aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMark Brown <broonie@kernel.org>2018-08-06 12:32:24 +0100
committerMark Brown <broonie@kernel.org>2018-08-06 12:32:24 +0100
commitb2cf79fb81cc04553c65feafda5ee994474694d9 (patch)
tree521713d2b10ca71535f4f579ea254a4ce1dcfa75
parentd089b17a9de3a6f2805b10874c2890492b5b662b (diff)
parentc3547993bf846cf6dafff25953713302676e1f19 (diff)
downloadlinux-linaro-stable-linux-linaro-lsk-v4.14-test.tar.gz
Merge tag 'v4.14.59-rt37' into linux-linaro-lsk-v4.14linux-linaro-lsk-v4.14-test
Linux 4.14.59-rt37
-rw-r--r--Documentation/trace/events.txt1548
-rw-r--r--Documentation/trace/ftrace.txt24
-rw-r--r--Documentation/trace/histogram.txt1995
-rw-r--r--arch/Kconfig1
-rw-r--r--arch/alpha/include/asm/spinlock_types.h4
-rw-r--r--arch/arm/Kconfig5
-rw-r--r--arch/arm/include/asm/irq.h2
-rw-r--r--arch/arm/include/asm/spinlock_types.h4
-rw-r--r--arch/arm/include/asm/switch_to.h8
-rw-r--r--arch/arm/include/asm/thread_info.h8
-rw-r--r--arch/arm/kernel/asm-offsets.c1
-rw-r--r--arch/arm/kernel/entry-armv.S19
-rw-r--r--arch/arm/kernel/entry-common.S9
-rw-r--r--arch/arm/kernel/patch.c6
-rw-r--r--arch/arm/kernel/process.c24
-rw-r--r--arch/arm/kernel/signal.c3
-rw-r--r--arch/arm/kernel/smp.c3
-rw-r--r--arch/arm/kernel/unwind.c14
-rw-r--r--arch/arm/mach-exynos/platsmp.c12
-rw-r--r--arch/arm/mach-hisi/platmcpm.c22
-rw-r--r--arch/arm/mach-omap2/omap-smp.c10
-rw-r--r--arch/arm/mach-prima2/platsmp.c10
-rw-r--r--arch/arm/mach-qcom/platsmp.c10
-rw-r--r--arch/arm/mach-spear/platsmp.c10
-rw-r--r--arch/arm/mach-sti/platsmp.c10
-rw-r--r--arch/arm/mm/fault.c6
-rw-r--r--arch/arm/mm/highmem.c58
-rw-r--r--arch/arm/plat-versatile/platsmp.c10
-rw-r--r--arch/arm64/Kconfig3
-rw-r--r--arch/arm64/crypto/Kconfig20
-rw-r--r--arch/arm64/crypto/crc32-ce-glue.c3
-rw-r--r--arch/arm64/include/asm/spinlock_types.h4
-rw-r--r--arch/arm64/include/asm/thread_info.h6
-rw-r--r--arch/arm64/kernel/asm-offsets.c1
-rw-r--r--arch/arm64/kernel/entry.S12
-rw-r--r--arch/arm64/kernel/signal.c2
-rw-r--r--arch/blackfin/include/asm/spinlock_types.h4
-rw-r--r--arch/hexagon/include/asm/spinlock_types.h4
-rw-r--r--arch/ia64/include/asm/spinlock_types.h4
-rw-r--r--arch/ia64/kernel/mca.c2
-rw-r--r--arch/m32r/include/asm/spinlock_types.h4
-rw-r--r--arch/metag/include/asm/spinlock_types.h4
-rw-r--r--arch/mips/Kconfig2
-rw-r--r--arch/mips/include/asm/switch_to.h4
-rw-r--r--arch/mips/kernel/mips-mt-fpaff.c2
-rw-r--r--arch/mips/kernel/traps.c6
-rw-r--r--arch/mn10300/include/asm/spinlock_types.h4
-rw-r--r--arch/powerpc/Kconfig6
-rw-r--r--arch/powerpc/include/asm/spinlock_types.h4
