---
 Documentation/driver-api/libata.rst                 |    3 
 arch/Kconfig                                        |    1 
 arch/alpha/include/asm/spinlock_types.h             |    4 
 arch/arm/Kconfig                                    |    5 
 arch/arm/configs/at91_dt_defconfig                  |    2 
 arch/arm/configs/sama5_defconfig                    |    2 
 arch/arm/include/asm/irq.h                          |    2 
 arch/arm/include/asm/spinlock_types.h               |    4 
 arch/arm/include/asm/switch_to.h                    |    8 
 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/patch.c                             |    6 
 arch/arm/kernel/process.c                           |   24 
 arch/arm/kernel/signal.c                            |    3 
 arch/arm/kernel/unwind.c                            |   14 
 arch/arm/mach-at91/Kconfig                          |   25 
 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/mm/fault.c                                 |    6 
 arch/arm/mm/highmem.c                               |   58 +
 arch/arm/plat-versatile/platsmp.c                   |   10 
 arch/arm64/Kconfig                                  |    1 
 arch/arm64/crypto/Kconfig                           |   30 
 arch/arm64/crypto/crc32-ce-glue.c                   |    3 
 arch/arm64/include/asm/alternative.h                |    6 
 arch/arm64/include/asm/spinlock_types.h             |    4 
 arch/arm64/include/asm/thread_info.h                |    6 
 arch/arm64/kernel/alternative.c                     |    1 
 arch/arm64/kernel/asm-offsets.c                     |    1 
 arch/arm64/kernel/entry.S                           |   12 
 arch/arm64/kernel/fpsimd.c                          |   31 
 arch/arm64/kernel/signal.c                          |    2 
 arch/arm64/kvm/va_layout.c                          |    7 
 arch/hexagon/include/asm/spinlock_types.h           |    4 
 arch/ia64/include/asm/spinlock_types.h              |    4 
 arch/ia64/kernel/mca.c                              |    2 
 arch/mips/Kconfig                                   |    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/Kconfig                                |    6 
 arch/powerpc/include/asm/spinlock_types.h           |    4 
 arch/powerpc/include/asm/thread_info.h              |    9 
 arch/powerpc/kernel/asm-offsets.c                   |    1 
 arch/powerpc/kernel/entry_32.S                      |   17 
 arch/powerpc/kernel/entry_64.S                      |   16 
 arch/powerpc/kernel/irq.c                           |    2 
 arch/powerpc/kernel/misc_32.S                       |    2 
 arch/powerpc/kernel/misc_64.S                       |    2 
 arch/powerpc/kvm/Kconfig                            |    1 
 arch/powerpc/platforms/cell/spufs/sched.c           |    2 
 arch/powerpc/platforms/ps3/device-init.c            |    2 
 arch/s390/include/asm/spinlock_types.h              |    4 
 arch/sh/include/asm/spinlock_types.h                |    4 
 arch/sh/kernel/irq.c                                |    2 
 arch/sparc/kernel/irq_64.c                          |    2 
 arch/x86/Kconfig                                    |    8 
 arch/x86/crypto/aesni-intel_glue.c                  |   22 
 arch/x86/crypto/cast5_avx_glue.c                    |   21 
 arch/x86/crypto/chacha20_glue.c                     |    9 
 arch/x86/crypto/glue_helper.c                       |   31 
 arch/x86/entry/common.c                             |   11 
 arch/x86/entry/entry_32.S                           |   17 
 arch/x86/entry/entry_64.S                           |   18 
 arch/x86/include/asm/fpu/api.h                      |    1 
 arch/x86/include/asm/preempt.h                      |   31 
 arch/x86/include/asm/signal.h                       |   13 
 arch/x86/include/asm/stackprotector.h               |    8 
 arch/x86/include/asm/thread_info.h                  |   11 
 arch/x86/kernel/apic/io_apic.c                      |   23 
 arch/x86/kernel/asm-offsets.c                       |    2 
 arch/x86/kernel/fpu/core.c                          |   12 
 arch/x86/kernel/irq_32.c                            |    2 
 arch/x86/kernel/process_32.c                        |   32 
 arch/x86/kvm/lapic.c                                |    2 
 arch/x86/kvm/x86.c                                  |    7 
 arch/x86/mm/highmem_32.c                            |   13 
 arch/x86/mm/iomap_32.c                              |   11 
 arch/x86/platform/efi/efi_64.c                      |   10 
 arch/xtensa/include/asm/spinlock_types.h            |    4 
 block/blk-core.c                                    |   17 
 block/blk-ioc.c                                     |    5 
 block/blk-mq.c                                      |   36 
 block/blk-mq.h                                      |    4 
 block/blk-softirq.c                                 |    3 
 crypto/cryptd.c                                     |   19 
 crypto/scompress.c                                  |    6 
 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 
 drivers/block/zram/zcomp.c                          |   13 
 drivers/block/zram/zcomp.h                          |    1 
 drivers/block/zram/zram_drv.c                       |   33 
 drivers/block/zram/zram_drv.h                       |    3 
 drivers/char/random.c                               |   26 
 drivers/char/tpm/tpm_tis.c                          |   29 
 drivers/clocksource/Kconfig                         |   13 
 drivers/clocksource/Makefile                        |    3 
 drivers/clocksource/tcb_clksrc.c                    |   69 +
 drivers/clocksource/timer-atmel-tcb.c               |  608 +++++++++++++
 drivers/connector/cn_proc.c                         |    6 
 drivers/cpufreq/Kconfig.x86                         |    2 
 drivers/firmware/efi/efi.c                          |    5 
 drivers/gpu/drm/i915/i915_irq.c                     |    2 
 drivers/gpu/drm/i915/intel_sprite.c                 |   11 
 drivers/gpu/drm/radeon/radeon_display.c             |    2 
 drivers/hv/hv.c                                     |    4 
 drivers/hv/hyperv_vmbus.h                           |    1 
 drivers/hv/vmbus_drv.c                              |    4 
 drivers/infiniband/hw/hfi1/affinity.c               |    6 
 drivers/infiniband/hw/hfi1/sdma.c                   |    3 
 drivers/infiniband/hw/qib/qib_file_ops.c            |    7 
 drivers/iommu/amd_iommu.c                           |   12 
 drivers/irqchip/irq-gic-v3-its.c                    |   98 +-
 drivers/leds/trigger/Kconfig                        |    2 
 drivers/md/bcache/Kconfig                           |    1 
 drivers/md/dm-rq.c                                  |    1 
 drivers/md/raid5.c                                  |   14 
 drivers/md/raid5.h                                  |    1 
 drivers/misc/Kconfig                                |   12 
 drivers/net/wireless/intersil/orinoco/orinoco_usb.c |    2 
 drivers/of/base.c                                   |   22 
 drivers/pci/switch/switchtec.c                      |   22 
 drivers/scsi/fcoe/fcoe.c                            |   16 
 drivers/scsi/fcoe/fcoe_ctlr.c                       |    4 
 drivers/scsi/libfc/fc_exch.c                        |    4 
 drivers/scsi/libsas/sas_ata.c                       |    3 
 drivers/scsi/qla2xxx/qla_inline.h                   |    4 
 drivers/staging/android/vsoc.c                      |    6 
 drivers/thermal/x86_pkg_temp_thermal.c              |   52 +
 drivers/tty/serial/8250/8250_core.c                 |   11 
 drivers/tty/serial/8250/8250_port.c                 |    5 
 drivers/tty/serial/amba-pl011.c                     |   15 
 drivers/tty/serial/omap-serial.c                    |   12 
 drivers/usb/core/hcd.c                              |    3 
 drivers/usb/gadget/function/f_fs.c                  |    2 
 drivers/usb/gadget/legacy/inode.c                   |    4 
 fs/aio.c                                            |   15 
 fs/autofs/expire.c                                  |    3 
 fs/buffer.c                                         |   21 
 fs/cifs/readdir.c                                   |    2 
 fs/dcache.c                                         |   50 -
 fs/eventpoll.c                                      |    4 
 fs/exec.c                                           |    2 
 fs/ext4/page-io.c                                   |    6 
 fs/fscache/cookie.c                                 |    8 
 fs/fscache/main.c                                   |    1 
 fs/fuse/dir.c                                       |    2 
 fs/inode.c                                          |    2 
 fs/libfs.c                                          |    6 
 fs/locks.c                                          |   32 
 fs/namei.c                                          |    4 
 fs/namespace.c                                      |    8 
 fs/nfs/delegation.c                                 |    4 
 fs/nfs/dir.c                                        |   12 
 fs/nfs/inode.c                                      |    4 
 fs/nfs/nfs4_fs.h                                    |    2 
 fs/nfs/nfs4proc.c                                   |    4 
 fs/nfs/nfs4state.c                                  |   22 
 fs/nfs/unlink.c                                     |   35 
 fs/ntfs/aops.c                                      |   14 
 fs/proc/array.c                                     |    4 
 fs/proc/base.c                                      |    2 
 fs/proc/proc_sysctl.c                               |    2 
 fs/squashfs/decompressor_multi_percpu.c             |   16 
 fs/timerfd.c                                        |    5 
 fs/xfs/xfs_aops.c                                   |    6 
 include/linux/backing-dev-defs.h                    |    3 
 include/linux/backing-dev.h                         |    4 
 include/linux/blk-mq.h                              |    2 
 include/linux/blkdev.h                              |    5 
 include/linux/bottom_half.h                         |   34 
 include/linux/buffer_head.h                         |   42 
 include/linux/cgroup-defs.h                         |    2 
 include/linux/completion.h                          |    8 
 include/linux/cpu.h                                 |    5 
 include/linux/dcache.h                              |    4 
 include/linux/delay.h                               |    6 
 include/linux/fs.h                                  |    2 
 include/linux/fscache.h                             |    1 
 include/linux/highmem.h                             |   32 
 include/linux/hrtimer.h                             |   38 
 include/linux/idr.h                                 |    5 
 include/linux/interrupt.h                           |   66 +
 include/linux/irq.h                                 |    4 
 include/linux/irq_work.h                            |    8 
 include/linux/irqchip/arm-gic-v3.h                  |    1 
 include/linux/irqdesc.h                             |    1 
 include/linux/irqflags.h                            |   23 
 include/linux/jbd2.h                                |   24 
 include/linux/kdb.h                                 |    2 
 include/linux/kernel.h                              |    4 
 include/linux/libata.h                              |    2 
 include/linux/list_bl.h                             |   30 
 include/linux/list_lru.h                            |   25 
 include/linux/locallock.h                           |  281 ++++++
 include/linux/mm_types.h                            |    4 
 include/linux/mutex.h                               |   20 
 include/linux/mutex_rt.h                            |  130 ++
 include/linux/netdevice.h                           |  108 ++
 include/linux/netfilter/x_tables.h                  |    7 
 include/linux/nfs_fs.h                              |    4 
 include/linux/nfs_xdr.h                             |    2 
 include/linux/percpu-rwsem.h                        |   24 
 include/linux/percpu.h                              |   29 
 include/linux/pid.h                                 |    1 
 include/linux/posix-timers.h                        |    2 
 include/linux/preempt.h                             |  107 ++
 include/linux/printk.h                              |    2 
 include/linux/radix-tree.h                          |    7 
 include/linux/random.h                              |    2 
 include/linux/rbtree.h                              |    2 
 include/linux/rcu_assign_pointer.h                  |   54 +
 include/linux/rcupdate.h                            |   75 -
 include/linux/rcutree.h                             |    8 
 include/linux/rtmutex.h                             |   22 
 include/linux/rwlock_rt.h                           |  119 ++
 include/linux/rwlock_types.h                        |    4 
 include/linux/rwlock_types_rt.h                     |   55 +
 include/linux/rwsem.h                               |   11 
 include/linux/rwsem_rt.h                            |   68 +
 include/linux/sched.h                               |  162 +++
 include/linux/sched/mm.h                            |   11 
 include/linux/sched/task.h                          |   11 
 include/linux/sched/user.h                          |    5 
 include/linux/sched/wake_q.h                        |   27 
 include/linux/seqlock.h                             |   66 +
 include/linux/signal.h                              |    1 
 include/linux/skbuff.h                              |    7 
 include/linux/smp.h                                 |    3 
 include/linux/spinlock.h                            |   12 
 include/linux/spinlock_api_smp.h                    |    4 
 include/linux/spinlock_rt.h                         |  156 +++
 include/linux/spinlock_types.h                      |   76 -
 include/linux/spinlock_types_nort.h                 |   33 
 include/linux/spinlock_types_raw.h                  |   55 +
 include/linux/spinlock_types_rt.h                   |   48 +
 include/linux/spinlock_types_up.h                   |    4 
 include/linux/suspend.h                             |    6 
 include/linux/swait.h                               |    1 
 include/linux/swap.h                                |    2 
 include/linux/swork.h                               |   24 
 include/linux/thread_info.h                         |   12 
 include/linux/timer.h                               |    2 
 include/linux/trace_events.h                        |    3 
 include/linux/uaccess.h                             |    2 
 include/linux/vmstat.h                              |    4 
 include/linux/wait.h                                |    5 
 include/net/gen_stats.h                             |    9 
 include/net/neighbour.h                             |    6 
 include/net/net_seq_lock.h                          |   15 
 include/net/sch_generic.h                           |   19 
 include/soc/at91/atmel_tcb.h                        |  216 ++++
 include/trace/events/cgroup.h                       |   47 -
 init/Kconfig                                        |    5 
 init/Makefile                                       |    2 
 init/init_task.c                                    |   10 
 init/main.c                                         |    1 
 kernel/Kconfig.locks                                |    4 
 kernel/Kconfig.preempt                              |   33 
 kernel/cgroup/cgroup-internal.h                     |   26 
 kernel/cgroup/cgroup-v1.c                           |    4 
 kernel/cgroup/cgroup.c                              |   21 
 kernel/cgroup/cpuset.c                              |   68 -
 kernel/cgroup/rstat.c                               |    5 
 kernel/cpu.c                                        |   67 +
 kernel/debug/kdb/kdb_io.c                           |    2 
 kernel/events/core.c                                |    4 
 kernel/exit.c                                       |    2 
 kernel/fork.c                                       |   45 
 kernel/futex.c                                      |  128 ++
 kernel/irq/handle.c                                 |    8 
 kernel/irq/manage.c                                 |   66 +
