutex. + */ + struct work_struct unbound_release_work; +@@ -357,20 +357,20 @@ static void workqueue_sysfs_unregister(s + #include + + #define assert_rcu_or_pool_mutex() \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU or wq_pool_mutex should be held") ++ "RCU or wq_pool_mutex should be held") + + #define assert_rcu_or_wq_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex), \ +- "sched RCU or wq->mutex should be held") ++ "RCU or wq->mutex should be held") + + #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ +- RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held() && \ ++ RCU_LOCKDEP_WARN(!rcu_read_lock_held() && \ + !lockdep_is_held(&wq->mutex) && \ + !lockdep_is_held(&wq_pool_mutex), \ +- "sched RCU, wq->mutex or wq_pool_mutex should be held") ++ "RCU, wq->mutex or wq_pool_mutex should be held") + + #define for_each_cpu_worker_pool(pool, cpu) \ + for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ +@@ -382,7 +382,7 @@ static void workqueue_sysfs_unregister(s + * @pool: iteration cursor + * @pi: integer used for iteration + * +- * This must be called either with wq_pool_mutex held or sched RCU read ++ * This must be called either with wq_pool_mutex held or RCU read + * locked. If the pool needs to be used beyond the locking in effect, the + * caller is responsible for guaranteeing that the pool stays online. + * +@@ -414,7 +414,7 @@ static void workqueue_sysfs_unregister(s + * @pwq: iteration cursor + * @wq: the target workqueue + * +- * This must be called either with wq->mutex held or sched RCU read locked. ++ * This must be called either with wq->mutex held or RCU read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. + * +@@ -550,7 +550,7 @@ static int worker_pool_assign_id(struct + * @wq: the target workqueue + * @node: the node ID + * +- * This must be called with any of wq_pool_mutex, wq->mutex or sched RCU ++ * This must be called with any of wq_pool_mutex, wq->mutex or RCU + * read locked. + * If the pwq needs to be used beyond the locking in effect, the caller is + * responsible for guaranteeing that the pwq stays online. +@@ -694,8 +694,8 @@ static struct pool_workqueue *get_work_p + * @work: the work item of interest + * + * Pools are created and destroyed under wq_pool_mutex, and allows read +- * access under sched-RCU read lock. As such, this function should be +- * called under wq_pool_mutex or with preemption disabled. ++ * access under RCU read lock. As such, this function should be ++ * called under wq_pool_mutex or inside of a rcu_read_lock() region. + * + * All fields of the returned pool are accessible as long as the above + * mentioned locking is in effect. If the returned pool needs to be used +@@ -1100,7 +1100,7 @@ static void put_pwq_unlocked(struct pool + { + if (pwq) { + /* +- * As both pwqs and pools are sched-RCU protected, the ++ * As both pwqs and pools are RCU protected, the + * following lock operations are safe. + */ + spin_lock_irq(&pwq->pool->lock); +@@ -1228,6 +1228,7 @@ static int try_to_grab_pending(struct wo + if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) + return 0; + ++ rcu_read_lock(); + /* + * The queueing is in progress, or it is already queued. Try to + * steal it from ->worklist without clearing WORK_STRUCT_PENDING. +@@ -1266,10 +1267,12 @@ static int try_to_grab_pending(struct wo + set_work_pool_and_keep_pending(work, pool->id); + + spin_unlock(&pool->lock); ++ rcu_read_unlock(); + return 1; + } + spin_unlock(&pool->lock); + fail: ++ rcu_read_unlock(); + local_irq_restore(*flags); + if (work_is_canceling(work)) + return -ENOENT; +@@ -1383,6 +1386,7 @@ static void __queue_work(int cpu, struct + if (unlikely(wq->flags & __WQ_DRAINING) && + WARN_ON_ONCE(!is_chained_work(wq))) + return; ++ rcu_read_lock(); + retry: + if (req_cpu == WORK_CPU_UNBOUND) + cpu = wq_select_unbound_cpu(raw_smp_processor_id()); +@@ -1439,10 +1443,8 @@ static void __queue_work(int cpu, struct + /* pwq determined, queue */ + trace_workqueue_queue_work(req_cpu, pwq, work); + +- if (WARN_ON(!list_empty(&work->entry))) { +- spin_unlock(&pwq->pool->lock); +- return; +- } ++ if (WARN_ON(!list_empty(&work->entry))) ++ goto out; + + pwq->nr_in_flight[pwq->work_color]++; + work_flags = work_color_to_flags(pwq->work_color); +@@ -1460,7 +1462,9 @@ static void __queue_work(int cpu, struct + + insert_work(pwq, work, worklist, work_flags); + ++out: + spin_unlock(&pwq->pool->lock); ++ rcu_read_unlock(); + } + + /** +@@ -2851,14 +2855,14 @@ static bool start_flush_work(struct work + + might_sleep(); + +- local_irq_disable(); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (!pool) { +- local_irq_enable(); ++ rcu_read_unlock(); + return false; + } + +- spin_lock(&pool->lock); ++ spin_lock_irq(&pool->lock); + /* see the comment in try_to_grab_pending() with the same code */ + pwq = get_work_pwq(work); + if (pwq) { +@@ -2889,10 +2893,11 @@ static bool start_flush_work(struct work + lock_map_acquire(&pwq->wq->lockdep_map); + lock_map_release(&pwq->wq->lockdep_map); + } +- ++ rcu_read_unlock(); + return true; + already_gone: + spin_unlock_irq(&pool->lock); ++ rcu_read_unlock(); + return false; + } + +@@ -3326,7 +3331,7 @@ static void rcu_free_pool(struct rcu_hea + * put_unbound_pool - put a worker_pool + * @pool: worker_pool to put + * +- * Put @pool. If its refcnt reaches zero, it gets destroyed in sched-RCU ++ * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU + * safe manner. get_unbound_pool() calls this function on its failure path + * and this function should be able to release pools which went through, + * successfully or not, init_worker_pool(). +@@ -3380,8 +3385,8 @@ static void put_unbound_pool(struct work + del_timer_sync(&pool->idle_timer); + del_timer_sync(&pool->mayday_timer); + +- /* sched-RCU protected to allow dereferences from get_work_pool() */ +- call_rcu_sched(&pool->rcu, rcu_free_pool); ++ /* RCU protected to allow dereferences from get_work_pool() */ ++ call_rcu(&pool->rcu, rcu_free_pool); + } + + /** +@@ -3488,14 +3493,14 @@ static void pwq_unbound_release_workfn(s + put_unbound_pool(pool); + mutex_unlock(&wq_pool_mutex); + +- call_rcu_sched(&pwq->rcu, rcu_free_pwq); ++ call_rcu(&pwq->rcu, rcu_free_pwq); + + /* + * If we're the last pwq going away, @wq is already dead and no one + * is gonna access it anymore. Schedule RCU