 kernel/irq/settings.h                               |   12 
 kernel/irq/spurious.c                               |    8 
 kernel/irq_work.c                                   |   60 +
 kernel/ksysfs.c                                     |   12 
 kernel/locking/Makefile                             |    9 
 kernel/locking/lockdep.c                            |    2 
 kernel/locking/locktorture.c                        |    1 
 kernel/locking/mutex-rt.c                           |  223 ++++
 kernel/locking/rtmutex.c                            |  931 +++++++++++++++++---
 kernel/locking/rtmutex_common.h                     |   29 
 kernel/locking/rwlock-rt.c                          |  378 ++++++++
 kernel/locking/rwsem-rt.c                           |  293 ++++++
 kernel/locking/spinlock.c                           |    7 
 kernel/locking/spinlock_debug.c                     |    5 
 kernel/panic.c                                      |    2 
 kernel/power/hibernate.c                            |    7 
 kernel/power/suspend.c                              |    4 
 kernel/printk/printk.c                              |  156 ++-
 kernel/ptrace.c                                     |    9 
 kernel/rcu/Kconfig                                  |    6 
 kernel/rcu/rcu.h                                    |   14 
 kernel/rcu/rcutorture.c                             |    7 
 kernel/rcu/srcutree.c                               |   36 
 kernel/rcu/tree.c                                   |  153 ++-
 kernel/rcu/tree.h                                   |    6 
 kernel/rcu/tree_exp.h                               |    4 
 kernel/rcu/tree_plugin.h                            |  156 ---
 kernel/rcu/update.c                                 |    4 
 kernel/sched/Makefile                               |    2 
 kernel/sched/completion.c                           |   34 
 kernel/sched/core.c                                 |  575 +++++++++---
 kernel/sched/cpudeadline.c                          |    4 
 kernel/sched/cpupri.c                               |    4 
 kernel/sched/deadline.c                             |    8 
 kernel/sched/debug.c                                |    4 
 kernel/sched/fair.c                                 |   52 -
 kernel/sched/features.h                             |    8 
 kernel/sched/rt.c                                   |    8 
 kernel/sched/sched.h                                |   10 
 kernel/sched/swait.c                                |   20 
 kernel/sched/swork.c                                |  173 +++
 kernel/sched/topology.c                             |    1 
 kernel/signal.c                                     |  114 ++
 kernel/softirq.c                                    |  706 +++++++++++++--
 kernel/time/alarmtimer.c                            |    2 
 kernel/time/hrtimer.c                               |  147 ++-
 kernel/time/itimer.c                                |    1 
 kernel/time/jiffies.c                               |    7 
 kernel/time/posix-cpu-timers.c                      |  154 +++
 kernel/time/posix-timers.c                          |   39 
 kernel/time/tick-broadcast-hrtimer.c                |    2 
 kernel/time/tick-common.c                           |   10 
 kernel/time/tick-sched.c                            |   31 
 kernel/time/timekeeping.c                           |    6 
 kernel/time/timekeeping.h                           |    3 
 kernel/time/timer.c                                 |   61 +
 kernel/trace/trace.c                                |   37 
 kernel/trace/trace.h                                |    2 
 kernel/trace/trace_events.c                         |    2 
 kernel/trace/trace_hwlat.c                          |    2 
 kernel/trace/trace_output.c                         |   19 
 kernel/user.c                                       |   11 
 kernel/watchdog.c                                   |    2 
 kernel/watchdog_hld.c                               |   10 
 kernel/workqueue.c                                  |  243 +++--
 kernel/workqueue_internal.h                         |    5 
 lib/Kconfig                                         |    1 
 lib/Kconfig.debug                                   |    2 
 lib/debugobjects.c                                  |    5 
 lib/irq_poll.c                                      |    5 
 lib/locking-selftest.c                              |   50 +
 lib/radix-tree.c                                    |   32 
 lib/scatterlist.c                                   |    2 
 lib/smp_processor_id.c                              |    2 
 localversion-rt                                     |    1 
 mm/Kconfig                                          |    2 
 mm/backing-dev.c                                    |   15 
 mm/compaction.c                                     |    6 
 mm/highmem.c                                        |    6 
 mm/list_lru.c                                       |   45 
 mm/memcontrol.c                                     |   28 
 mm/mmu_context.c                                    |    2 
 mm/page_alloc.c                                     |  196 +++-
 mm/slab.c                                           |   94 +-
 mm/slab.h                                           |    2 
 mm/slub.c                                           |  139 ++
 mm/swap.c                                           |   74 +
 mm/vmalloc.c                                        |   13 
 mm/vmstat.c                                         |   12 
 mm/workingset.c                                     |   19 
 mm/zsmalloc.c                                       |   80 +
 net/Kconfig                                         |    2 
 net/core/dev.c                                      |  111 +-
 net/core/filter.c                                   |    6 
 net/core/gen_estimator.c                            |    6 
 net/core/gen_stats.c                                |    8 
 net/core/pktgen.c                                   |    4 
 net/core/skbuff.c                                   |   35 
 net/ipv4/icmp.c                                     |    8 
 net/ipv4/tcp_ipv4.c                                 |    6 
 net/netfilter/core.c                                |    6 
 net/packet/af_packet.c                              |    5 
 net/rds/ib_rdma.c                                   |    3 
 net/sched/sch_api.c                                 |    2 
 net/sched/sch_generic.c                             |   14 
 net/sunrpc/svc_xprt.c                               |    4 
 samples/trace_events/trace-events-sample.c          |    2 
 scripts/mkcompile_h                                 |    4 
 security/apparmor/include/path.h                    |   19 
 security/apparmor/lsm.c                             |    2 
 virt/kvm/arm/arm.c                                  |    6 
 397 files changed, 9590 insertions(+), 2073 deletions(-)

Index: linux-4.18.5-rt3/Documentation/driver-api/libata.rst
===================================================================
--- linux-4.18.5-rt3.orig/Documentation/driver-api/libata.rst
+++ linux-4.18.5-rt3/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
 ~~~~~~~~~~~~~~~~~~~
Index: linux-4.18.5-rt3/arch/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/Kconfig
+++ linux-4.18.5-rt3/arch/Kconfig
@@ -20,6 +20,7 @@ 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
Index: linux-4.18.5-rt3/arch/alpha/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/alpha/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/arm/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/Kconfig
+++ linux-4.18.5-rt3/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)
@@ -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
@@ -2169,7 +2170,7 @@ 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.
 
Index: linux-4.18.5-rt3/arch/arm/configs/at91_dt_defconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/configs/at91_dt_defconfig
+++ linux-4.18.5-rt3/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
@@ -64,7 +65,6 @@ 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
Index: linux-4.18.5-rt3/arch/arm/configs/sama5_defconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/configs/sama5_defconfig
+++ linux-4.18.5-rt3/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
@@ -75,7 +76,6 @@ 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
Index: linux-4.18.5-rt3/arch/arm/include/asm/irq.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/include/asm/irq.h
+++ linux-4.18.5-rt3/arch/arm/include/asm/irq.h
@@ -23,6 +23,8 @@
 #endif
 
 #ifndef __ASSEMBLY__
+#include <linux/cpumask.h>
+
 struct irqaction;
 struct pt_regs;
 extern void migrate_irqs(void);
Index: linux-4.18.5-rt3/arch/arm/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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 {
Index: linux-4.18.5-rt3/arch/arm/include/asm/switch_to.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/include/asm/switch_to.h
+++ linux-4.18.5-rt3/arch/arm/include/asm/switch_to.h
@@ -4,6 +4,13 @@
 
 #include <linux/thread_info.h>
 
+#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)
 
Index: linux-4.18.5-rt3/arch/arm/include/asm/thread_info.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/include/asm/thread_info.h
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/arch/arm/kernel/asm-offsets.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/asm-offsets.c
+++ linux-4.18.5-rt3/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));
Index: linux-4.18.5-rt3/arch/arm/kernel/entry-armv.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/entry-armv.S
+++ linux-4.18.5-rt3/arch/arm/kernel/entry-armv.S
@@ -216,11 +216,18 @@ __irq_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 @@ svc_preempt:
 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:
Index: linux-4.18.5-rt3/arch/arm/kernel/entry-common.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/entry-common.S
+++ linux-4.18.5-rt3/arch/arm/kernel/entry-common.S
@@ -56,7 +56,9 @@ __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     fast_work_pending
+       tst     r1, #_TIF_SECCOMP
        bne     fast_work_pending
 
 
@@ -93,8 +95,11 @@ __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)
 
Index: linux-4.18.5-rt3/arch/arm/kernel/patch.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/patch.c
+++ linux-4.18.5-rt3/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);
 }
Index: linux-4.18.5-rt3/arch/arm/kernel/process.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/process.c
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/arm/kernel/signal.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/signal.c
+++ linux-4.18.5-rt3/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)))
Index: linux-4.18.5-rt3/arch/arm/kernel/unwind.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/kernel/unwind.c
+++ linux-4.18.5-rt3/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);
 }
Index: linux-4.18.5-rt3/arch/arm/mach-at91/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-at91/Kconfig
+++ linux-4.18.5-rt3/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
 
Index: linux-4.18.5-rt3/arch/arm/mach-exynos/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-exynos/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mach-hisi/platmcpm.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-hisi/platmcpm.c
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/arm/mach-omap2/omap-smp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-omap2/omap-smp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mach-prima2/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-prima2/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mach-qcom/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-qcom/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mach-spear/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-spear/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mach-sti/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mach-sti/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mm/fault.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mm/fault.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm/mm/highmem.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/mm/highmem.c
+++ linux-4.18.5-rt3/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;
 }
@@ -106,44 +115,75 @@ 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));
-               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() */
                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
Index: linux-4.18.5-rt3/arch/arm/plat-versatile/platsmp.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm/plat-versatile/platsmp.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/arm64/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/Kconfig
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/arm64/crypto/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/crypto/Kconfig
+++ linux-4.18.5-rt3/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
 
Index: linux-4.18.5-rt3/arch/arm64/crypto/crc32-ce-glue.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/crypto/crc32-ce-glue.c
+++ linux-4.18.5-rt3/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;
 
Index: linux-4.18.5-rt3/arch/arm64/include/asm/alternative.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/include/asm/alternative.h
+++ linux-4.18.5-rt3/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"                                     \
Index: linux-4.18.5-rt3/arch/arm64/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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 <linux/types.h>
 
 #define TICKET_SHIFT   16
Index: linux-4.18.5-rt3/arch/arm64/include/asm/thread_info.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/include/asm/thread_info.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/arch/arm64/kernel/alternative.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kernel/alternative.c
+++ linux-4.18.5-rt3/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);
 }
 
Index: linux-4.18.5-rt3/arch/arm64/kernel/asm-offsets.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kernel/asm-offsets.c
+++ linux-4.18.5-rt3/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));
Index: linux-4.18.5-rt3/arch/arm64/kernel/entry.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kernel/entry.S
+++ linux-4.18.5-rt3/arch/arm64/kernel/entry.S
@@ -633,11 +633,16 @@ el1_irq:
 
 #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 @@ el1_preempt:
 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
 
Index: linux-4.18.5-rt3/arch/arm64/kernel/fpsimd.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kernel/fpsimd.c
+++ linux-4.18.5-rt3/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(&current->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);
 
Index: linux-4.18.5-rt3/arch/arm64/kernel/signal.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kernel/signal.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/arch/arm64/kvm/va_layout.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/arm64/kvm/va_layout.c
+++ linux-4.18.5-rt3/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()
         */
Index: linux-4.18.5-rt3/arch/hexagon/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/hexagon/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/ia64/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/ia64/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/ia64/kernel/mca.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/ia64/kernel/mca.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/arch/mips/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/mips/Kconfig
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/mips/include/asm/switch_to.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/mips/include/asm/switch_to.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/arch/mips/kernel/mips-mt-fpaff.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/mips/kernel/mips-mt-fpaff.c
+++ linux-4.18.5-rt3/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:
Index: linux-4.18.5-rt3/arch/mips/kernel/traps.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/mips/kernel/traps.c