free. + */ + if (is_last) +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } + + /** +@@ -4180,7 +4185,7 @@ void destroy_workqueue(struct workqueue_ + * The base ref is never dropped on per-cpu pwqs. Directly + * schedule RCU free. + */ +- call_rcu_sched(&wq->rcu, rcu_free_wq); ++ call_rcu(&wq->rcu, rcu_free_wq); + } else { + /* + * We're the sole accessor of @wq at this point. Directly +@@ -4290,7 +4295,8 @@ bool workqueue_congested(int cpu, struct + struct pool_workqueue *pwq; + bool ret; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); ++ preempt_disable(); + + if (cpu == WORK_CPU_UNBOUND) + cpu = smp_processor_id(); +@@ -4301,7 +4307,8 @@ bool workqueue_congested(int cpu, struct + pwq = unbound_pwq_by_node(wq, cpu_to_node(cpu)); + + ret = !list_empty(&pwq->delayed_works); +- rcu_read_unlock_sched(); ++ preempt_enable(); ++ rcu_read_unlock(); + + return ret; + } +@@ -4327,15 +4334,15 @@ unsigned int work_busy(struct work_struc + if (work_pending(work)) + ret |= WORK_BUSY_PENDING; + +- local_irq_save(flags); ++ rcu_read_lock(); + pool = get_work_pool(work); + if (pool) { +- spin_lock(&pool->lock); ++ spin_lock_irqsave(&pool->lock, flags); + if (find_worker_executing_work(pool, work)) + ret |= WORK_BUSY_RUNNING; +- spin_unlock(&pool->lock); ++ spin_unlock_irqrestore(&pool->lock, flags); + } +- local_irq_restore(flags); ++ rcu_read_unlock(); + + return ret; + } +@@ -4519,7 +4526,7 @@ void show_workqueue_state(void) + unsigned long flags; + int pi; + +- rcu_read_lock_sched(); ++ rcu_read_lock(); + + pr_info("Showing busy workqueues and worker pools:\n"); + +@@ -4584,7 +4591,7 @@ void show_workqueue_state(void) + touch_nmi_watchdog(); + } + +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + + /* used to show worker information through /proc/PID/{comm,stat,status} */ +@@ -4971,16 +4978,16 @@ bool freeze_workqueues_busy(void) + * nr_active is monotonically decreasing. It's safe + * to peek without lock. + */ +- rcu_read_lock_sched(); ++ rcu_read_lock(); + for_each_pwq(pwq, wq) { + WARN_ON_ONCE(pwq->nr_active < 0); + if (pwq->nr_active) { + busy = true; +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + goto out_unlock; + } + } +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); + } + out_unlock: + mutex_unlock(&wq_pool_mutex); +@@ -5175,7 +5182,8 @@ static ssize_t wq_pool_ids_show(struct d + const char *delim = ""; + int node, written = 0; + +- rcu_read_lock_sched(); ++ get_online_cpus(); ++ rcu_read_lock(); + for_each_node(node) { + written += scnprintf(buf + written, PAGE_SIZE - written, + "%s%d:%d", delim, node, +@@ -5183,7 +5191,8 @@ static ssize_t wq_pool_ids_show(struct d + delim = " "; + } + written += scnprintf(buf + written, PAGE_SIZE - written, "\n"); +- rcu_read_unlock_sched(); ++ rcu_read_unlock(); ++ put_online_cpus(); + + return written; + } diff --git a/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch b/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch new file mode 100644 index 000000000..99ecbcb81 --- /dev/null +++ b/debian/patches/features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch @@ -0,0 +1,112 @@ +Subject: x86: crypto: Reduce preempt disabled regions +From: Peter Zijlstra +Date: Mon, 14 Nov 2011 18:19:27 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Restrict the preempt disabled regions to the actual floating point +operations and enable preemption for the administrative actions. + +This is necessary on RT to avoid that kfree and other operations are +called with preemption disabled. + +Reported-and-tested-by: Carsten Emde +Signed-off-by: Peter Zijlstra + +Signed-off-by: Thomas Gleixner +--- + arch/x86/crypto/aesni-intel_glue.c | 22 ++++++++++++---------- + 1 file changed, 12 insertions(+), 10 deletions(-) + +--- a/arch/x86/crypto/aesni-intel_glue.c ++++ b/arch/x86/crypto/aesni-intel_glue.c +@@ -434,14 +434,14 @@ static int ecb_encrypt(struct skcipher_r + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -456,14 +456,14 @@ static int ecb_decrypt(struct skcipher_r + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_ecb_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -478,14 +478,14 @@ static int cbc_encrypt(struct skcipher_r + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_enc(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -500,14 +500,14 @@ static int cbc_decrypt(struct skcipher_r + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes)) { ++ kernel_fpu_begin(); + aesni_cbc_dec(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } +- kernel_fpu_end(); + + return err; + } +@@ -557,18 +557,20 @@ static int ctr_crypt(struct skcipher_req + + err = skcipher_walk_virt(&walk, req, true); + +- kernel_fpu_begin(); + while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) { ++ kernel_fpu_begin(); + aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr, + nbytes & AES_BLOCK_MASK, walk.iv); ++ kernel_fpu_end(); + nbytes &= AES_BLOCK_SIZE - 1; + err = skcipher_walk_done(&walk, nbytes); + } + if (walk.nbytes) { ++ kernel_fpu_begin(); + ctr_crypt_final(ctx, &walk); ++ kernel_fpu_end(); + err = skcipher_walk_done(&walk, 0); + } +- kernel_fpu_end(); + + return err; + } diff --git a/debian/patches/features/all/rt/x86-efi-drop-task_lock-from-efi_switch_mm.patch b/debian/patches/features/all/rt/x86-efi-drop-task_lock-from-efi_switch_mm.patch new file mode 100644 index 000000000..8f657b1b0 --- /dev/null +++ b/debian/patches/features/all/rt/x86-efi-drop-task_lock-from-efi_switch_mm.patch @@ -0,0 +1,49 @@ +From: Sebastian Andrzej Siewior +Date: Tue, 24 Jul 2018 14:48:55 +0200 +Subject: [PATCH] x86/efi: drop task_lock() from efi_switch_mm() +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +efi_switch_mm() is a wrapper around switch_mm() which saves current's +->active_mm, sets the requests mm as ->active_mm and invokes +switch_mm(). +I don't think that task_lock() is required during that procedure. It +protects ->mm which isn't changed here. + +It needs to be mentioned that during the whole procedure (switch to +EFI's mm and back) the preemption needs to be disabled. A context switch +at this point would reset the cr3 value based on current->mm. Also, this +function may not be invoked at the same time on a different CPU because +it would overwrite the efi_scratch.prev_mm information. + +Remove task_lock() and also update the comment to reflect it. + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/platform/efi/efi_64.c | 10 ++++------ + 1 file changed, 4 insertions(+), 6 deletions(-) + +--- a/arch/x86/platform/efi/efi_64.c ++++ b/arch/x86/platform/efi/efi_64.c +@@ -619,18 +619,16 @@ void __init efi_dump_pagetable(void) + + /* + * Makes the calling thread switch to/from efi_mm context. Can be used +- * for SetVirtualAddressMap() i.e. current->active_mm == init_mm as well +- * as during efi runtime calls i.e current->active_mm == current_mm. +- * We are not mm_dropping()/mm_grabbing() any mm, because we are not +- * losing/creating any references. ++ * in a kernel thread and user context. Preemption needs to remain disabled ++ * while the EFI-mm is borrowed. mmgrab()/mmdrop() is not used because the mm ++ * can not change under us. ++ * It should be ensured that there are no concurent calls to this function. + */ + void efi_switch_mm(struct mm_struct *mm) + { +- task_lock(current); + efi_scratch.prev_mm = current->active_mm; + current->active_mm = mm; + switch_mm(efi_scratch.prev_mm, mm, NULL); +- task_unlock(current); + } + + #ifdef CONFIG_EFI_MIXED diff --git a/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch b/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch new file mode 100644 index 000000000..0240ce490 --- /dev/null +++ b/debian/patches/features/all/rt/x86-highmem-add-a-already-used-pte-check.patch @@ -0,0 +1,23 @@ +From: Sebastian Andrzej Siewior +Date: Mon, 11 Mar 2013 17:09:55 +0100 +Subject: x86/highmem: Add a "already used pte" check +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +This is a copy from kmap_atomic_prot(). + +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/mm/iomap_32.c | 2 ++ + 1 file changed, 2 insertions(+) + +--- a/arch/x86/mm/iomap_32.c ++++ b/arch/x86/mm/iomap_32.c +@@ -69,6 +69,8 @@ void *kmap_atomic_prot_pfn(unsigned long + type = kmap_atomic_idx_push(); + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); ++ WARN_ON(!pte_none(*(kmap_pte - idx))); ++ + #ifdef CONFIG_PREEMPT_RT_FULL + current->kmap_pte[type] = pte; + #endif diff --git a/debian/patches/features/all/rt/x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch b/debian/patches/features/all/rt/x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch new file mode 100644 index 000000000..be3b67337 --- /dev/null +++ b/debian/patches/features/all/rt/x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch @@ -0,0 +1,106 @@ +From: Thomas Gleixner +Date: Tue, 17 Jul 2018 18:25:31 +0200 +Subject: [PATCH] x86/ioapic: Don't let setaffinity unmask threaded EOI + interrupt too early +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +There is an issue with threaded interrupts which are marked ONESHOT +and using the fasteoi handler. + + if (IS_ONESHOT()) + mask_irq(); + + .... + .... + + cond_unmask_eoi_irq() + chip->irq_eoi(); + +So if setaffinity is pending then the interrupt will be moved and then +unmasked, which is wrong as it should be kept masked up to the point where +the threaded handler finished. It's not a real problem, the interrupt will +just be able to fire before the threaded handler has finished, though the irq +masked state will be wrong for a bit. + +The patch below should cure the issue. It also renames the horribly +misnomed functions so it becomes clear what they are supposed to do. + +Signed-off-by: Thomas Gleixner +[bigeasy: add the body of the patch, use the same functions in both + ifdef paths (spotted by Andy Shevchenko)] +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/kernel/apic/io_apic.c | 23 +++++++++++++---------- + 1 file changed, 13 insertions(+), 10 deletions(-) + +--- a/arch/x86/kernel/apic/io_apic.c ++++ b/arch/x86/kernel/apic/io_apic.c +@@ -1721,19 +1721,20 @@ static bool io_apic_level_ack_pending(st + return false; + } + +-static inline bool ioapic_irqd_mask(struct irq_data *data) ++static inline bool ioapic_prepare_move(struct irq_data *data) + { + /* If we are moving the irq we need to mask it */ + if (unlikely(irqd_is_setaffinity_pending(data))) { +- mask_ioapic_irq(data); ++ if (!irqd_irq_masked(data)) ++ mask_ioapic_irq(data); + return true; + } + return false; + } + +-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) ++static inline void ioapic_finish_move(struct irq_data *data, bool moveit) + { +- if (unlikely(masked)) { ++ if (unlikely(moveit)) { + /* Only migrate the irq if the ack has been received. + * + * On rare occasions the broadcast level triggered ack gets +@@ -1762,15 +1763,17 @@ static inline void ioapic_irqd_unmask(st + */ + if (!io_apic_level_ack_pending(data->chip_data)) + irq_move_masked_irq(data); +- unmask_ioapic_irq(data); ++ /* If the irq is masked in the core, leave it */ ++ if (!irqd_irq_masked(data)) ++ unmask_ioapic_irq(data); + } + } + #else +-static inline bool ioapic_irqd_mask(struct irq_data *data) ++static inline bool ioapic_prepare_move(struct irq_data *data) + { + return false; + } +-static inline void ioapic_irqd_unmask(struct irq_data *data, bool masked) ++static inline void ioapic_finish_move(struct irq_data *data, bool moveit) + { + } + #endif +@@ -1779,11 +1782,11 @@ static void ioapic_ack_level(struct irq_ + { + struct irq_cfg *cfg = irqd_cfg(irq_data); + unsigned long v; +- bool masked; ++ bool moveit; + int i; + + irq_complete_move(cfg); +- masked = ioapic_irqd_mask(irq_data); ++ moveit = ioapic_prepare_move(irq_data); + + /* + * It appears there is an erratum which affects at least version 0x11 +@@ -1838,7 +1841,7 @@ static void ioapic_ack_level(struct irq_ + eoi_ioapic_pin(cfg->vector, irq_data->chip_data); + } + +- ioapic_irqd_unmask(irq_data, masked); ++ ioapic_finish_move(irq_data, moveit); + } + + static void ioapic_ir_ack_level(struct irq_data *irq_data) diff --git a/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch b/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch new file mode 100644 index 000000000..209889760 --- /dev/null +++ b/debian/patches/features/all/rt/x86-kvm-require-const-tsc-for-rt.patch @@ -0,0 +1,31 @@ +Subject: x86: kvm Require const tsc for RT +From: Thomas Gleixner +Date: Sun, 06 Nov 2011 12:26:18 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Non constant TSC is a nightmare on bare metal already, but with +virtualization it becomes a complete disaster because the workarounds +are horrible latency wise. That's also a preliminary for running RT in +a guest on top of a RT host. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/kvm/x86.c | 7 +++++++ + 1 file changed, 7 insertions(+) + +--- a/arch/x86/kvm/x86.c ++++ b/arch/x86/kvm/x86.c +@@ -6564,6 +6564,13 @@ int kvm_arch_init(void *opaque) + goto out; + } + ++#ifdef CONFIG_PREEMPT_RT_FULL ++ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) { ++ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n"); ++ return -EOPNOTSUPP; ++ } ++#endif ++ + r = kvm_mmu_module_init(); + if (r) + goto out_free_percpu; diff --git a/debian/patches/features/all/rt/x86-preempt-lazy.patch b/debian/patches/features/all/rt/x86-preempt-lazy.patch new file mode 100644 index 000000000..d70346ab1 --- /dev/null +++ b/debian/patches/features/all/rt/x86-preempt-lazy.patch @@ -0,0 +1,222 @@ +Subject: x86: Support for lazy preemption +From: Thomas Gleixner +Date: Thu, 01 Nov 2012 11:03:47 +0100 +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Implement the x86 pieces for lazy preempt. + +Signed-off-by: Thomas Gleixner +--- + arch/x86/Kconfig | 1 + + arch/x86/entry/common.c | 4 ++-- + arch/x86/entry/entry_32.S | 17 +++++++++++++++++ + arch/x86/entry/entry_64.S | 16 ++++++++++++++++ + arch/x86/include/asm/preempt.h | 31 ++++++++++++++++++++++++++++++- + arch/x86/include/asm/thread_info.h | 11 +++++++++++ + arch/x86/kernel/asm-offsets.c | 2 ++ + 7 files changed, 79 insertions(+), 3 deletions(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -178,6 +178,7 @@ config X86 + select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI + select HAVE_PERF_REGS + select HAVE_PERF_USER_STACK_DUMP ++ select HAVE_PREEMPT_LAZY + select HAVE_RCU_TABLE_FREE + select HAVE_REGS_AND_STACK_ACCESS_API + select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION +--- a/arch/x86/entry/common.c ++++ b/arch/x86/entry/common.c +@@ -133,7 +133,7 @@ static long syscall_trace_enter(struct p + + #define EXIT_TO_USERMODE_LOOP_FLAGS \ + (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ +- _TIF_NEED_RESCHED | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) ++ _TIF_NEED_RESCHED_MASK | _TIF_USER_RETURN_NOTIFY | _TIF_PATCH_PENDING) + + static void exit_to_usermode_loop(struct pt_regs *regs, u32 cached_flags) + { +@@ -148,7 +148,7 @@ static void exit_to_usermode_loop(struct + /* We have work to do. */ + local_irq_enable(); + +- if (cached_flags & _TIF_NEED_RESCHED) ++ if (cached_flags & _TIF_NEED_RESCHED_MASK) + schedule(); + + #ifdef ARCH_RT_DELAYS_SIGNAL_SEND +--- a/arch/x86/entry/entry_32.S ++++ b/arch/x86/entry/entry_32.S +@@ -350,8 +350,25 @@ END(ret_from_exception) + ENTRY(resume_kernel) + DISABLE_INTERRUPTS(CLBR_ANY) + .Lneed_resched: ++ # preempt count == 0 + NEED_RS set? + cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz restore_all ++#else ++ jz test_int_off ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jne restore_all ++ ++ movl PER_CPU_VAR(current_task), %ebp ++ cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ? ++ jnz restore_all ++ ++ testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp) ++ jz restore_all ++test_int_off: ++#endif + testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ? + jz restore_all + call preempt_schedule_irq +--- a/arch/x86/entry/entry_64.S ++++ b/arch/x86/entry/entry_64.S +@@ -704,7 +704,23 @@ GLOBAL(swapgs_restore_regs_and_return_to + bt $9, EFLAGS(%rsp) /* were interrupts off? */ + jnc 1f + 0: cmpl $0, PER_CPU_VAR(__preempt_count) ++#ifndef CONFIG_PREEMPT_LAZY + jnz 1f ++#else ++ jz do_preempt_schedule_irq ++ ++ # atleast preempt count == 0 ? ++ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count) ++ jnz 1f ++ ++ movq PER_CPU_VAR(current_task), %rcx ++ cmpl $0, TASK_TI_preempt_lazy_count(%rcx) ++ jnz 1f ++ ++ bt $TIF_NEED_RESCHED_LAZY,TASK_TI_flags(%rcx) ++ jnc 1f ++do_preempt_schedule_irq: ++#endif + call preempt_schedule_irq + jmp 0b + 1: +--- a/arch/x86/include/asm/preempt.h ++++ b/arch/x86/include/asm/preempt.h +@@ -86,17 +86,46 @@ static __always_inline void __preempt_co + * a decrement which hits zero means we have no preempt_count and should + * reschedule. + */ +-static __always_inline bool __preempt_count_dec_and_test(void) ++static __always_inline bool ____preempt_count_dec_and_test(void) + { + GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e); + } + ++static __always_inline bool __preempt_count_dec_and_test(void) ++{ ++ if (____preempt_count_dec_and_test()) ++ return true; ++#ifdef CONFIG_PREEMPT_LAZY ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else ++ return false; ++#endif ++} ++ + /* + * Returns true when we need to resched and can (barring IRQ state). + */ + static __always_inline bool should_resched(int preempt_offset) + { ++#ifdef CONFIG_PREEMPT_LAZY ++ u32 tmp; ++ ++ tmp = raw_cpu_read_4(__preempt_count); ++ if (tmp == preempt_offset) ++ return true; ++ ++ /* preempt count == 0 ? */ ++ tmp &= ~PREEMPT_NEED_RESCHED; ++ if (tmp) ++ return false; ++ if (current_thread_info()->preempt_lazy_count) ++ return false; ++ return test_thread_flag(TIF_NEED_RESCHED_LAZY); ++#else + return unlikely(raw_cpu_read_4(__preempt_count) == preempt_offset); ++#endif + } + + #ifdef CONFIG_PREEMPT +--- a/arch/x86/include/asm/thread_info.h ++++ b/arch/x86/include/asm/thread_info.h +@@ -56,17 +56,24 @@ struct task_struct; + struct thread_info { + unsigned long flags; /* low level flags */ + u32 status; /* thread synchronous flags */ ++ int preempt_lazy_count; /* 0 => lazy preemptable ++ <0 => BUG */ + }; + + #define INIT_THREAD_INFO(tsk) \ + { \ + .flags = 0, \ ++ .preempt_lazy_count = 0, \ + } + + #else /* !