+++ linux-4.18.5-rt3/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(&current->cpus_allowed, &mt_fpu_cpumask)) {
+               if (cpumask_intersects(&current->cpus_mask, &mt_fpu_cpumask)) {
                        cpumask_t tmask;
 
                        current->thread.user_cpus_allowed
-                               = current->cpus_allowed;
-                       cpumask_and(&tmask, &current->cpus_allowed,
+                               = current->cpus_mask;
+                       cpumask_and(&tmask, &current->cpus_mask,
                                    &mt_fpu_cpumask);
                        set_cpus_allowed_ptr(current, &tmask);
                        set_thread_flag(TIF_FPUBOUND);
Index: linux-4.18.5-rt3/arch/powerpc/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/Kconfig
+++ linux-4.18.5-rt3/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
@@ -214,6 +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
@@ -394,7 +396,7 @@ 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
Index: linux-4.18.5-rt3/arch/powerpc/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/powerpc/include/asm/thread_info.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/include/asm/thread_info.h
+++ linux-4.18.5-rt3/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;
@@ -80,7 +82,7 @@ extern int arch_dup_task_struct(struct t
 #define TIF_SIGPENDING         1       /* signal pending */
 #define TIF_NEED_RESCHED       2       /* rescheduling necessary */
 #define TIF_FSCHECK            3       /* Check FS is USER_DS on return */
-#define TIF_32BIT              4       /* 32 bit binary */
+#define TIF_NEED_RESCHED_LAZY  4       /* lazy rescheduling necessary */
 #define TIF_RESTORE_TM         5       /* need to restore TM FP/VEC/VSX */
 #define TIF_PATCH_PENDING      6       /* pending live patching update */
 #define TIF_SYSCALL_AUDIT      7       /* syscall auditing active */
@@ -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_32BIT              20      /* 32 bit binary */
 
 /* as above, but as bit values */
 #define _TIF_SYSCALL_TRACE     (1<<TIF_SYSCALL_TRACE)
@@ -118,6 +121,7 @@ extern int arch_dup_task_struct(struct t
 #define _TIF_SYSCALL_TRACEPOINT        (1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_EMULATE_STACK_STORE       (1<<TIF_EMULATE_STACK_STORE)
 #define _TIF_NOHZ              (1<<TIF_NOHZ)
+#define _TIF_NEED_RESCHED_LAZY (1<<TIF_NEED_RESCHED_LAZY)
 #define _TIF_FSCHECK           (1<<TIF_FSCHECK)
 #define _TIF_SYSCALL_DOTRACE   (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
                                 _TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
@@ -126,8 +130,9 @@ extern int arch_dup_task_struct(struct t
 #define _TIF_USER_WORK_MASK    (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
                                 _TIF_NOTIFY_RESUME | _TIF_UPROBE | \
                                 _TIF_RESTORE_TM | _TIF_PATCH_PENDING | \
-                                _TIF_FSCHECK)
+                                _TIF_FSCHECK | _TIF_NEED_RESCHED_LAZY)
 #define _TIF_PERSYSCALL_MASK   (_TIF_RESTOREALL|_TIF_NOERROR)
+#define _TIF_NEED_RESCHED_MASK (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)
 
 /* Bits in local_flags */
 /* Don't move TLF_NAPPING without adjusting the code in entry_32.S */
Index: linux-4.18.5-rt3/arch/powerpc/kernel/asm-offsets.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/asm-offsets.c
+++ linux-4.18.5-rt3/arch/powerpc/kernel/asm-offsets.c
@@ -156,6 +156,7 @@ int main(void)
        OFFSET(TI_FLAGS, thread_info, flags);
        OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
        OFFSET(TI_PREEMPT, thread_info, preempt_count);
+       OFFSET(TI_PREEMPT_LAZY, thread_info, preempt_lazy_count);
        OFFSET(TI_TASK, thread_info, task);
        OFFSET(TI_CPU, thread_info, cpu);
 
Index: linux-4.18.5-rt3/arch/powerpc/kernel/entry_32.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/entry_32.S
+++ linux-4.18.5-rt3/arch/powerpc/kernel/entry_32.S
@@ -873,7 +873,14 @@ resume_kernel:
        cmpwi   0,r0,0          /* if non-zero, just restore regs and return */
        bne     restore
        andi.   r8,r8,_TIF_NEED_RESCHED
+       bne+    1f
+       lwz     r0,TI_PREEMPT_LAZY(r9)
+       cmpwi   0,r0,0          /* if non-zero, just restore regs and return */
+       bne     restore
+       lwz     r0,TI_FLAGS(r9)
+       andi.   r0,r0,_TIF_NEED_RESCHED_LAZY
        beq+    restore
+1:
        lwz     r3,_MSR(r1)
        andi.   r0,r3,MSR_EE    /* interrupts off? */
        beq     restore         /* don't schedule if so */
@@ -884,11 +891,11 @@ resume_kernel:
         */
        bl      trace_hardirqs_off
 #endif
-1:     bl      preempt_schedule_irq
+2:     bl      preempt_schedule_irq
        CURRENT_THREAD_INFO(r9, r1)
        lwz     r3,TI_FLAGS(r9)
-       andi.   r0,r3,_TIF_NEED_RESCHED
-       bne-    1b
+       andi.   r0,r3,_TIF_NEED_RESCHED_MASK
+       bne-    2b
 #ifdef CONFIG_TRACE_IRQFLAGS
        /* And now, to properly rebalance the above, we tell lockdep they
         * are being turned back on, which will happen when we return
@@ -1211,7 +1218,7 @@ global_dbcr0:
 #endif /* !(CONFIG_4xx || CONFIG_BOOKE) */
 
 do_work:                       /* r10 contains MSR_KERNEL here */
-       andi.   r0,r9,_TIF_NEED_RESCHED
+       andi.   r0,r9,_TIF_NEED_RESCHED_MASK
        beq     do_user_signal
 
 do_resched:                    /* r10 contains MSR_KERNEL here */
@@ -1232,7 +1239,7 @@ recheck:
        MTMSRD(r10)             /* disable interrupts */
        CURRENT_THREAD_INFO(r9, r1)
        lwz     r9,TI_FLAGS(r9)
-       andi.   r0,r9,_TIF_NEED_RESCHED
+       andi.   r0,r9,_TIF_NEED_RESCHED_MASK
        bne-    do_resched
        andi.   r0,r9,_TIF_USER_WORK_MASK
        beq     restore_user
Index: linux-4.18.5-rt3/arch/powerpc/kernel/entry_64.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/entry_64.S
+++ linux-4.18.5-rt3/arch/powerpc/kernel/entry_64.S
@@ -168,7 +168,7 @@ system_call:                        /* label this so stack tr
  * based on caller's run-mode / personality.
  */
        ld      r11,SYS_CALL_TABLE@toc(2)
-       andi.   r10,r10,_TIF_32BIT
+       andis.  r10,r10,_TIF_32BIT@h
        beq     15f
        addi    r11,r11,8       /* use 32-bit syscall entries */
        clrldi  r3,r3,32
@@ -707,7 +707,7 @@ _GLOBAL(ret_from_except_lite)
        bl      restore_math
        b       restore
 #endif
-1:     andi.   r0,r4,_TIF_NEED_RESCHED
+1:     andi.   r0,r4,_TIF_NEED_RESCHED_MASK
        beq     2f
        bl      restore_interrupts
        SCHEDULE_USER
@@ -769,10 +769,18 @@ resume_kernel:
 
 #ifdef CONFIG_PREEMPT
        /* Check if we need to preempt */
+       lwz     r8,TI_PREEMPT(r9)
+       cmpwi   0,r8,0          /* if non-zero, just restore regs and return */
+       bne     restore
        andi.   r0,r4,_TIF_NEED_RESCHED
+       bne+    check_count
+
+       andi.   r0,r4,_TIF_NEED_RESCHED_LAZY
        beq+    restore
+       lwz     r8,TI_PREEMPT_LAZY(r9)
+
        /* Check that preempt_count() == 0 and interrupts are enabled */
-       lwz     r8,TI_PREEMPT(r9)
+check_count:
        cmpwi   cr0,r8,0
        bne     restore
        ld      r0,SOFTE(r1)
@@ -789,7 +797,7 @@ resume_kernel:
        /* Re-test flags and eventually loop */
        CURRENT_THREAD_INFO(r9, r1)
        ld      r4,TI_FLAGS(r9)
-       andi.   r0,r4,_TIF_NEED_RESCHED
+       andi.   r0,r4,_TIF_NEED_RESCHED_MASK
        bne     1b
 
        /*
Index: linux-4.18.5-rt3/arch/powerpc/kernel/irq.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/irq.c
+++ linux-4.18.5-rt3/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)
 {
Index: linux-4.18.5-rt3/arch/powerpc/kernel/misc_32.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/misc_32.S
+++ linux-4.18.5-rt3/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 @@ _GLOBAL(call_do_softirq)
        stw     r10,THREAD+KSP_LIMIT(r2)
        mtlr    r0
        blr
+#endif
 
 /*
  * void call_do_irq(struct pt_regs *regs, struct thread_info *irqtp);
Index: linux-4.18.5-rt3/arch/powerpc/kernel/misc_64.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kernel/misc_64.S
+++ linux-4.18.5-rt3/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 @@ _GLOBAL(call_do_softirq)
        ld      r0,16(r1)
        mtlr    r0
        blr
+#endif
 
 _GLOBAL(call_do_irq)
        mflr    r0
Index: linux-4.18.5-rt3/arch/powerpc/kvm/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/kvm/Kconfig
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/powerpc/platforms/cell/spufs/sched.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/platforms/cell/spufs/sched.c
+++ linux-4.18.5-rt3/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, &current->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();
Index: linux-4.18.5-rt3/arch/powerpc/platforms/ps3/device-init.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/powerpc/platforms/ps3/device-init.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/s390/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/s390/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/sh/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/sh/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/sh/kernel/irq.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/sh/kernel/irq.c
+++ linux-4.18.5-rt3/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)
 {
Index: linux-4.18.5-rt3/arch/sparc/kernel/irq_64.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/sparc/kernel/irq_64.c
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/arch/x86/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/Kconfig
+++ linux-4.18.5-rt3/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_RCU_TABLE_INVALIDATE        if HAVE_RCU_TABLE_FREE
        select HAVE_REGS_AND_STACK_ACCESS_API
@@ -262,8 +263,11 @@ 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
@@ -940,7 +944,7 @@ 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.
Index: linux-4.18.5-rt3/arch/x86/crypto/aesni-intel_glue.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/crypto/aesni-intel_glue.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/arch/x86/crypto/cast5_avx_glue.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/crypto/cast5_avx_glue.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/arch/x86/crypto/chacha20_glue.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/crypto/chacha20_glue.c
+++ linux-4.18.5-rt3/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;
 }
 
Index: linux-4.18.5-rt3/arch/x86/crypto/glue_helper.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/crypto/glue_helper.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/arch/x86/entry/common.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/entry/common.c
+++ linux-4.18.5-rt3/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)
 {
@@ -148,9 +148,16 @@ 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
+               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);
 
Index: linux-4.18.5-rt3/arch/x86/entry/entry_32.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/entry/entry_32.S
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/x86/entry/entry_64.S
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/entry/entry_64.S
+++ linux-4.18.5-rt3/arch/x86/entry/entry_64.S
@@ -704,7 +704,23 @@ retint_kernel:
        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:
@@ -1038,6 +1054,7 @@ bad_gs:
        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 +1065,7 @@ 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
Index: linux-4.18.5-rt3/arch/x86/include/asm/fpu/api.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/include/asm/fpu/api.h
+++ linux-4.18.5-rt3/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);
 
 /*
Index: linux-4.18.5-rt3/arch/x86/include/asm/preempt.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/include/asm/preempt.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/x86/include/asm/signal.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/include/asm/signal.h
+++ linux-4.18.5-rt3/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)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
 #ifndef CONFIG_COMPAT
 typedef sigset_t compat_sigset_t;
 #endif
Index: linux-4.18.5-rt3/arch/x86/include/asm/stackprotector.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/include/asm/stackprotector.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/arch/x86/include/asm/thread_info.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/include/asm/thread_info.h
+++ linux-4.18.5-rt3/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 <asm/asm-offsets.h>
 
+#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)
 
 /*
Index: linux-4.18.5-rt3/arch/x86/kernel/apic/io_apic.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kernel/apic/io_apic.c
+++ linux-4.18.5-rt3/arch/x86/kernel/apic/io_apic.c
@@ -1722,19 +1722,20 @@ 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
@@ -1763,15 +1764,17 @@ 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
@@ -1780,11 +1783,11 @@ 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
@@ -1839,7 +1842,7 @@ 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)
Index: linux-4.18.5-rt3/arch/x86/kernel/asm-offsets.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kernel/asm-offsets.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/arch/x86/kernel/fpu/core.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kernel/fpu/core.c
+++ linux-4.18.5-rt3/arch/x86/kernel/fpu/core.c
@@ -138,6 +138,18 @@ 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):
  *
Index: linux-4.18.5-rt3/arch/x86/kernel/irq_32.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kernel/irq_32.c
+++ linux-4.18.5-rt3/arch/x86/kernel/irq_32.c
@@ -130,6 +130,7 @@ 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;
@@ -146,6 +147,7 @@ void do_softirq_own_stack(void)
 
        call_on_stack(__do_softirq, isp);
 }
+#endif
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
Index: linux-4.18.5-rt3/arch/x86/kernel/process_32.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kernel/process_32.c
+++ linux-4.18.5-rt3/arch/x86/kernel/process_32.c
@@ -38,6 +38,7 @@
 #include <linux/io.h>
 #include <linux/kdebug.h>
 #include <linux/syscalls.h>
+#include <linux/highmem.h>
 
 #include <asm/pgtable.h>
 #include <asm/ldt.h>
@@ -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 @@ __switch_to(struct task_struct *prev_p,
                     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
Index: linux-4.18.5-rt3/arch/x86/kvm/lapic.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kvm/lapic.c
+++ linux-4.18.5-rt3/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;
 
        /*
Index: linux-4.18.5-rt3/arch/x86/kvm/x86.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/kvm/x86.c
+++ linux-4.18.5-rt3/arch/x86/kvm/x86.c
@@ -6597,6 +6597,13 @@ 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;
Index: linux-4.18.5-rt3/arch/x86/mm/highmem_32.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/mm/highmem_32.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/arch/x86/mm/iomap_32.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/mm/iomap_32.c
+++ linux-4.18.5-rt3/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 +69,12 @@ 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));
+       WARN_ON(!pte_none(*(kmap_pte - idx)));
+
+#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 +125,9 @@ 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();
        }
Index: linux-4.18.5-rt3/arch/x86/platform/efi/efi_64.c
===================================================================
--- linux-4.18.5-rt3.orig/arch/x86/platform/efi/efi_64.c
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/arch/xtensa/include/asm/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/arch/xtensa/include/asm/spinlock_types.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/block/blk-core.c
===================================================================
--- linux-4.18.5-rt3.orig/block/blk-core.c
+++ linux-4.18.5-rt3/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;
@@ -962,12 +965,21 @@ 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)
@@ -1061,6 +1073,7 @@ 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.
@@ -3945,6 +3958,8 @@ 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);
 
Index: linux-4.18.5-rt3/block/blk-ioc.c
===================================================================
--- linux-4.18.5-rt3.orig/block/blk-ioc.c
+++ linux-4.18.5-rt3/block/blk-ioc.c
@@ -9,6 +9,7 @@
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/sched/task.h>
+#include <linux/delay.h>
 
 #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 @@ retry:
                                spin_unlock(icq->q->queue_lock);
                        } else {
                                spin_unlock_irqrestore(&ioc->lock, flags);
-                               cpu_relax();
+                               cpu_chill();
                                goto retry;
                        }
                }
Index: linux-4.18.5-rt3/block/blk-mq.c
===================================================================
--- linux-4.18.5-rt3.orig/block/blk-mq.c
+++ linux-4.18.5-rt3/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)
 {
@@ -568,19 +583,27 @@ 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);
 
        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);
        }
-       put_cpu();
+       put_cpu_light();
 }
 
 static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
@@ -1324,14 +1347,14 @@ 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,
@@ -2982,10 +3005,9 @@ 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;
Index: linux-4.18.5-rt3/block/blk-mq.h
===================================================================
--- linux-4.18.5-rt3.orig/block/blk-mq.h
+++ linux-4.18.5-rt3/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 {
Index: linux-4.18.5-rt3/block/blk-softirq.c
===================================================================
--- linux-4.18.5-rt3.orig/block/blk-softirq.c
+++ linux-4.18.5-rt3/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 @@ do_local:
                goto do_local;
 
        local_irq_restore(flags);
+       preempt_check_resched_rt();
 }
 EXPORT_SYMBOL(__blk_complete_request);
 
Index: linux-4.18.5-rt3/crypto/cryptd.c
===================================================================
--- linux-4.18.5-rt3.orig/crypto/cryptd.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/crypto/scompress.c
===================================================================
--- linux-4.18.5-rt3.orig/crypto/scompress.c
+++ linux-4.18.5-rt3/crypto/scompress.c
@@ -24,6 +24,7 @@
 #include <linux/cryptouser.h>
 #include <net/netlink.h>
 #include <linux/scatterlist.h>
+#include <linux/locallock.h>
 #include <crypto/scatterwalk.h>
 #include <crypto/internal/acompress.h>
 #include <crypto/internal/scompress.h>
@@ -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;
 }
 
Index: linux-4.18.5-rt3/drivers/ata/libata-sff.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/libata-sff.c
+++ linux-4.18.5-rt3/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
  *
Index: linux-4.18.5-rt3/drivers/ata/pata_cmd640.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_cmd640.c
+++ linux-4.18.5-rt3/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,
Index: linux-4.18.5-rt3/drivers/ata/pata_icside.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_icside.c
+++ linux-4.18.5-rt3/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,
Index: linux-4.18.5-rt3/drivers/ata/pata_imx.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_imx.c
+++ linux-4.18.5-rt3/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,
 };
Index: linux-4.18.5-rt3/drivers/ata/pata_legacy.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_legacy.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/drivers/ata/pata_palmld.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_palmld.c
+++ linux-4.18.5-rt3/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,
 };
 
Index: linux-4.18.5-rt3/drivers/ata/pata_pcmcia.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_pcmcia.c
+++ linux-4.18.5-rt3/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,
 };
Index: linux-4.18.5-rt3/drivers/ata/pata_platform.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_platform.c
+++ linux-4.18.5-rt3/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,
 };
Index: linux-4.18.5-rt3/drivers/ata/pata_via.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/ata/pata_via.c
+++ linux-4.18.5-rt3/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,
 };
 
 /**
Index: linux-4.18.5-rt3/drivers/block/zram/zcomp.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/block/zram/zcomp.c
+++ linux-4.18.5-rt3/drivers/block/zram/zcomp.c
@@ -116,12 +116,20 @@ 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 = *get_local_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);
+       put_local_ptr(zstrm);
 }
 
 int zcomp_compress(struct zcomp_strm *zstrm,
@@ -171,6 +179,7 @@ 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;
 }
Index: linux-4.18.5-rt3/drivers/block/zram/zcomp.h
===================================================================
--- linux-4.18.5-rt3.orig/drivers/block/zram/zcomp.h
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/drivers/block/zram/zram_drv.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/block/zram/zram_drv.c
+++ linux-4.18.5-rt3/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)
 {
@@ -898,6 +923,8 @@ 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;
@@ -928,6 +955,7 @@ 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;
 }
 
@@ -986,6 +1014,7 @@ 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);
@@ -1020,6 +1049,7 @@ 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);
@@ -1027,14 +1057,13 @@ 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. */
Index: linux-4.18.5-rt3/drivers/block/zram/zram_drv.h
===================================================================
--- linux-4.18.5-rt3.orig/drivers/block/zram/zram_drv.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/char/random.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/char/random.c
+++ linux-4.18.5-rt3/drivers/char/random.c
@@ -265,6 +265,7 @@
 #include <linux/syscalls.h>
 #include <linux/completion.h>
 #include <linux/uuid.h>
+#include <linux/locallock.h>
 #include <crypto/chacha20.h>
 
 #include <asm/processor.h>
@@ -1122,8 +1123,6 @@ 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 +1160,6 @@ 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,
@@ -1219,28 +1216,27 @@ 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);
@@ -2198,6 +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;
@@ -2218,7 +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) {
@@ -2228,12 +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;
@@ -2248,7 +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) {
@@ -2258,7 +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);
Index: linux-4.18.5-rt3/drivers/char/tpm/tpm_tis.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/char/tpm/tpm_tis.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/drivers/clocksource/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/drivers/clocksource/Kconfig
+++ linux-4.18.5-rt3/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
@@ -403,6 +406,14 @@ 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
Index: linux-4.18.5-rt3/drivers/clocksource/Makefile
===================================================================
--- linux-4.18.5-rt3.orig/drivers/clocksource/Makefile
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/clocksource/tcb_clksrc.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/clocksource/tcb_clksrc.c
+++ linux-4.18.5-rt3/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
@@ -126,6 +125,8 @@ static struct clocksource clksrc = {
 struct tc_clkevt_device {
        struct clock_event_device       clkevt;
        struct clk                      *clk;
+       bool                            clk_enabled;
+       u32                             freq;
        void __iomem                    *regs;
 };
 
@@ -134,15 +135,26 @@ 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)
+{
+       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 +162,14 @@ 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;
 }
@@ -164,9 +182,9 @@ 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 */
+       /* 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));
@@ -186,12 +204,12 @@ 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 */
+       /* 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));
@@ -218,9 +236,13 @@ 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,
+               .set_state_shutdown     = tc_shutdown_clk_off,
                .set_state_periodic     = tc_set_periodic,
                .set_state_oneshot      = tc_set_oneshot,
        },
@@ -240,8 +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];
@@ -262,7 +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);
 
@@ -273,7 +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;
 }
@@ -410,7 +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;
 
Index: linux-4.18.5-rt3/drivers/clocksource/timer-atmel-tcb.c
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/drivers/clocksource/timer-atmel-tcb.c
@@ -0,0 +1,608 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/clk.h>
+#include <linux/clockchips.h>
+#include <linux/clocksource.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/regmap.h>
+#include <linux/sched_clock.h>
+#include <soc/at91/atmel_tcb.h>
+
+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);
Index: linux-4.18.5-rt3/drivers/connector/cn_proc.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/connector/cn_proc.c
+++ linux-4.18.5-rt3/drivers/connector/cn_proc.c
@@ -32,6 +32,7 @@
 #include <linux/pid_namespace.h>
 
 #include <linux/cn_proc.h>
+#include <linux/locallock.h>
 
 /*
  * 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)
Index: linux-4.18.5-rt3/drivers/cpufreq/Kconfig.x86
===================================================================
--- linux-4.18.5-rt3.orig/drivers/cpufreq/Kconfig.x86
+++ linux-4.18.5-rt3/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.
Index: linux-4.18.5-rt3/drivers/firmware/efi/efi.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/firmware/efi/efi.c
+++ linux-4.18.5-rt3/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;
@@ -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);
Index: linux-4.18.5-rt3/drivers/gpu/drm/i915/i915_irq.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/gpu/drm/i915/i915_irq.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/drivers/gpu/drm/i915/intel_sprite.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/gpu/drm/i915/intel_sprite.c
+++ linux-4.18.5-rt3/drivers/gpu/drm/i915/intel_sprite.c
@@ -36,6 +36,7 @@
 #include <drm/drm_rect.h>
 #include <drm/drm_atomic.h>
 #include <drm/drm_plane_helper.h>
+#include <linux/locallock.h>
 #include "intel_drv.h"
 #include "intel_frontbuffer.h"
 #include <drm/i915_drm.h>
@@ -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;
Index: linux-4.18.5-rt3/drivers/gpu/drm/radeon/radeon_display.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/gpu/drm/radeon/radeon_display.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/drivers/hv/hv.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/hv/hv.c
+++ linux-4.18.5-rt3/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,
Index: linux-4.18.5-rt3/drivers/hv/hyperv_vmbus.h
===================================================================
--- linux-4.18.5-rt3.orig/drivers/hv/hyperv_vmbus.h
+++ linux-4.18.5-rt3/drivers/hv/hyperv_vmbus.h
@@ -31,6 +31,7 @@
 #include <linux/atomic.h>
 #include <linux/hyperv.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 
 #include "hv_trace.h"
 
Index: linux-4.18.5-rt3/drivers/hv/vmbus_drv.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/hv/vmbus_drv.c
+++ linux-4.18.5-rt3/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);
 }
 
 
Index: linux-4.18.5-rt3/drivers/infiniband/hw/hfi1/affinity.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/infiniband/hw/hfi1/affinity.c
+++ linux-4.18.5-rt3/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 = &current->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));
Index: linux-4.18.5-rt3/drivers/infiniband/hw/hfi1/sdma.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/infiniband/hw/hfi1/sdma.c
+++ linux-4.18.5-rt3/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 = &current->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();
Index: linux-4.18.5-rt3/drivers/infiniband/hw/qib/qib_file_ops.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/infiniband/hw/qib/qib_file_ops.c
+++ linux-4.18.5-rt3/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(&current->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(&current->cpus_allowed);
-               const unsigned int weight =
-                       cpumask_weight(&current->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)
Index: linux-4.18.5-rt3/drivers/iommu/amd_iommu.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/iommu/amd_iommu.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/drivers/irqchip/irq-gic-v3-its.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/irqchip/irq-gic-v3-its.c
+++ linux-4.18.5-rt3/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;
 
@@ -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)
 
@@ -1555,7 +1556,7 @@ static void its_free_prop_table(struct p
                   get_order(LPI_PROPBASE_SZ));
 }
 
-static int __init its_alloc_lpi_tables(void)
+static int __init its_alloc_lpi_prop_table(void)
 {
        phys_addr_t paddr;
 
@@ -1877,30 +1878,47 @@ static void its_free_pending_table(struc
                   get_order(max_t(u32, LPI_PENDBASE_SZ, SZ_64K)));
 }
 
-static void its_cpu_init_lpis(void)
+static int __init allocate_lpi_tables(void)
 {
-       void __iomem *rbase = gic_data_rdist_rd_base();
-       struct page *pend_page;
-       u64 val, tmp;
+       int err, cpu;
 
-       /* 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;
+       err = its_alloc_lpi_prop_table();
+       if (err)
+               return err;
+
+       /*
+        * We allocate all the pending tables anyway, as we may have a
+        * mix of RDs that have had LPIs enabled, and some that
+        * don't. We'll free the unused ones as each CPU comes online.
+        */
+       for_each_possible_cpu(cpu) {
+               struct page *pend_page;
 
                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;
+                       pr_err("Failed to allocate PENDBASE for CPU%d\n", cpu);
+                       return -ENOMEM;
                }
 
-               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;
+               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();
+       struct page *pend_page;
+       phys_addr_t paddr;
+       u64 val, tmp;
+
+       if (gic_data_rdist()->lpi_enabled)
+               return;
+
+       pend_page = gic_data_rdist()->pend_page;
+       paddr = page_to_phys(pend_page);
+
        /* set PROPBASE */
        val = (page_to_phys(gic_rdists->prop_page) |
               GICR_PROPBASER_InnerShareable |
@@ -1952,6 +1970,10 @@ static void its_cpu_init_lpis(void)
 
        /* Make sure the GIC has seen the above */
        dsb(sy);
+       gic_data_rdist()->lpi_enabled = true;
+       pr_info("GICv3: CPU%d: using LPI pending table @%pa\n",
+               smp_processor_id(),
+               &paddr);
 }
 
 static void its_cpu_init_collection(struct its_node *its)
@@ -1997,12 +2019,12 @@ 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 +3092,7 @@ 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 +3124,7 @@ err:
                        writel_relaxed(its->ctlr_save, base + GITS_CTLR);
                }
        }
-       spin_unlock(&its_lock);
+       raw_spin_unlock(&its_lock);
 
        return err;
 }
@@ -3112,7 +3134,7 @@ 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 +3186,7 @@ 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 +3420,9 @@ 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;
 
@@ -3427,16 +3449,6 @@ static int redist_disable_lpis(void)
        u64 timeout = USEC_PER_SEC;
        u64 val;
 
-       /*
-        * If coming via a CPU hotplug event, we don't need to disable
-        * LPIs before trying to re-enable them. They are already
-        * configured and all is well in the world. Detect this case
-        * by checking the allocation of the pending table for the
-        * current CPU.