__ASSEMBLY__ */ + + #include + ++#define GET_THREAD_INFO(reg) \ ++ _ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \ ++ _ASM_SUB $(THREAD_SIZE),reg ; ++ + #endif + + /* +@@ -83,6 +90,7 @@ struct thread_info { + #define TIF_SYSCALL_EMU 6 /* syscall emulation active */ + #define TIF_SYSCALL_AUDIT 7 /* syscall auditing active */ + #define TIF_SECCOMP 8 /* secure computing */ ++#define TIF_NEED_RESCHED_LAZY 9 /* lazy rescheduling necessary */ + #define TIF_USER_RETURN_NOTIFY 11 /* notify kernel of userspace return */ + #define TIF_UPROBE 12 /* breakpointed or singlestepping */ + #define TIF_PATCH_PENDING 13 /* pending live patching update */ +@@ -110,6 +118,7 @@ struct thread_info { + #define _TIF_SYSCALL_EMU (1 << TIF_SYSCALL_EMU) + #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) + #define _TIF_SECCOMP (1 << TIF_SECCOMP) ++#define _TIF_NEED_RESCHED_LAZY (1 << TIF_NEED_RESCHED_LAZY) + #define _TIF_USER_RETURN_NOTIFY (1 << TIF_USER_RETURN_NOTIFY) + #define _TIF_UPROBE (1 << TIF_UPROBE) + #define _TIF_PATCH_PENDING (1 << TIF_PATCH_PENDING) +@@ -151,6 +160,8 @@ struct thread_info { + #define _TIF_WORK_CTXSW_PREV (_TIF_WORK_CTXSW|_TIF_USER_RETURN_NOTIFY) + #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW) + ++#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY) ++ + #define STACK_WARN (THREAD_SIZE/8) + + /* +--- a/arch/x86/kernel/asm-offsets.c ++++ b/arch/x86/kernel/asm-offsets.c +@@ -38,6 +38,7 @@ void common(void) { + + BLANK(); + OFFSET(TASK_TI_flags, task_struct, thread_info.flags); ++ OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count); + OFFSET(TASK_addr_limit, task_struct, thread.addr_limit); + + BLANK(); +@@ -94,6 +95,7 @@ void common(void) { + + BLANK(); + DEFINE(PTREGS_SIZE, sizeof(struct pt_regs)); ++ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED); + + /* TLB state for the entry code */ + OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask); diff --git a/debian/patches/features/all/rt/x86-signal-delay-calling-signals-on-32bit.patch b/debian/patches/features/all/rt/x86-signal-delay-calling-signals-on-32bit.patch new file mode 100644 index 000000000..2f3761fe5 --- /dev/null +++ b/debian/patches/features/all/rt/x86-signal-delay-calling-signals-on-32bit.patch @@ -0,0 +1,43 @@ +From: Yang Shi +Date: Thu, 10 Dec 2015 10:58:51 -0800 +Subject: x86/signal: delay calling signals on 32bit +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +When running some ptrace single step tests on x86-32 machine, the below problem +is triggered: + +BUG: sleeping function called from invalid context at kernel/locking/rtmutex.c:917 +in_atomic(): 1, irqs_disabled(): 0, pid: 1041, name: dummy2 +Preemption disabled at:[] do_debug+0x1f/0x1a0 + +CPU: 10 PID: 1041 Comm: dummy2 Tainted: G W 4.1.13-rt13 #1 +Call Trace: + [] dump_stack+0x46/0x5c + [] ___might_sleep+0x137/0x220 + [] rt_spin_lock+0x1f/0x80 + [] do_force_sig_info+0x2a/0xc0 + [] force_sig_info+0xd/0x10 + [] send_sigtrap+0x6f/0x80 + [] do_debug+0x161/0x1a0 + [] debug_stack_correct+0x2e/0x35 + +This happens since 959274753857 ("x86, traps: Track entry into and exit +from IST context") which was merged in v4.1-rc1. + +Signed-off-by: Yang Shi +Signed-off-by: Sebastian Andrzej Siewior +--- + arch/x86/include/asm/signal.h | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +--- a/arch/x86/include/asm/signal.h ++++ b/arch/x86/include/asm/signal.h +@@ -37,7 +37,7 @@ typedef struct { + * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the + * trap. + */ +-#if defined(CONFIG_PREEMPT_RT_FULL) && defined(CONFIG_X86_64) ++#if defined(CONFIG_PREEMPT_RT_FULL) + #define ARCH_RT_DELAYS_SIGNAL_SEND + #endif + diff --git a/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch b/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch new file mode 100644 index 000000000..8d69143a0 --- /dev/null +++ b/debian/patches/features/all/rt/x86-stackprot-no-random-on-rt.patch @@ -0,0 +1,46 @@ +From: Thomas Gleixner +Date: Thu, 16 Dec 2010 14:25:18 +0100 +Subject: x86: stackprotector: Avoid random pool on rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +CPU bringup calls into the random pool to initialize the stack +canary. During boot that works nicely even on RT as the might sleep +checks are disabled. During CPU hotplug the might sleep checks +trigger. Making the locks in random raw is a major PITA, so avoid the +call on RT is the only sensible solution. This is basically the same +randomness which we get during boot where the random pool has no +entropy and we rely on the TSC randomnness. + +Reported-by: Carsten Emde +Signed-off-by: Thomas Gleixner + +--- + arch/x86/include/asm/stackprotector.h | 8 +++++++- + 1 file changed, 7 insertions(+), 1 deletion(-) + +--- a/arch/x86/include/asm/stackprotector.h ++++ b/arch/x86/include/asm/stackprotector.h +@@ -60,7 +60,7 @@ + */ + static __always_inline void boot_init_stack_canary(void) + { +- u64 canary; ++ u64 uninitialized_var(canary); + u64 tsc; + + #ifdef CONFIG_X86_64 +@@ -71,8 +71,14 @@ static __always_inline void boot_init_st + * of randomness. The TSC only matters for very early init, + * there it already has some randomness on most systems. Later + * on during the bootup the random pool has true entropy too. ++ * For preempt-rt we need to weaken the randomness a bit, as ++ * we can't call into the random generator from atomic context ++ * due to locking constraints. We just leave canary ++ * uninitialized and use the TSC based randomness on top of it. + */ ++#ifndef CONFIG_PREEMPT_RT_FULL + get_random_bytes(&canary, sizeof(canary)); ++#endif + tsc = rdtsc(); + canary += tsc + (tsc << 32UL); + canary &= CANARY_MASK; diff --git a/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch b/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch new file mode 100644 index 000000000..bbb0a0d00 --- /dev/null +++ b/debian/patches/features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch @@ -0,0 +1,29 @@ +From: Thomas Gleixner +Date: Sun, 26 Jul 2009 02:21:32 +0200 +Subject: x86: Use generic rwsem_spinlocks on -rt +Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.18/older/patches-4.18-rc8-rt1.tar.xz + +Simplifies the separation of anon_rw_semaphores and rw_semaphores for +-rt. + +Signed-off-by: Thomas Gleixner + +--- + arch/x86/Kconfig | 5 ++++- + 1 file changed, 4 insertions(+), 1 deletion(-) + +--- a/arch/x86/Kconfig ++++ b/arch/x86/Kconfig +@@ -260,8 +260,11 @@ config ARCH_MAY_HAVE_PC_FDC + def_bool y + depends on ISA_DMA_API + ++config RWSEM_GENERIC_SPINLOCK ++ def_bool PREEMPT_RT_FULL ++ + config RWSEM_XCHGADD_ALGORITHM +- def_bool y ++ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL + + config GENERIC_CALIBRATE_DELAY + def_bool y diff --git a/debian/patches/series-rt b/debian/patches/series-rt index e69de29bb..7978ee93d 100644 --- a/debian/patches/series-rt +++ b/debian/patches/series-rt @@ -0,0 +1,432 @@ +########################################################### +# DELTA against a known Linus release +########################################################### + +############################################################ +# UPSTREAM merged +############################################################ + +#misc +features/all/rt/SCSI-libsas-remove-irq-save-in-sas_ata_qc_issue.patch +features/all/rt/SCSI-qla2xxx-remove-irq-save-in-qla2x00_poll.patch +features/all/rt/cgroup-tracing-Move-taking-of-spin-lock-out-of-trace.patch +features/all/rt/sched-core-Remove-get_cpu-from-sched_fork.patch +features/all/rt/random-Remove-preempt-disabled-region.patch +features/all/rt/iommu-amd-drop-irqs_disabled-warn_on.patch +# atomic_dec_and_lock_irqsave / refcount_dec_and_lock_irqsave +features/all/rt/0002-drivers-md-raid5-Use-irqsave-variant-of-atomic_dec_a.patch +features/all/rt/0003-drivers-md-raid5-Do-not-disable-irq-on-release_inact.patch +features/all/rt/0001-bdi-use-refcount_t-for-reference-counting-instead-at.patch +features/all/rt/0002-userns-use-refcount_t-for-reference-counting-instead.patch +features/all/rt/0005-bdi-Use-irqsave-variant-of-refcount_dec_and_lock.patch +features/all/rt/0006-userns-Use-irqsave-variant-of-refcount_dec_and_lock.patch +features/all/rt/libata-remove-ata_sff_data_xfer_noirq.patch +features/all/rt/ntfs-avoid-disabling-interrupts-during-kmap_atomic.patch +# mm/workingset +features/all/rt/0001-mm-workingset-remove-local_irq_disable-from-count_sh.patch +features/all/rt/0002-mm-workingset-make-shadow_lru_isolate-use-locking-su.patch +features/all/rt/0001-mm-list_lru-use-list_lru_walk_one-in-list_lru_walk_n.patch +features/all/rt/0002-mm-list_lru-Move-locking-from-__list_lru_walk_one-to.patch +features/all/rt/0003-mm-list_lru-Pass-struct-list_lru_node-as-an-argument.patch +features/all/rt/0004-mm-list_lru-Introduce-list_lru_shrink_walk_irq.patch + +############################################################ +# POSTED by others +############################################################ +# AT91 +# Alexandre Belloni | [PATCH v4 0/6] clocksource: rework Atmel TCB timer driver +# Date: Wed, 18 Apr 2018 12:51:37 +0200 +features/all/rt/0001-ARM-at91-add-TCB-registers-definitions.patch +features/all/rt/0002-clocksource-drivers-Add-a-new-driver-for-the-Atmel-A.patch +features/all/rt/0003-clocksource-drivers-atmel-pit-make-option-silent.patch +features/all/rt/0004-ARM-at91-Implement-clocksource-selection.patch +features/all/rt/0005-ARM-configs-at91-use-new-TCB-timer-driver.patch +features/all/rt/0006-ARM-configs-at91-unselect-PIT.patch + +############################################################ +# POSTED +############################################################ +features/all/rt/arm-convert-boot-lock-to-raw.patch +features/all/rt/x86-ioapic-Don-t-let-setaffinity-unmask-threaded-EOI.patch +features/all/rt/arm-kprobe-replace-patch_lock-to-raw-lock.patch +features/all/rt/arm-unwind-use_raw_lock.patch +features/all/rt/cgroup-use-irqsave-in-cgroup_rstat_flush_locked.patch +features/all/rt/fscache-initialize-cookie-hash-table-raw-spinlocks.patch + +############################################################ +# Ready for posting +############################################################ +features/all/rt/irqchip-gic-v3-its-Make-its_lock-a-raw_spin_lock_t.patch +features/all/rt/irqchip-gic-v3-its-Move-ITS-pend_page-allocation-int.patch +features/all/rt/efi-Allow-efi-runtime.patch + +############################################################ +# Needs to address review feedback +############################################################ + +############################################################ +# Almost ready, needs final polishing +############################################################ +features/all/rt/x86-efi-drop-task_lock-from-efi_switch_mm.patch +features/all/rt/arm64-KVM-compute_layout-before-altenates-are-applie.patch + +############################################################### +# Stuff broken upstream and upstream wants something different +############################################################### +features/all/rt/NFSv4-replace-seqcount_t-with-a-seqlock_t.patch +features/all/rt/kernel-sched-Provide-a-pointer-to-the-valid-CPU-mask.patch +features/all/rt/add_migrate_disable.patch + +# Those two should vanish soon (not use PIT during bootup) +features/all/rt/at91_dont_enable_disable_clock.patch +features/all/rt/clocksource-tclib-allow-higher-clockrates.patch + +# Timekeeping split jiffies lock. Needs a good argument :) +features/all/rt/timekeeping-split-jiffies-lock.patch + +# PTRACE/SIGNAL crap +features/all/rt/signal-revert-ptrace-preempt-magic.patch + +# NETWORKING +features/all/rt/net-sched-dev_deactivate_many-use-msleep-1-instead-o.patch + +# The removal of NONRT helpers +features/all/rt/dm-rq-remove-BUG_ON-irqs_disabled-check.patch +features/all/rt/usb-do-not-disable-interrupts-in-giveback.patch + +################################################## +# REAL RT STUFF starts here +################################################## + +# Kconfig on/off +features/all/rt/rt-preempt-base-config.patch +features/all/rt/kconfig-preempt-rt-full.patch +features/all/rt/cpumask-disable-offstack-on-rt.patch +features/all/rt/jump-label-rt.patch +features/all/rt/kconfig-disable-a-few-options-rt.patch +features/all/rt/lockdep-disable-self-test.patch +features/all/rt/mm-disable-sloub-rt.patch +features/all/rt/mutex-no-spin-on-rt.patch +features/all/rt/rcu-disable-rcu-fast-no-hz-on-rt.patch +features/all/rt/rcu-make-RCU_BOOST-default-on-RT.patch +features/all/rt/sched-disable-rt-group-sched-on-rt.patch +features/all/rt/net_disable_NET_RX_BUSY_POLL.patch +features/all/rt/arm-disable-NEON-in-kernel-mode.patch +features/all/rt/power-use-generic-rwsem-on-rt.patch +features/all/rt/powerpc-kvm-Disable-in-kernel-MPIC-emulation-for-PRE.patch +features/all/rt/power-disable-highmem-on-rt.patch +features/all/rt/mips-disable-highmem-on-rt.patch +features/all/rt/x86-use-gen-rwsem-spinlocks-rt.patch +features/all/rt/leds-trigger-disable-CPU-trigger-on-RT.patch +features/all/rt/cpufreq-drop-K8-s-driver-from-beeing-selected.patch +features/all/rt/md-disable-bcache.patch +features/all/rt/efi-Disable-runtime-services-on-RT.patch + +# PRINTK +features/all/rt/printk-kill.patch +features/all/rt/printk-27force_early_printk-27-boot-param-to-help-with-debugging.patch + +# PREEMPT NORT +features/all/rt/preempt-nort-rt-variants.patch + +# local locks & migrate disable +features/all/rt/futex-workaround-migrate_disable-enable-in-different.patch +features/all/rt/rt-local-irq-lock.patch +features/all/rt/locallock-provide-get-put-_locked_ptr-variants.patch + +# ANNOTATE local_irq_disable sites +features/all/rt/mm-scatterlist-dont-disable-irqs-on-RT.patch + +# Sigh +features/all/rt/oleg-signal-rt-fix.patch +features/all/rt/x86-signal-delay-calling-signals-on-32bit.patch + +# BIT SPINLOCKS - SIGH +features/all/rt/fs-replace-bh_uptodate_lock-for-rt.patch +features/all/rt/fs-jbd-replace-bh_state-lock.patch + +# GENIRQ +features/all/rt/list_bl.h-make-list-head-locking-RT-safe.patch +features/all/rt/list_bl-fixup-bogus-lockdep-warning.patch +features/all/rt/genirq-disable-irqpoll-on-rt.patch +features/all/rt/genirq-force-threading.patch + +# MM page alloc +features/all/rt/0001-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch +features/all/rt/0002-Split-IRQ-off-and-zone-lock-while-freeing-pages-from.patch +features/all/rt/0003-mm-SLxB-change-list_lock-to-raw_spinlock_t.patch +features/all/rt/0004-mm-SLUB-delay-giving-back-empty-slubs-to-IRQ-enabled.patch +features/all/rt/mm-page_alloc-rt-friendly-per-cpu-pages.patch + +# MM SWAP +features/all/rt/mm-convert-swap-to-percpu-locked.patch +features/all/rt/mm-perform-lru_add_drain_all-remotely.patch + +# MM vmstat +features/all/rt/mm-make-vmstat-rt-aware.patch + +# MM memory +features/all/rt/re-preempt_rt_full-arm-coredump-fails-for-cpu-3e-3d-4.patch + +# MM SLxB +features/all/rt/mm-enable-slub.patch +features/all/rt/slub-enable-irqs-for-no-wait.patch +features/all/rt/slub-disable-SLUB_CPU_PARTIAL.patch + +# MM +features/all/rt/mm-memcontrol-Don-t-call-schedule_work_on-in-preempt.patch +features/all/rt/mm-memcontrol-do_not_disable_irq.patch +features/all/rt/mm_zsmalloc_copy_with_get_cpu_var_and_locking.patch + +# RADIX TREE +features/all/rt/radix-tree-use-local-locks.patch + +# TIMERS +features/all/rt/timers-prepare-for-full-preemption.patch + +# KVM require constant freq TSC (smp function call -> cpufreq) +features/all/rt/x86-kvm-require-const-tsc-for-rt.patch +# +# SIMPLE WAITQUEUE +features/all/rt/wait.h-include-atomic.h.patch +features/all/rt/work-simple-Simple-work-queue-implemenation.patch +features/all/rt/completion-use-simple-wait-queues.patch +features/all/rt/fs-aio-simple-simple-work.patch +features/all/rt/genirq-do-not-invoke-the-affinity-callback-via-a-wor.patch + +# HRTIMERS +features/all/rt/time-hrtimer-avoid-schedule_work-with-interrupts-dis.patch +features/all/rt/hrtimer-consolidate-hrtimer_init-hrtimer_init_sleepe.patch +features/all/rt/hrtimers-prepare-full-preemption.patch +features/all/rt/hrtimer-by-timers-by-default-into-the-softirq-context.patch +features/all/rt/hrtimer-Move-schedule_work-call-to-helper-thread.patch + +# POSIX-CPU-TIMERS +features/all/rt/posix-timers-thread-posix-cpu-timers-on-rt.patch + +# SCHEDULER +features/all/rt/sched-delay-put-task.patch +features/all/rt/sched-limit-nr-migrate.patch +features/all/rt/sched-mmdrop-delayed.patch +features/all/rt/kernel-sched-move-stack-kprobe-clean-up-to-__put_tas.patch +features/all/rt/sched-rt-mutex-wakeup.patch +features/all/rt/sched-might-sleep-do-not-account-rcu-depth.patch +features/all/rt/cond-resched-lock-rt-tweak.patch +features/all/rt/sched-disable-ttwu-queue.patch +features/all/rt/sched-workqueue-Only-wake-up-idle-workers-if-not-blo.patch +features/all/rt/rt-Increase-decrease-the-nr-of-migratory-tasks-when-.patch + +# MIGRATE DISABLE AND PER CPU +features/all/rt/hotplug-light-get-online-cpus.patch +features/all/rt/ftrace-migrate-disable-tracing.patch + +# LOCKDEP +features/all/rt/lockdep-no-softirq-accounting-on-rt.patch + +# SOFTIRQ +features/all/rt/tasklet-rt-prevent-tasklets-from-going-into-infinite-spin-in-rt.patch +features/all/rt/softirq-preempt-fix-3-re.patch +features/all/rt/softirq-disable-softirq-stacks-for-rt.patch +features/all/rt/softirq-split-locks.patch +features/all/rt/net-core-use-local_bh_disable-in-netif_rx_ni.patch +features/all/rt/irq-allow-disabling-of-softirq-processing-in-irq-thread-context.patch +features/all/rt/softirq-split-timer-softirqs-out-of-ksoftirqd.patch +features/all/rt/rtmutex-trylock-is-okay-on-RT.patch + +# compile fix due to rtmutex locks +features/all/rt/fs-nfs-turn-rmdir_sem-into-a-semaphore.patch + +# FUTEX/RTMUTEX +features/all/rt/rtmutex-futex-prepare-rt.patch +features/all/rt/futex-requeue-pi-fix.patch +features/all/rt/futex-Ensure-lock-unlock-symetry-versus-pi_lock-and-.patch + +# RTMUTEX +features/all/rt/pid.h-include-atomic.h.patch +features/all/rt/arm-include-definition-for-cpumask_t.patch +features/all/rt/locking-locktorture-Do-NOT-include-rwlock.h-directly.patch +features/all/rt/rtmutex-lock-killable.patch +features/all/rt/rtmutex-Make-lock_killable-work.patch +features/all/rt/spinlock-types-separate-raw.patch +features/all/rt/rtmutex-avoid-include-hell.patch +features/all/rt/rtmutex_dont_include_rcu.patch +features/all/rt/rtmutex-Provide-rt_mutex_slowlock_locked.patch +features/all/rt/rtmutex-export-lockdep-less-version-of-rt_mutex-s-lo.patch +features/all/rt/rtmutex-add-sleeping-lock-implementation.patch +features/all/rt/rtmutex-add-mutex-implementation-based-on-rtmutex.patch +features/all/rt/rtmutex-add-rwsem-implementation-based-on-rtmutex.patch +features/all/rt/rtmutex-add-rwlock-implementation-based-on-rtmutex.patch +features/all/rt/rtmutex-wire-up-RT-s-locking.patch +features/all/rt/rtmutex-add-ww_mutex-addon-for-mutex-rt.patch +features/all/rt/locking-rt-mutex-fix-deadlock-in-device-mapper-block.patch +features/all/rt/locking-rtmutex-re-init-the-wait_lock-in-rt_mutex_in.patch +features/all/rt/ptrace-fix-ptrace-vs-tasklist_lock-race.patch +features/all/rt/rtmutex-annotate-sleeping-lock-context.patch +features/all/rt/sched-migrate_disable-fallback-to-preempt_disable-in.patch +features/all/rt/locking-don-t-check-for-__LINUX_SPINLOCK_TYPES_H-on-.patch + +# RCU +features/all/rt/peter_zijlstra-frob-rcu.patch +features/all/rt/rcu-merge-rcu-bh-into-rcu-preempt-for-rt.patch +features/all/rt/patch-to-introduce-rcu-bh-qs-where-safe-from-softirq.patch +features/all/rt/rcu-Eliminate-softirq-processing-from-rcutree.patch +features/all/rt/srcu-use-cpu_online-instead-custom-check.patch +features/all/rt/srcu-replace-local_irqsave-with-a-locallock.patch +features/all/rt/rcu-enable-rcu_normal_after_boot-by-default-for-RT.patch + +# DRIVERS SERIAL +features/all/rt/drivers-tty-fix-omap-lock-crap.patch +features/all/rt/drivers-tty-pl011-irq-disable-madness.patch +features/all/rt/rt-serial-warn-fix.patch +features/all/rt/tty-serial-8250-don-t-take-the-trylock-during-oops.patch + +# FS +features/all/rt/peterz-percpu-rwsem-rt.patch +features/all/rt/mm-protect-activate-switch-mm.patch +features/all/rt/fs-dcache-bring-back-explicit-INIT_HLIST_BL_HEAD-in.patch +features/all/rt/fs-dcache-disable-preemption-on-i_dir_seq-s-write-si.patch +features/all/rt/squashfs-make-use-of-local-lock-in-multi_cpu-decompr.patch + +# X86 +features/all/rt/thermal-Defer-thermal-wakups-to-threads.patch + +# CPU get light +features/all/rt/epoll-use-get-cpu-light.patch +features/all/rt/mm-vmalloc-use-get-cpu-light.patch +features/all/rt/block-mq-use-cpu_light.patch +features/all/rt/block-mq-drop-preempt-disable.patch +features/all/rt/block-mq-don-t-complete-requests-via-IPI.patch +features/all/rt/md-raid5-percpu-handling-rt-aware.patch + +# CPU CHILL +features/all/rt/rt-introduce-cpu-chill.patch + +# block +features/all/rt/block-blk-mq-move-blk_queue_usage_counter_release-in.patch + +# BLOCK LIVELOCK PREVENTION +features/all/rt/block-use-cpu-chill.patch + +# FS LIVELOCK PREVENTION +features/all/rt/fs-dcache-use-cpu-chill-in-trylock-loops.patch +features/all/rt/net-use-cpu-chill.patch +features/all/rt/fs-dcache-use-swait_queue-instead-of-waitqueue.patch + +# WORKQUEUE more fixes +features/all/rt/workqueue-use-rcu.patch +features/all/rt/workqueue-use-locallock.patch +features/all/rt/work-queue-work-around-irqsafe-timer-optimization.patch +features/all/rt/workqueue-distangle-from-rq-lock.patch + +# DEBUGOBJECTS +features/all/rt/debugobjects-rt.patch + +# SEQLOCKS +features/all/rt/seqlock-prevent-rt-starvation.patch + +# NETWORKING +features/all/rt/sunrpc-make-svc_xprt_do_enqueue-use-get_cpu_light.patch +features/all/rt/skbufhead-raw-lock.patch +features/all/rt/net-move-xmit_recursion-to-per-task-variable-on-RT.patch +features/all/rt/net-provide-a-way-to-delegate-processing-a-softirq-t.patch +features/all/rt/net-dev-always-take-qdisc-s-busylock-in-__dev_xmit_s.patch +features/all/rt/net-Qdisc-use-a-seqlock-instead-seqcount.patch +features/all/rt/net-add-back-the-missing-serialization-in-ip_send_un.patch +features/all/rt/net-add-a-lock-around-icmp_sk.patch +features/all/rt/net-Have-__napi_schedule_irqoff-disable-interrupts-o.patch + +# irqwork +features/all/rt/irqwork-push_most_work_into_softirq_context.patch + +# CONSOLE. NEEDS more thought !!! +features/all/rt/printk-rt-aware.patch +features/all/rt/kernel-printk-Don-t-try-to-print-from-IRQ-NMI-region.patch +features/all/rt/HACK-printk-drop-the-logbuf_lock-more-often.patch + +# POWERC +features/all/rt/powerpc-ps3-device-init.c-adapt-to-completions-using.patch + +# ARM +features/all/rt/ARM-enable-irq-in-translation-section-permission-fau.patch +features/all/rt/genirq-update-irq_set_irqchip_state-documentation.patch +features/all/rt/KVM-arm-arm64-downgrade-preempt_disable-d-region-to-.patch +features/all/rt/arm64-fpsimd-use-preemp_disable-in-addition-to-local.patch + +# KGDB +features/all/rt/kgb-serial-hackaround.patch + +# SYSFS - RT indicator +features/all/rt/sysfs-realtime-entry.patch + +# KMAP/HIGHMEM +features/all/rt/mm-rt-kmap-atomic-scheduling.patch +features/all/rt/x86-highmem-add-a-already-used-pte-check.patch +features/all/rt/arm-highmem-flush-tlb-on-unmap.patch +features/all/rt/arm-enable-highmem-for-rt.patch + +# SCSI/FCOE +features/all/rt/scsi-fcoe-rt-aware.patch + +# crypto drivers +features/all/rt/x86-crypto-reduce-preempt-disabled-regions.patch +features/all/rt/crypto-Reduce-preempt-disabled-regions-more-algos.patch +features/all/rt/crypto-limit-more-FPU-enabled-sections.patch +features/all/rt/crypto-scompress-serialize-RT-percpu-scratch-buffer-.patch +features/all/rt/crypto-cryptd-add-a-lock-instead-preempt_disable-loc.patch + +# RANDOM +features/all/rt/panic-disable-random-on-rt.patch +features/all/rt/x86-stackprot-no-random-on-rt.patch +features/all/rt/random-make-it-work-on-rt.patch +features/all/rt/random-avoid-preempt_disable-ed-section.patch + +# HOTPLUG +features/all/rt/cpu-hotplug--Implement-CPU-pinning.patch +features/all/rt/hotplug-duct-tape-RT-rwlock-usage-for-non-RT.patch + +# NET +features/all/rt/upstream-net-rt-remove-preemption-disabling-in-netif_rx.patch +features/all/rt/net-another-local-irq-disable-alloc-atomic-headache.patch +features/all/rt/net-core-protect-users-of-napi_alloc_cache-against-r.patch +features/all/rt/net-fix-iptable-xt-write-recseq-begin-rt-fallout.patch +features/all/rt/net-make-devnet_rename_seq-a-mutex.patch + +# LOCKDEP +features/all/rt/lockdep-selftest-only-do-hardirq-context-test-for-raw-spinlock.patch +features/all/rt/lockdep-selftest-fix-warnings-due-to-missing-PREEMPT.patch + +# PREEMPT LAZY +features/all/rt/preempt-lazy-support.patch +features/all/rt/ftrace-Fix-trace-header-alignment.patch +features/all/rt/x86-preempt-lazy.patch +features/all/rt/arm-preempt-lazy-support.patch +features/all/rt/powerpc-preempt-lazy-support.patch +features/all/rt/arch-arm64-Add-lazy-preempt-support.patch + +# DRIVERS +features/all/rt/connector-cn_proc-Protect-send_msg-with-a-local-lock.patch +features/all/rt/drivers-block-zram-Replace-bit-spinlocks-with-rtmute.patch +features/all/rt/drivers-zram-Don-t-disable-preemption-in-zcomp_strea.patch +features/all/rt/drivers-zram-fix-zcomp_stream_get-smp_processor_id-u.patch +features/all/rt/tpm_tis-fix-stall-after-iowrite-s.patch +features/all/rt/pci-switchtec-Don-t-use-completion-s-wait-queue.patch + +# I915 +features/all/rt/drmradeoni915_Use_preempt_disableenable_rt()_where_recommended.patch +features/all/rt/drmi915_Use_local_lockunlock_irq()_in_intel_pipe_update_startend().patch + +# CGROUPS +features/all/rt/cgroups-use-simple-wait-in-css_release.patch +features/all/rt/cpuset-Convert-callback_lock-to-raw_spinlock_t.patch + +# Security +features/all/rt/apparmor-use-a-locallock-instead-preempt_disable.patch + +# WORKQUEUE SIGH +features/all/rt/workqueue-prevent-deadlock-stall.patch + +# Nice to have +features/all/rt/signals-allow-rt-tasks-to-cache-one-sigqueue-struct.patch + +# Add RT to version +features/all/rt/localversion.patch