-        */
-       if (gic_data_rdist()->pend_page)
-               return 0;
-
        if (!gic_rdists_supports_plpis()) {
                pr_info("CPU%d: LPIs not supported\n", smp_processor_id());
                return -ENXIO;
@@ -3446,7 +3458,18 @@ static int redist_disable_lpis(void)
        if (!(val & GICR_CTLR_ENABLE_LPIS))
                return 0;
 
-       pr_warn("CPU%d: Booted with LPIs enabled, memory probably corrupted\n",
+       /*
+        * If coming via a CPU hotplug event, we don't need to disable
+        * LPIs before trying to re-enable them. They are already
+        * configured and all is well in the world.
+        */
+       if (gic_data_rdist()->lpi_enabled)
+               return 0;
+
+       /*
+        * From that point on, we only try to do some damage control.
+        */
+       pr_warn("GICv3: CPU%d: Booted with LPIs enabled, memory probably corrupted\n",
                smp_processor_id());
        add_taint(TAINT_CRAP, LOCKDEP_STILL_OK);
 
@@ -3702,7 +3725,8 @@ int __init its_init(struct fwnode_handle
        }
 
        gic_rdists = rdists;
-       err = its_alloc_lpi_tables();
+
+       err = allocate_lpi_tables();
        if (err)
                return err;
 
Index: linux-4.18.5-rt3/drivers/leds/trigger/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/drivers/leds/trigger/Kconfig
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/md/bcache/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/drivers/md/bcache/Kconfig
+++ linux-4.18.5-rt3/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.
Index: linux-4.18.5-rt3/drivers/md/dm-rq.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/md/dm-rq.c
+++ linux-4.18.5-rt3/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());
        }
 }
 
Index: linux-4.18.5-rt3/drivers/md/raid5.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/md/raid5.c
+++ linux-4.18.5-rt3/drivers/md/raid5.c
@@ -409,16 +409,14 @@ 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);
+               spin_unlock_irqrestore(&conf->device_lock, flags);
                release_inactive_stripe_list(conf, &list, hash);
        }
-       local_irq_restore(flags);
 }
 
 static inline void remove_hash(struct stripe_head *sh)
@@ -2071,8 +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++;
@@ -2131,7 +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)
@@ -6795,6 +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;
 }
 
@@ -6805,7 +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,
Index: linux-4.18.5-rt3/drivers/md/raid5.h
===================================================================
--- linux-4.18.5-rt3.orig/drivers/md/raid5.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/misc/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/drivers/misc/Kconfig
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/drivers/of/base.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/of/base.c
+++ linux-4.18.5-rt3/drivers/of/base.c
@@ -108,43 +108,49 @@ void of_populate_phandle_cache(void)
        u32 cache_entries;
        struct device_node *np;
        u32 phandles = 0;
+       struct device_node **shadow;
 
        raw_spin_lock_irqsave(&devtree_lock, flags);
-
-       kfree(phandle_cache);
+       shadow = phandle_cache;
        phandle_cache = NULL;
 
        for_each_of_allnodes(np)
                if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL)
                        phandles++;
 
+       raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
        cache_entries = roundup_pow_of_two(phandles);
        phandle_cache_mask = cache_entries - 1;
 
-       phandle_cache = kcalloc(cache_entries, sizeof(*phandle_cache),
-                               GFP_ATOMIC);
-       if (!phandle_cache)
-               goto out;
+       kfree(shadow);
+       shadow = kcalloc(cache_entries, sizeof(*phandle_cache), GFP_KERNEL);
+
+       if (!shadow)
+               return;
+       raw_spin_lock_irqsave(&devtree_lock, flags);
+       phandle_cache = shadow;
 
        for_each_of_allnodes(np)
                if (np->phandle && np->phandle != OF_PHANDLE_ILLEGAL)
                        phandle_cache[np->phandle & phandle_cache_mask] = np;
 
-out:
        raw_spin_unlock_irqrestore(&devtree_lock, flags);
 }
 
 int of_free_phandle_cache(void)
 {
        unsigned long flags;
+       struct device_node **shadow;
 
        raw_spin_lock_irqsave(&devtree_lock, flags);
 
-       kfree(phandle_cache);
+       shadow = phandle_cache;
        phandle_cache = NULL;
 
        raw_spin_unlock_irqrestore(&devtree_lock, flags);
 
+       kfree(shadow);
        return 0;
 }
 #if !defined(CONFIG_MODULES)
Index: linux-4.18.5-rt3/drivers/pci/switch/switchtec.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/pci/switch/switchtec.c
+++ linux-4.18.5-rt3/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);
        }
Index: linux-4.18.5-rt3/drivers/scsi/fcoe/fcoe.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/scsi/fcoe/fcoe.c
+++ linux-4.18.5-rt3/drivers/scsi/fcoe/fcoe.c
@@ -1459,11 +1459,11 @@ err2:
 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);
 }
 
Index: linux-4.18.5-rt3/drivers/scsi/fcoe/fcoe_ctlr.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/scsi/fcoe/fcoe_ctlr.c
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/drivers/scsi/libfc/fc_exch.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/scsi/libfc/fc_exch.c
+++ linux-4.18.5-rt3/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) {
Index: linux-4.18.5-rt3/drivers/scsi/libsas/sas_ata.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/scsi/libsas/sas_ata.c
+++ linux-4.18.5-rt3/drivers/scsi/libsas/sas_ata.c
@@ -176,7 +176,6 @@ qc_already_gone:
 
 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;
 }
 
Index: linux-4.18.5-rt3/drivers/scsi/qla2xxx/qla_inline.h
===================================================================
--- linux-4.18.5-rt3.orig/drivers/scsi/qla2xxx/qla_inline.h
+++ linux-4.18.5-rt3/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 *
Index: linux-4.18.5-rt3/drivers/staging/android/vsoc.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/staging/android/vsoc.c
+++ linux-4.18.5-rt3/drivers/staging/android/vsoc.c
@@ -438,12 +438,10 @@ static int handle_vsoc_cond_wait(struct
 
                if (!timespec_valid(&ts))
                        return -EINVAL;
-               hrtimer_init_on_stack(&to->timer, CLOCK_MONOTONIC,
-                                     HRTIMER_MODE_ABS);
+               hrtimer_init_sleeper_on_stack(to, CLOCK_MONOTONIC,
+                                             HRTIMER_MODE_ABS, current);
                hrtimer_set_expires_range_ns(&to->timer, timespec_to_ktime(ts),
                                             current->timer_slack_ns);
-
-               hrtimer_init_sleeper(to, current);
        }
 
        while (1) {
Index: linux-4.18.5-rt3/drivers/thermal/x86_pkg_temp_thermal.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/thermal/x86_pkg_temp_thermal.c
+++ linux-4.18.5-rt3/drivers/thermal/x86_pkg_temp_thermal.c
@@ -29,6 +29,7 @@
 #include <linux/pm.h>
 #include <linux/thermal.h>
 #include <linux/debugfs.h>
+#include <linux/swork.h>
 #include <asm/cpu_device_id.h>
 #include <asm/mce.h>
 
@@ -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(&notify_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(&notify_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)
 
Index: linux-4.18.5-rt3/drivers/tty/serial/8250/8250_core.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/tty/serial/8250/8250_core.c
+++ linux-4.18.5-rt3/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 <asm/serial.h>
 /*
Index: linux-4.18.5-rt3/drivers/tty/serial/8250/8250_port.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/tty/serial/8250/8250_port.c
+++ linux-4.18.5-rt3/drivers/tty/serial/8250/8250_port.c
@@ -31,6 +31,7 @@
 #include <linux/nmi.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/kdb.h>
 #include <linux/uaccess.h>
 #include <linux/pm_runtime.h>
 #include <linux/ktime.h>
@@ -3221,9 +3222,9 @@ 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)
+       else if (in_kdb_printk())
                locked = spin_trylock_irqsave(&port->lock, flags);
        else
                spin_lock_irqsave(&port->lock, flags);
Index: linux-4.18.5-rt3/drivers/tty/serial/amba-pl011.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/tty/serial/amba-pl011.c
+++ linux-4.18.5-rt3/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);
 }
Index: linux-4.18.5-rt3/drivers/tty/serial/omap-serial.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/tty/serial/omap-serial.c
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/drivers/usb/core/hcd.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/usb/core/hcd.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/drivers/usb/gadget/function/f_fs.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/usb/gadget/function/f_fs.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/drivers/usb/gadget/legacy/inode.c
===================================================================
--- linux-4.18.5-rt3.orig/drivers/usb/gadget/legacy/inode.c
+++ linux-4.18.5-rt3/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 {
Index: linux-4.18.5-rt3/fs/aio.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/aio.c
+++ linux-4.18.5-rt3/fs/aio.c
@@ -40,6 +40,7 @@
 #include <linux/ramfs.h>
 #include <linux/percpu-refcount.h>
 #include <linux/mount.h>
+#include <linux/swork.h>
 
 #include <asm/kmap_types.h>
 #include <linux/uaccess.h>
@@ -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;
Index: linux-4.18.5-rt3/fs/autofs/expire.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/autofs/expire.c
+++ linux-4.18.5-rt3/fs/autofs/expire.c
@@ -8,6 +8,7 @@
  * option, any later version, incorporated herein by reference.
  */
 
+#include <linux/delay.h>
 #include "autofs_i.h"
 
 static unsigned long now;
@@ -148,7 +149,7 @@ again:
                        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);
Index: linux-4.18.5-rt3/fs/buffer.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/buffer.c
+++ linux-4.18.5-rt3/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();
Index: linux-4.18.5-rt3/fs/cifs/readdir.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/cifs/readdir.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/fs/dcache.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/dcache.c
+++ linux-4.18.5-rt3/fs/dcache.c
@@ -2430,9 +2430,10 @@ 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();
        }
@@ -2440,26 +2441,30 @@ 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)
 {
-       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);
@@ -2473,7 +2478,7 @@ 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)) {
@@ -2501,7 +2506,7 @@ retry:
        }
 
        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;
@@ -2574,7 +2579,7 @@ 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);
@@ -3115,6 +3120,8 @@ __setup("dhash_entries=", set_dhash_entr
 
 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.
         */
@@ -3131,11 +3138,16 @@ 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
@@ -3159,6 +3171,10 @@ 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;
 }
 
Index: linux-4.18.5-rt3/fs/eventpoll.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/eventpoll.c
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/fs/exec.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/exec.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/fs/ext4/page-io.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/ext4/page-io.c
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/fs/fscache/cookie.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/fscache/cookie.c
+++ linux-4.18.5-rt3/fs/fscache/cookie.c
@@ -973,3 +973,11 @@ inconsistent:
        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]);
+}
Index: linux-4.18.5-rt3/fs/fscache/main.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/fscache/main.c
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/fs/fuse/dir.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/fuse/dir.c
+++ linux-4.18.5-rt3/fs/fuse/dir.c
@@ -1196,7 +1196,7 @@ 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) {
                /*
Index: linux-4.18.5-rt3/fs/inode.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/inode.c
+++ linux-4.18.5-rt3/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;
 
Index: linux-4.18.5-rt3/fs/libfs.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/libfs.c
+++ linux-4.18.5-rt3/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 @@ retry:
 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);
 }
 
Index: linux-4.18.5-rt3/fs/locks.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/locks.c
+++ linux-4.18.5-rt3/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 @@ find_conflict:
 
 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 @@ restart:
        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 @@ restart:
        }
 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 @@ out_setup:
                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);
 }
Index: linux-4.18.5-rt3/fs/namei.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/namei.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/fs/namespace.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/namespace.c
+++ linux-4.18.5-rt3/fs/namespace.c
@@ -14,6 +14,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
+#include <linux/delay.h>
 #include <linux/security.h>
 #include <linux/cred.h>
 #include <linux/idr.h>
@@ -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
Index: linux-4.18.5-rt3/fs/nfs/delegation.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/delegation.c
+++ linux-4.18.5-rt3/fs/nfs/delegation.c
@@ -152,11 +152,11 @@ again:
                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);
Index: linux-4.18.5-rt3/fs/nfs/dir.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/dir.c
+++ linux-4.18.5-rt3/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 };
@@ -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);
Index: linux-4.18.5-rt3/fs/nfs/inode.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/inode.c
+++ linux-4.18.5-rt3/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);
 }
Index: linux-4.18.5-rt3/fs/nfs/nfs4_fs.h
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/nfs4_fs.h
+++ linux-4.18.5-rt3/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;
 };
 
Index: linux-4.18.5-rt3/fs/nfs/nfs4proc.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/nfs4proc.c
+++ linux-4.18.5-rt3/fs/nfs/nfs4proc.c
@@ -2818,7 +2818,7 @@ 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)
@@ -2856,7 +2856,7 @@ 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);
Index: linux-4.18.5-rt3/fs/nfs/nfs4state.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/nfs4state.c
+++ linux-4.18.5-rt3/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 @@ restart:
                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;
 }
 
Index: linux-4.18.5-rt3/fs/nfs/unlink.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/nfs/unlink.c
+++ linux-4.18.5-rt3/fs/nfs/unlink.c
@@ -13,7 +13,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
 #include <linux/sched.h>
-#include <linux/wait.h>
+#include <linux/swait.h>
 #include <linux/namei.h>
 #include <linux/fsnotify.h>
 
@@ -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
@@ -183,7 +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);
Index: linux-4.18.5-rt3/fs/ntfs/aops.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/ntfs/aops.c
+++ linux-4.18.5-rt3/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);
@@ -108,8 +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;
@@ -124,8 +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
@@ -146,13 +142,11 @@ 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);
@@ -160,9 +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);
 }
 
 /**
Index: linux-4.18.5-rt3/fs/proc/array.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/proc/array.c
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/fs/proc/base.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/proc/base.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/fs/proc/proc_sysctl.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/proc/proc_sysctl.c
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/fs/squashfs/decompressor_multi_percpu.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/squashfs/decompressor_multi_percpu.c
+++ linux-4.18.5-rt3/fs/squashfs/decompressor_multi_percpu.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/percpu.h>
 #include <linux/buffer_head.h>
+#include <linux/locallock.h>
 
 #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",
Index: linux-4.18.5-rt3/fs/timerfd.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/timerfd.c
+++ linux-4.18.5-rt3/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);
        }
 
        /*
Index: linux-4.18.5-rt3/fs/xfs/xfs_aops.c
===================================================================
--- linux-4.18.5-rt3.orig/fs/xfs/xfs_aops.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/backing-dev-defs.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/backing-dev-defs.h
+++ linux-4.18.5-rt3/include/linux/backing-dev-defs.h
@@ -12,6 +12,7 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 #include <linux/kref.h>
+#include <linux/refcount.h>
 
 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
Index: linux-4.18.5-rt3/include/linux/backing-dev.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/backing-dev.h
+++ linux-4.18.5-rt3/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);
 }
 
Index: linux-4.18.5-rt3/include/linux/blk-mq.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/blk-mq.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/blkdev.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/blkdev.h
+++ linux-4.18.5-rt3/include/linux/blkdev.h
@@ -27,6 +27,7 @@
 #include <linux/percpu-refcount.h>
 #include <linux/scatterlist.h>
 #include <linux/blkzoned.h>
+#include <linux/swork.h>
 #include <linux/seqlock.h>
 #include <linux/u64_stats_sync.h>
 
@@ -151,6 +152,9 @@ 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;
@@ -648,6 +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;
 
Index: linux-4.18.5-rt3/include/linux/bottom_half.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/bottom_half.h
+++ linux-4.18.5-rt3/include/linux/bottom_half.h
@@ -4,6 +4,39 @@
 
 #include <linux/preempt.h>
 
+#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 */
Index: linux-4.18.5-rt3/include/linux/buffer_head.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/buffer_head.h
+++ linux-4.18.5-rt3/include/linux/buffer_head.h
@@ -76,8 +76,50 @@ 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;
+#if IS_ENABLED(CONFIG_JBD2)
+       spinlock_t b_state_lock;
+       spinlock_t b_journal_head_lock;
+#endif
+#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);
+#if IS_ENABLED(CONFIG_JBD2)
+       spin_lock_init(&bh->b_state_lock);
+       spin_lock_init(&bh->b_journal_head_lock);
+#endif
+#endif
+}
+
 /*
  * macro tricks to expand the set_buffer_foo(), clear_buffer_foo()
  * and buffer_foo() functions.
Index: linux-4.18.5-rt3/include/linux/cgroup-defs.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/cgroup-defs.h
+++ linux-4.18.5-rt3/include/linux/cgroup-defs.h
@@ -20,6 +20,7 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/workqueue.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/swork.h>
 
 #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;
 
        /*
Index: linux-4.18.5-rt3/include/linux/completion.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/completion.h
+++ linux-4.18.5-rt3/include/linux/completion.h
@@ -9,7 +9,7 @@
  * See kernel/sched/completion.c for details.
  */
 
-#include <linux/wait.h>
+#include <linux/swait.h>
 
 /*
  * 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);
 }
 
 /**
Index: linux-4.18.5-rt3/include/linux/cpu.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/cpu.h
+++ linux-4.18.5-rt3/include/linux/cpu.h
@@ -110,6 +110,8 @@ 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 */
 
@@ -120,6 +122,9 @@ 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 */
Index: linux-4.18.5-rt3/include/linux/dcache.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/dcache.h
+++ linux-4.18.5-rt3/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 *);
Index: linux-4.18.5-rt3/include/linux/delay.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/delay.h
+++ linux-4.18.5-rt3/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) */
Index: linux-4.18.5-rt3/include/linux/fs.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/fs.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/include/linux/fscache.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/fscache.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/highmem.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/highmem.h
+++ linux-4.18.5-rt3/include/linux/highmem.h
@@ -8,6 +8,7 @@
 #include <linux/mm.h>
 #include <linux/uaccess.h>
 #include <linux/hardirq.h>
+#include <linux/sched.h>
 
 #include <asm/cacheflush.h>
 
@@ -66,7 +67,7 @@ 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 +76,7 @@ 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 +88,51 @@ 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
 }
 
Index: linux-4.18.5-rt3/include/linux/hrtimer.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/hrtimer.h
+++ linux-4.18.5-rt3/include/linux/hrtimer.h
@@ -22,6 +22,7 @@
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <linux/timerqueue.h>
+#include <linux/wait.h>
 
 struct hrtimer_clock_base;
 struct hrtimer_cpu_base;
@@ -41,6 +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,
@@ -51,6 +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,
 };
 
 /*
@@ -216,6 +223,9 @@ 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;
@@ -364,10 +374,17 @@ 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 +394,15 @@ 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
 
@@ -417,6 +443,13 @@ 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);
 
@@ -442,7 +475,7 @@ 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;
 }
@@ -480,9 +513,6 @@ 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,
Index: linux-4.18.5-rt3/include/linux/idr.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/idr.h
+++ linux-4.18.5-rt3/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.
Index: linux-4.18.5-rt3/include/linux/interrupt.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/interrupt.h
+++ linux-4.18.5-rt3/include/linux/interrupt.h
@@ -13,6 +13,7 @@
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
 #include <linux/workqueue.h>
+#include <linux/swork.h>
 
 #include <linux/atomic.h>
 #include <asm/ptrace.h>
@@ -61,6 +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
@@ -74,6 +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)
 
@@ -225,6 +228,7 @@ 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 +240,11 @@ 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);
 };
@@ -427,7 +435,11 @@ 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
@@ -493,9 +505,10 @@ struct softirq_action
        void    (*action)(struct softirq_action *);
 };
 
+#ifndef CONFIG_PREEMPT_RT_FULL
 asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
-
+static inline void thread_do_softirq(void) { do_softirq(); }
 #ifdef __ARCH_HAS_DO_SOFTIRQ
 void do_softirq_own_stack(void);
 #else
@@ -504,13 +517,25 @@ 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);
 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);
+extern void softirq_check_pending_idle(void);
 
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
@@ -532,8 +557,9 @@ 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.
@@ -558,27 +584,36 @@ 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
@@ -612,17 +647,18 @@ 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,
                         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;
Index: linux-4.18.5-rt3/include/linux/irq.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/irq.h
+++ linux-4.18.5-rt3/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)
 
Index: linux-4.18.5-rt3/include/linux/irq_work.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/irq_work.h
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/include/linux/irqchip/arm-gic-v3.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/irqchip/arm-gic-v3.h
+++ linux-4.18.5-rt3/include/linux/irqchip/arm-gic-v3.h
@@ -574,6 +574,7 @@ struct rdists {
                void __iomem    *rd_base;
                struct page     *pend_page;
                phys_addr_t     phys_base;
+               bool            lpi_enabled;
        } __percpu              *rdist;
        struct page             *prop_page;
        int                     id_bits;
Index: linux-4.18.5-rt3/include/linux/irqdesc.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/irqdesc.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/include/linux/irqflags.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/irqflags.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/include/linux/jbd2.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/jbd2.h
+++ linux-4.18.5-rt3/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))
Index: linux-4.18.5-rt3/include/linux/kdb.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/kdb.h
+++ linux-4.18.5-rt3/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; }
Index: linux-4.18.5-rt3/include/linux/kernel.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/kernel.h
+++ linux-4.18.5-rt3/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
 
Index: linux-4.18.5-rt3/include/linux/libata.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/libata.h
+++ linux-4.18.5-rt3/include/linux/libata.h
@@ -1858,8 +1858,6 @@ 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,
Index: linux-4.18.5-rt3/include/linux/list_bl.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/list_bl.h
+++ linux-4.18.5-rt3/include/linux/list_bl.h
@@ -3,6 +3,7 @@
 #define _LINUX_LIST_BL_H
 
 #include <linux/list.h>
+#include <linux/spinlock.h>
 #include <linux/bit_spinlock.h>
 
 /*
@@ -33,13 +34,24 @@
 
 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)
+
+#ifdef CONFIG_PREEMPT_RT_BASE
+#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)
 {
@@ -119,12 +131,26 @@ 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)
Index: linux-4.18.5-rt3/include/linux/list_lru.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/list_lru.h
+++ linux-4.18.5-rt3/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)
 {
Index: linux-4.18.5-rt3/include/linux/locallock.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/include/linux/locallock.h
@@ -0,0 +1,281 @@
+#ifndef _LINUX_LOCALLOCK_H
+#define _LINUX_LOCALLOCK_H
+
+#include <linux/percpu.h>
+#include <linux/spinlock.h>
+
+#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 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);                                       \
+               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 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()
+
+#endif
+
+#endif
Index: linux-4.18.5-rt3/include/linux/mm_types.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/mm_types.h
+++ linux-4.18.5-rt3/include/linux/mm_types.h
@@ -12,6 +12,7 @@
 #include <linux/completion.h>
 #include <linux/cpumask.h>
 #include <linux/uprobes.h>
+#include <linux/rcupdate.h>
 #include <linux/page-flags-layout.h>
 #include <linux/workqueue.h>
 
@@ -483,6 +484,9 @@ 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
Index: linux-4.18.5-rt3/include/linux/mutex.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/mutex.h
+++ linux-4.18.5-rt3/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 <linux/mutex_rt.h>
+#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 */
Index: linux-4.18.5-rt3/include/linux/mutex_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 <linux/rtmutex.h>
+
+/* FIXME: Just for __lockfunc */
+#include <linux/spinlock.h>
+
+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
Index: linux-4.18.5-rt3/include/linux/netdevice.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/netdevice.h
+++ linux-4.18.5-rt3/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)
 {
@@ -573,7 +585,11 @@ 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
         */
@@ -2555,14 +2571,53 @@ 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);
@@ -2917,6 +2972,7 @@ struct softnet_data {
        unsigned int            dropped;
        struct sk_buff_head     input_pkt_queue;
        struct napi_struct      backlog;
+       struct sk_buff_head     tofree_queue;
 
 };
 
@@ -3639,10 +3695,48 @@ 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 +3753,32 @@ 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;
 }
 
Index: linux-4.18.5-rt3/include/linux/netfilter/x_tables.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/netfilter/x_tables.h
+++ linux-4.18.5-rt3/include/linux/netfilter/x_tables.h
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/static_key.h>
 #include <linux/netfilter.h>
+#include <linux/locallock.h>
 #include <uapi/linux/netfilter/x_tables.h>
 
 /* 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);
 }
 
 /*
Index: linux-4.18.5-rt3/include/linux/nfs_fs.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/nfs_fs.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/include/linux/nfs_xdr.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/nfs_xdr.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/include/linux/percpu-rwsem.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/percpu-rwsem.h
+++ linux-4.18.5-rt3/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 *);
 
Index: linux-4.18.5-rt3/include/linux/percpu.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/percpu.h
+++ linux-4.18.5-rt3/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)
 
Index: linux-4.18.5-rt3/include/linux/pid.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/pid.h
+++ linux-4.18.5-rt3/include/linux/pid.h
@@ -3,6 +3,7 @@
 #define _LINUX_PID_H
 
 #include <linux/rculist.h>
+#include <linux/atomic.h>
 
 enum pid_type
 {
Index: linux-4.18.5-rt3/include/linux/posix-timers.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/posix-timers.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/preempt.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/preempt.h
+++ linux-4.18.5-rt3/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 <asm/preempt.h>
 
 #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)))
@@ -118,7 +127,11 @@
 /*
  * 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:
@@ -167,6 +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() \
@@ -175,16 +202,53 @@ do { \
        barrier(); \
 } while (0)
 
+#define preempt_lazy_disable() \
+do { \
+       inc_preempt_lazy_count(); \
+       barrier(); \
+} while (0)
+
 #define sched_preempt_enable_no_resched() \
 do { \
        barrier(); \
        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()
+# 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())
 
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+
+extern void migrate_disable(void);
+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()              preempt_disable()
+#define migrate_enable()               preempt_enable()
+static inline int __migrate_disabled(struct task_struct *p)
+{
+       return 0;
+}
+#endif
+
 #ifdef CONFIG_PREEMPT
 #define preempt_enable() \
 do { \
@@ -206,6 +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 { \
@@ -213,6 +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(); \
@@ -251,8 +328,16 @@ 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()
+#define migrate_enable()                       barrier()
+
+static inline int __migrate_disabled(struct task_struct *p)
+{
+       return 0;
+}
 #endif /* CONFIG_PREEMPT_COUNT */
 
 #ifdef MODULE
@@ -271,10 +356,22 @@ do { \
 } while (0)
 #define preempt_fold_need_resched() \
 do { \
-       if (tif_need_resched()) \
+       if (tif_need_resched_now()) \
                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;
Index: linux-4.18.5-rt3/include/linux/printk.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/printk.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/radix-tree.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/radix-tree.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/random.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/random.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/rbtree.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rbtree.h
+++ linux-4.18.5-rt3/include/linux/rbtree.h
@@ -31,7 +31,7 @@
 
 #include <linux/kernel.h>
 #include <linux/stddef.h>
-#include <linux/rcupdate.h>
+#include <linux/rcu_assign_pointer.h>
 
 struct rb_node {
        unsigned long  __rb_parent_color;
Index: linux-4.18.5-rt3/include/linux/rcu_assign_pointer.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/include/linux/rcu_assign_pointer.h
@@ -0,0 +1,54 @@
+#ifndef __LINUX_RCU_ASSIGN_POINTER_H__
+#define __LINUX_RCU_ASSIGN_POINTER_H__
+#include <linux/compiler.h>
+#include <asm/barrier.h>
+
+/**
+ * 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
Index: linux-4.18.5-rt3/include/linux/rcupdate.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rcupdate.h
+++ linux-4.18.5-rt3/include/linux/rcupdate.h
@@ -42,6 +42,7 @@
 #include <linux/lockdep.h>
 #include <asm/processor.h>
 #include <linux/cpumask.h>
+#include <linux/rcu_assign_pointer.h>
 
 #define ULONG_CMP_GE(a, b)     (ULONG_MAX / 2 >= (a) - (b))
 #define ULONG_CMP_LT(a, b)     (ULONG_MAX / 2 < (a) - (b))
@@ -55,7 +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);
@@ -74,6 +79,11 @@ 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 +109,8 @@ 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 */
@@ -256,7 +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 */
@@ -366,54 +385,6 @@ 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
@@ -705,10 +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
 }
 
 /*
@@ -718,10 +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();
 }
 
Index: linux-4.18.5-rt3/include/linux/rcutree.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rcutree.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/rtmutex.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rtmutex.h
+++ linux-4.18.5-rt3/include/linux/rtmutex.h
@@ -14,11 +14,15 @@
 #define __LINUX_RT_MUTEX_H
 
 #include <linux/linkage.h>
+#include <linux/spinlock_types_raw.h>
 #include <linux/rbtree.h>
-#include <linux/spinlock_types.h>
 
 extern int max_lock_depth; /* for sysctl */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+#include <linux/debug_locks.h>
+#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
@@ -115,6 +126,7 @@ 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);
 
Index: linux-4.18.5-rt3/include/linux/rwlock_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/rwlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rwlock_types.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/rwlock_types_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/rwsem.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/rwsem.h
+++ linux-4.18.5-rt3/include/linux/rwsem.h
@@ -20,6 +20,10 @@
 #include <linux/osq_lock.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+#include <linux/rwsem_rt.h>
+#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
  */
Index: linux-4.18.5-rt3/include/linux/rwsem_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 <linux/rtmutex.h>
+#include <linux/swait.h>
+
+#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
Index: linux-4.18.5-rt3/include/linux/sched.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/sched.h
+++ linux-4.18.5-rt3/include/linux/sched.h
@@ -28,6 +28,7 @@
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/rseq.h>
+#include <asm/kmap_types.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
 struct audit_context;
@@ -101,12 +102,8 @@ 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)
@@ -134,6 +131,9 @@ 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 +143,7 @@ struct task_group;
                current->state = (state_value);                         \
                raw_spin_unlock_irqrestore(&current->pi_lock, flags);   \
        } while (0)
+
 #else
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -187,6 +188,9 @@ 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
@@ -600,6 +604,8 @@ 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
@@ -660,7 +666,25 @@ struct task_struct {
 
        unsigned int                    policy;
        int                             nr_cpus_allowed;
-       cpumask_t                       cpus_allowed;
+       const cpumask_t                 *cpus_ptr;
+       cpumask_t                       cpus_mask;
+#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
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+# ifdef CONFIG_SCHED_DEBUG
+       int                             migrate_disable;
+       int                             migrate_disable_atomic;
+# endif
+#endif
+#ifdef CONFIG_PREEMPT_RT_FULL
+       int                             sleeping_lock;
+#endif
 
 #ifdef CONFIG_PREEMPT_RCU
        int                             rcu_read_lock_nesting;
@@ -819,6 +843,9 @@ 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: */
@@ -862,11 +889,17 @@ 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: */
        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;
@@ -891,6 +924,7 @@ 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: */
@@ -1158,9 +1192,23 @@ struct task_struct {
        unsigned int                    sequential_io;
        unsigned int                    sequential_io_avg;
 #endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+       struct rcu_head                 put_rcu;
+       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
+#ifdef CONFIG_PREEMPT_RT_FULL
+       int                             xmit_recursion;
+#endif
        int                             pagefault_disabled;
 #ifdef CONFIG_MMU
        struct task_struct              *oom_reaper_list;
@@ -1374,6 +1422,7 @@ 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 */
@@ -1397,7 +1446,7 @@ 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 */
@@ -1593,6 +1642,7 @@ 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
@@ -1675,6 +1725,89 @@ 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))
+               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
@@ -1727,6 +1860,23 @@ 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.
  */
Index: linux-4.18.5-rt3/include/linux/sched/mm.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/sched/mm.h
+++ linux-4.18.5-rt3/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.
Index: linux-4.18.5-rt3/include/linux/sched/task.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/sched/task.h
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/sched/user.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/sched/user.h
+++ linux-4.18.5-rt3/include/linux/sched/user.h
@@ -4,6 +4,7 @@
 
 #include <linux/uidgid.h>
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/ratelimit.h>
 
 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 *);
Index: linux-4.18.5-rt3/include/linux/sched/wake_q.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/sched/wake_q.h
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/include/linux/seqlock.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/seqlock.h
+++ linux-4.18.5-rt3/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 +479,45 @@ 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 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)
 {
-       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 +526,7 @@ 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 +536,7 @@ 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);
 }
 
Index: linux-4.18.5-rt3/include/linux/signal.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/signal.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/include/linux/skbuff.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/skbuff.h
+++ linux-4.18.5-rt3/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)
 {
Index: linux-4.18.5-rt3/include/linux/smp.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/smp.h
+++ linux-4.18.5-rt3/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:
Index: linux-4.18.5-rt3/include/linux/spinlock.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/spinlock.h
+++ linux-4.18.5-rt3/include/linux/spinlock.h
@@ -279,7 +279,11 @@ static inline void do_raw_spin_unlock(ra
 })
 
 /* Include rwlock functions */
-#include <linux/rwlock.h>
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_rt.h>
+#else
+# include <linux/rwlock.h>
+#endif
 
 /*
  * Pull the _spin_*()/_read_*()/_write_*() functions/declarations:
@@ -290,6 +294,10 @@ static inline void do_raw_spin_unlock(ra
 # include <linux/spinlock_api_up.h>
 #endif
 
+#ifdef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_rt.h>
+#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)
Index: linux-4.18.5-rt3/include/linux/spinlock_api_smp.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/spinlock_api_smp.h
+++ linux-4.18.5-rt3/include/linux/spinlock_api_smp.h
@@ -187,6 +187,8 @@ static inline int __raw_spin_trylock_bh(
        return 0;
 }
 
-#include <linux/rwlock_api_smp.h>
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/rwlock_api_smp.h>
+#endif
 
 #endif /* __LINUX_SPINLOCK_API_SMP_H */
Index: linux-4.18.5-rt3/include/linux/spinlock_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 <linux/bug.h>
+
+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
Index: linux-4.18.5-rt3/include/linux/spinlock_types.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/spinlock_types.h
+++ linux-4.18.5-rt3/include/linux/spinlock_types.h
@@ -9,77 +9,15 @@
  * Released under the General Public License (GPL).
  */
 
-#if defined(CONFIG_SMP)
-# include <asm/spinlock_types.h>
-#else
-# include <linux/spinlock_types_up.h>
-#endif
-
-#include <linux/lockdep.h>
-
-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
+#include <linux/spinlock_types_raw.h>
 
-#ifdef CONFIG_DEBUG_SPINLOCK
-# define SPIN_DEBUG_INIT(lockname)             \
-       .magic = SPINLOCK_MAGIC,                \
-       .owner_cpu = -1,                        \
-       .owner = SPINLOCK_OWNER_INIT,
+#ifndef CONFIG_PREEMPT_RT_FULL
+# include <linux/spinlock_types_nort.h>
+# include <linux/rwlock_types.h>
 #else
-# define SPIN_DEBUG_INIT(lockname)
+# include <linux/rtmutex.h>
+# include <linux/spinlock_types_rt.h>
+# include <linux/rwlock_types_rt.h>
 #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 <linux/rwlock_types.h>
-
 #endif /* __LINUX_SPINLOCK_TYPES_H */
Index: linux-4.18.5-rt3/include/linux/spinlock_types_nort.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/linux/spinlock_types_raw.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/include/linux/spinlock_types_raw.h
@@ -0,0 +1,55 @@
+#ifndef __LINUX_SPINLOCK_TYPES_RAW_H
+#define __LINUX_SPINLOCK_TYPES_RAW_H
+
+#include <linux/types.h>
+
+#if defined(CONFIG_SMP)
+# include <asm/spinlock_types.h>
+#else
+# include <linux/spinlock_types_up.h>
+#endif
+
+#include <linux/lockdep.h>
+
+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
Index: linux-4.18.5-rt3/include/linux/spinlock_types_rt.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 <linux/cache.h>
+
+/*
+ * 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
Index: linux-4.18.5-rt3/include/linux/spinlock_types_up.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/spinlock_types_up.h
+++ linux-4.18.5-rt3/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
  *
Index: linux-4.18.5-rt3/include/linux/suspend.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/suspend.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/include/linux/swait.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/swait.h
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/include/linux/swap.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/swap.h
+++ linux-4.18.5-rt3/include/linux/swap.h
@@ -12,6 +12,7 @@
 #include <linux/fs.h>
 #include <linux/atomic.h>
 #include <linux/page-flags.h>
+#include <linux/locallock.h>
 #include <asm/page.h>
 
 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);
Index: linux-4.18.5-rt3/include/linux/swork.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/include/linux/swork.h
@@ -0,0 +1,24 @@
+#ifndef _LINUX_SWORK_H
+#define _LINUX_SWORK_H
+
+#include <linux/list.h>
+
+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 */
Index: linux-4.18.5-rt3/include/linux/thread_info.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/thread_info.h
+++ linux-4.18.5-rt3/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,
Index: linux-4.18.5-rt3/include/linux/timer.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/timer.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/include/linux/trace_events.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/trace_events.h
+++ linux-4.18.5-rt3/include/linux/trace_events.h
@@ -62,6 +62,9 @@ struct trace_entry {
        unsigned char           flags;
        unsigned char           preempt_count;
        int                     pid;
+       unsigned short          migrate_disable;
+       unsigned short          padding;
+       unsigned char           preempt_lazy_count;
 };
 
 #define TRACE_EVENT_TYPE_MAX                                           \
Index: linux-4.18.5-rt3/include/linux/uaccess.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/uaccess.h
+++ linux-4.18.5-rt3/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();
 }
 
 /*
Index: linux-4.18.5-rt3/include/linux/vmstat.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/vmstat.h
+++ linux-4.18.5-rt3/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)
Index: linux-4.18.5-rt3/include/linux/wait.h
===================================================================
--- linux-4.18.5-rt3.orig/include/linux/wait.h
+++ linux-4.18.5-rt3/include/linux/wait.h
@@ -10,6 +10,7 @@
 
 #include <asm/current.h>
 #include <uapi/linux/wait.h>
+#include <linux/atomic.h>
 
 typedef struct wait_queue_entry wait_queue_entry_t;
 
@@ -488,8 +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,                 \
Index: linux-4.18.5-rt3/include/net/gen_stats.h
===================================================================
--- linux-4.18.5-rt3.orig/include/net/gen_stats.h
+++ linux-4.18.5-rt3/include/net/gen_stats.h
@@ -6,6 +6,7 @@
 #include <linux/socket.h>
 #include <linux/rtnetlink.h>
 #include <linux/pkt_sched.h>
+#include <net/net_seq_lock.h>
 
 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);
Index: linux-4.18.5-rt3/include/net/neighbour.h
===================================================================
--- linux-4.18.5-rt3.orig/include/net/neighbour.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/include/net/net_seq_lock.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/include/net/sch_generic.h
===================================================================
--- linux-4.18.5-rt3.orig/include/net/sch_generic.h
+++ linux-4.18.5-rt3/include/net/sch_generic.h
@@ -10,6 +10,7 @@
 #include <linux/percpu.h>
 #include <linux/dynamic_queue_limits.h>
 #include <linux/list.h>
+#include <net/net_seq_lock.h>
 #include <linux/refcount.h>
 #include <linux/workqueue.h>
 #include <net/gen_stats.h>
@@ -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);
 
Index: linux-4.18.5-rt3/include/soc/at91/atmel_tcb.h
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/include/trace/events/cgroup.h
===================================================================
--- linux-4.18.5-rt3.orig/include/trace/events/cgroup.h
+++ linux-4.18.5-rt3/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 */
Index: linux-4.18.5-rt3/init/Kconfig
===================================================================
--- linux-4.18.5-rt3.orig/init/Kconfig
+++ linux-4.18.5-rt3/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
@@ -1591,6 +1592,7 @@ 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 +1613,7 @@ 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
@@ -1652,7 +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
Index: linux-4.18.5-rt3/init/Makefile
===================================================================
--- linux-4.18.5-rt3.orig/init/Makefile
+++ linux-4.18.5-rt3/init/Makefile
@@ -34,4 +34,4 @@ silent_chk_compile.h = :
 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)"
Index: linux-4.18.5-rt3/init/init_task.c
===================================================================
--- linux-4.18.5-rt3.orig/init/init_task.c
+++ linux-4.18.5-rt3/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)
@@ -64,7 +70,8 @@ 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,
@@ -111,6 +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),
Index: linux-4.18.5-rt3/init/main.c
===================================================================
--- linux-4.18.5-rt3.orig/init/main.c
+++ linux-4.18.5-rt3/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();
 
Index: linux-4.18.5-rt3/kernel/Kconfig.locks
===================================================================
--- linux-4.18.5-rt3.orig/kernel/Kconfig.locks
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/kernel/Kconfig.preempt
===================================================================
--- linux-4.18.5-rt3.orig/kernel/Kconfig.preempt
+++ linux-4.18.5-rt3/kernel/Kconfig.preempt
@@ -1,3 +1,16 @@
+config PREEMPT
+       bool
+       select PREEMPT_COUNT
+
+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"
@@ -33,9 +46,9 @@ 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 +65,22 @@ 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.
+
+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
Index: linux-4.18.5-rt3/kernel/cgroup/cgroup-internal.h
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cgroup/cgroup-internal.h
+++ linux-4.18.5-rt3/kernel/cgroup/cgroup-internal.h
@@ -8,6 +8,32 @@
 #include <linux/list.h>
 #include <linux/refcount.h>
 
+#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
Index: linux-4.18.5-rt3/kernel/cgroup/cgroup-v1.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cgroup/cgroup-v1.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/kernel/cgroup/cgroup.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cgroup/cgroup.c
+++ linux-4.18.5-rt3/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;
 }
@@ -4608,10 +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;
 
@@ -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);
@@ -4671,8 +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,
@@ -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;
@@ -5395,6 +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);
Index: linux-4.18.5-rt3/kernel/cgroup/cpuset.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cgroup/cpuset.c
+++ linux-4.18.5-rt3/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);
 }
 
@@ -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, &current->cpus_allowed);
+       set_cpus_allowed_ptr(task, current->cpus_ptr);
        task->mems_allowed = current->mems_allowed;
 }
 
@@ -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;
 }
 
Index: linux-4.18.5-rt3/kernel/cgroup/rstat.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cgroup/rstat.c
+++ linux-4.18.5-rt3/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() ||
Index: linux-4.18.5-rt3/kernel/cpu.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/cpu.c
+++ linux-4.18.5-rt3/kernel/cpu.c
@@ -74,6 +74,11 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_s
        .fail = CPUHP_INVALID,
 };
 
+#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
+
 #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);
@@ -283,6 +288,55 @@ static int cpu_hotplug_disabled;
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+/**
+ * pin_current_cpu - Prevent the current cpu from being unplugged
+ */
+void pin_current_cpu(void)
+{
+#ifdef CONFIG_PREEMPT_RT_FULL
+       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;
+#endif
+}
+
+/**
+ * unpin_current_cpu - Allow unplug of current cpu
+ */
+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()))
+               cpuhp_pin = per_cpu_ptr(&cpuhp_pin_lock, current->pinned_on_cpu);
+
+       current->pinned_on_cpu = -1;
+       __read_rt_unlock(cpuhp_pin);
+#endif
+}
+
 DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
 
 void cpus_read_lock(void)
@@ -839,6 +893,9 @@ 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;
 
@@ -851,11 +908,18 @@ 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 */
@@ -874,6 +938,9 @@ 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();
 
Index: linux-4.18.5-rt3/kernel/debug/kdb/kdb_io.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/debug/kdb/kdb_io.c
+++ linux-4.18.5-rt3/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;
 }
Index: linux-4.18.5-rt3/kernel/events/core.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/events/core.c
+++ linux-4.18.5-rt3/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;
 
        /*
Index: linux-4.18.5-rt3/kernel/exit.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/exit.c
+++ linux-4.18.5-rt3/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);
 
Index: linux-4.18.5-rt3/kernel/fork.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/fork.c
+++ linux-4.18.5-rt3/kernel/fork.c
@@ -40,6 +40,7 @@
 #include <linux/hmm.h>
 #include <linux/fs.h>
 #include <linux/mm.h>
+#include <linux/kprobes.h>
 #include <linux/vmacache.h>
 #include <linux/nsproxy.h>
 #include <linux/capability.h>
@@ -637,6 +638,19 @@ 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;
@@ -671,13 +685,24 @@ 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);
        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);
@@ -688,7 +713,18 @@ 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) { }
 
@@ -845,6 +881,8 @@ 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
@@ -857,6 +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);
 
@@ -1561,6 +1600,9 @@ 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;
@@ -1717,6 +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
Index: linux-4.18.5-rt3/kernel/futex.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/futex.c
+++ linux-4.18.5-rt3/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;
                }
@@ -1412,6 +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);
@@ -1473,13 +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;
 }
@@ -2086,6 +2089,16 @@ retry_private:
                                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
@@ -2624,10 +2637,9 @@ 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 +2738,8 @@ 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);
        }
 
@@ -2783,7 +2794,7 @@ retry_private:
                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
@@ -2798,9 +2809,18 @@ retry_private:
         * 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 +2967,21 @@ retry:
                 * 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);
 
                /*
@@ -3109,7 +3139,7 @@ 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;
@@ -3125,10 +3155,9 @@ 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);
        }
@@ -3137,7 +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))
@@ -3168,20 +3197,55 @@ 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(&current->pi_lock);
+       if (current->pi_blocked_on) {
+               /*
+                * We have been requeued or are in the process of
+                * being requeued.
+                */
+               raw_spin_unlock_irq(&current->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(&current->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(&current->pi_lock);
+               current->pi_blocked_on = NULL;
+               raw_spin_unlock_irq(&current->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) {
@@ -3190,7 +3254,8 @@ 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;
@@ -3201,7 +3266,7 @@ 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;
@@ -3215,7 +3280,8 @@ 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;
 
Index: linux-4.18.5-rt3/kernel/irq/handle.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/irq/handle.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/kernel/irq/manage.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/irq/manage.c
+++ linux-4.18.5-rt3/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)
@@ -257,7 +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);
 
@@ -295,10 +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;
@@ -320,6 +325,35 @@ out:
        kref_put(&notify->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
@@ -348,7 +382,12 @@ irq_set_affinity_notifier(unsigned int i
        if (notify) {
                notify->irq = irq;
                kref_init(&notify->kref);
+#ifdef CONFIG_PREEMPT_RT_BASE
+               INIT_SWORK(&notify->swork, irq_affinity_notify);
+               init_helper_thread();
+#else
                INIT_WORK(&notify->work, irq_affinity_notify);
+#endif
        }
 
        raw_spin_lock_irqsave(&desc->lock, flags);
@@ -921,7 +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;
 }
 
@@ -1018,6 +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);
        }
 
@@ -1431,6 +1484,9 @@ __setup_irq(unsigned int irq, struct irq
                        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 {
@@ -2211,7 +2267,7 @@ 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,
Index: linux-4.18.5-rt3/kernel/irq/settings.h
===================================================================
--- linux-4.18.5-rt3.orig/kernel/irq/settings.h
+++ linux-4.18.5-rt3/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;
Index: linux-4.18.5-rt3/kernel/irq/spurious.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/irq/spurious.c
+++ linux-4.18.5-rt3/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");
Index: linux-4.18.5-rt3/kernel/irq_work.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/irq_work.c
+++ linux-4.18.5-rt3/kernel/irq_work.c
@@ -17,6 +17,7 @@
 #include <linux/cpu.h>
 #include <linux/notifier.h>
 #include <linux/smp.h>
+#include <linux/interrupt.h>
 #include <asm/processor.h>
 
 
@@ -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
Index: linux-4.18.5-rt3/kernel/ksysfs.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/ksysfs.c
+++ linux-4.18.5-rt3/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
 };
 
Index: linux-4.18.5-rt3/kernel/locking/Makefile
===================================================================
--- linux-4.18.5-rt3.orig/kernel/locking/Makefile
+++ linux-4.18.5-rt3/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
Index: linux-4.18.5-rt3/kernel/locking/lockdep.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/locking/lockdep.c
+++ linux-4.18.5-rt3/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);
Index: linux-4.18.5-rt3/kernel/locking/locktorture.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/locking/locktorture.c
+++ linux-4.18.5-rt3/kernel/locking/locktorture.c
@@ -26,7 +26,6 @@
 #include <linux/kthread.h>
 #include <linux/sched/rt.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/mutex.h>
 #include <linux/rwsem.h>
 #include <linux/smp.h>
Index: linux-4.18.5-rt3/kernel/locking/mutex-rt.c
===================================================================
--- /dev/null
+++ linux-4.18.5-rt3/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 <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * 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 <andrea@suse.de>
+ *  - 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 <tglx@timesys.com>
+ *  - 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 <rostedt@goodmis.org>
+ *  - debugged and patched Thomas Gleixner's rework.
+ *  - added back the cmpxchg to the rework.
+ *  - turned atomic require back on for SMP.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/rtmutex.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/syscalls.h>
+#include <linux/interrupt.h>
+#include <linux/plist.h>
+#include <linux/fs.h>
+#include <linux/futex.h>
+#include <linux/hrtimer.h>
+
+#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);
Index: linux-4.18.5-rt3/kernel/locking/rtmutex.c
===================================================================
--- linux-4.18.5-rt3.orig/kernel/locking/rtmutex.c
+++ linux-4.18.5-rt3/kernel/locking/rtmutex.c
@@ -7,6 +7,11 @@
  *  Copyright (C) 2005-2006 Timesys Corp., Thomas Gleixner <tglx@timesys.com>
  *  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 <srostedt@redhat.com>
  *
  *  See Documentation/locking/rt-mutex-design.txt for details.
  */
@@ -18,6 +23,8 @@
 #include <linux/sched/wake_q.h>
 #include <linux/sched/debug.h>
 #include <linux/timer.h>
+#include <linux/ww_mutex.h>
+#include <linux/blkdev.h>
 
 #include "rtmutex_common.h"
 
@@ -135,6 +142,12 @@ 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 &&
+               waiter != PI_REQUEUE_INPROGRESS;
+}
+
 /*
  * We can speed up the acquire/release, if there's no debugging state to be
  * set up.
@@ -228,7 +241,7 @@ 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,
@@ -268,6 +281,27 @@ 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)
 {
@@ -372,6 +406,14 @@ 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:
  */
@@ -379,7 +421,8 @@ 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 +558,7 @@ 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;
 
        /*
@@ -696,13 +739,16 @@ 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;
        }
@@ -804,9 +850,11 @@ 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);
 
@@ -842,12 +890,11 @@ 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.
@@ -865,14 +912,12 @@ 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
@@ -919,6 +964,338 @@ takeit:
        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)
+{
+       sleeping_lock_inc();
+       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)
+{
+       sleeping_lock_inc();
+       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();
+       sleeping_lock_dec();
+}
+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;
+
+       sleeping_lock_inc();
+       migrate_disable();
+       ret = __rt_mutex_trylock(&lock->lock);
+       if (ret) {
+               spin_acquire(&lock->dep_map, 0, 1, _RET_IP_);
+       } else {
+               migrate_enable();
+               sleeping_lock_dec();
+       }
+       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) {
+               sleeping_lock_inc();
+               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) {
+               sleeping_lock_inc();
+               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 */
+
+#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)
+{
+       return __try_to_take_rt_mutex(lock, task, waiter, STEAL_NORMAL);
+}
+
 /*
  * Task blocks on lock.
  *
@@ -951,6 +1328,22 @@ 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 +1367,7 @@ 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;
@@ -1016,6 +1409,7 @@ 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;
@@ -1055,7 +1449,10 @@ 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(&current->pi_lock);
 }
 
@@ -1070,7 +1467,7 @@ 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 +1493,8 @@ 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);
 
@@ -1132,26 +1530,28 @@ 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;
        }
        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;
 }
 
 /**
@@ -1167,7 +1567,8 @@ 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;
 
@@ -1176,16 +1577,17 @@ __rt_mutex_slowlock(struct rt_mutex *loc
                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 (timeout && !timeout->task) {
+                       ret = -ETIMEDOUT;
+                       break;
+               }
+               if (signal_pending_state(state, current)) {
+                       ret = -EINTR;
+                       break;
+               }
+
+               if (ww_ctx && ww_ctx->acquired > 0) {
+                       ret = __mutex_lock_check_stamp(lock, ww_ctx);
                        if (ret)
                                break;
                }
@@ -1224,33 +1626,104 @@ 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)
+static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
+                                                  struct ww_acquire_ctx *ww_ctx)
 {
-       struct rt_mutex_waiter waiter;
-       unsigned long flags;
-       int ret = 0;
+#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);
 
-       rt_mutex_init_waiter(&waiter);
+       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;
+       }
 
        /*
-        * 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.
+        * Naughty, using a different class will lead to undefined behavior!
         */
-       raw_spin_lock_irqsave(&lock->wait_lock, flags);
+       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)) {
-               raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
+               if (ww_ctx)
+                       ww_mutex_account_lock(lock, ww_ctx);
                return 0;
        }
 
@@ -1260,16 +1733,26 @@ 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))
+       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);
+               remove_waiter(lock, 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);
        }
 
        /*
@@ -1277,6 +1760,36 @@ 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 ww_acquire_ctx *ww_ctx)
+{
+       struct rt_mutex_waiter waiter;
+       unsigned long flags;
+       int ret = 0;
+
+       rt_mutex_init_waiter(&waiter, false);
+
+       /*
+        * 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, ww_ctx,
+                                      &waiter);
 
        raw_spin_unlock_irqrestore(&lock->wait_lock, flags);
 
@@ -1337,7 +1850,8 @@ 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;
 
@@ -1391,7 +1905,7 @@ 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() */
@@ -1405,29 +1919,45 @@ 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);
+       /*
+        * 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);
 }
 
 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);
+       if (unlikely(blk_needs_flush_plug(current)))
+               blk_schedule_flush_plug(current);
+
+       return slowfn(lock, state, timeout, chwalk, ww_ctx);
 }
 
 static inline int
@@ -1443,9 +1973,11 @@ 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();
@@ -1454,23 +1986,46 @@ 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);
 }
 
-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
@@ -1511,16 +2066,7 @@ 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);
 
@@ -1538,6 +2084,22 @@ 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
+ */
+int __sched rt_mutex_lock_killable(struct rt_mutex *lock)
+{
+       return rt_mutex_lock_state(lock, 0, TASK_KILLABLE);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_killable);
+
+/**
  * rt_mutex_timed_lock - lock a rt_mutex interruptible
  *                     the timeout structure is provided
  *                     by the caller
@@ -1560,6 +2122,7 @@ 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_);
@@ -1568,6 +2131,18 @@ 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
  *
@@ -1583,10 +2158,7 @@ int __sched rt_mutex_trylock(struct rt_m
 {
        int ret;
 
-       if (WARN_ON_ONCE(in_irq() || in_nmi() || in_serving_softirq()))
-               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_);
 
@@ -1594,6 +2166,11 @@ 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
  *
@@ -1602,16 +2179,13 @@ EXPORT_SYMBOL_GPL(rt_mutex_trylock);
 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);
 
@@ -1628,23 +2202,35 @@ 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);
 }
 
 /**
@@ -1683,7 +2269,7 @@ void __rt_mutex_init(struct rt_mutex *lo
        if (name && key)