-rw-r--r--arch/powerpc/include/asm/thread_info.h11
-rw-r--r--arch/powerpc/kernel/asm-offsets.c1
-rw-r--r--arch/powerpc/kernel/entry_32.S17
-rw-r--r--arch/powerpc/kernel/entry_64.S14
-rw-r--r--arch/powerpc/kernel/irq.c2
-rw-r--r--arch/powerpc/kernel/misc_32.S2
-rw-r--r--arch/powerpc/kernel/misc_64.S2
-rw-r--r--arch/powerpc/kvm/Kconfig1
-rw-r--r--arch/powerpc/platforms/cell/spufs/sched.c2
-rw-r--r--arch/powerpc/platforms/ps3/device-init.c2
-rw-r--r--arch/s390/include/asm/spinlock_types.h4
-rw-r--r--arch/sh/include/asm/spinlock_types.h4
-rw-r--r--arch/sh/kernel/irq.c2
-rw-r--r--arch/sparc/Kconfig6
-rw-r--r--arch/sparc/kernel/irq_64.c2
-rw-r--r--arch/tile/include/asm/setup.h2
-rw-r--r--arch/tile/include/asm/spinlock_types.h4
-rw-r--r--arch/tile/kernel/hardwall.c10
-rw-r--r--arch/x86/Kconfig8
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c22
-rw-r--r--arch/x86/crypto/camellia_aesni_avx2_glue.c20
-rw-r--r--arch/x86/crypto/camellia_aesni_avx_glue.c19
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c21
-rw-r--r--arch/x86/crypto/cast6_avx_glue.c24
-rw-r--r--arch/x86/crypto/chacha20_glue.c9
-rw-r--r--arch/x86/crypto/glue_helper.c31
-rw-r--r--arch/x86/crypto/serpent_avx2_glue.c19
-rw-r--r--arch/x86/crypto/serpent_avx_glue.c23
-rw-r--r--arch/x86/crypto/serpent_sse2_glue.c23
-rw-r--r--arch/x86/crypto/twofish_avx_glue.c27
-rw-r--r--arch/x86/entry/common.c11
-rw-r--r--arch/x86/entry/entry_32.S17
-rw-r--r--arch/x86/entry/entry_64.S18
-rw-r--r--arch/x86/include/asm/fpu/api.h1
-rw-r--r--arch/x86/include/asm/preempt.h31
-rw-r--r--arch/x86/include/asm/signal.h13
-rw-r--r--arch/x86/include/asm/stackprotector.h8
-rw-r--r--arch/x86/include/asm/thread_info.h11
-rw-r--r--arch/x86/include/asm/uv/uv_bau.h14
-rw-r--r--arch/x86/kernel/apic/io_apic.c3
-rw-r--r--arch/x86/kernel/asm-offsets.c2
-rw-r--r--arch/x86/kernel/cpu/mcheck/dev-mcelog.c37
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c54
-rw-r--r--arch/x86/kernel/fpu/core.c12
-rw-r--r--arch/x86/kernel/irq_32.c2
-rw-r--r--arch/x86/kernel/process_32.c32
-rw-r--r--arch/x86/kvm/lapic.c2
-rw-r--r--arch/x86/kvm/x86.c7
-rw-r--r--arch/x86/mm/highmem_32.c13
-rw-r--r--arch/x86/mm/iomap_32.c11
-rw-r--r--arch/x86/platform/uv/tlb_uv.c26
-rw-r--r--arch/x86/platform/uv/uv_time.c20
-rw-r--r--arch/xtensa/include/asm/spinlock_types.h4
-rw-r--r--block/blk-core.c31
-rw-r--r--block/blk-ioc.c5
-rw-r--r--block/blk-mq.c36
-rw-r--r--block/blk-mq.h4
-rw-r--r--block/blk-softirq.c3
-rw-r--r--block/bounce.c4
-rw-r--r--crypto/algapi.c4
-rw-r--r--crypto/api.c6
-rw-r--r--crypto/internal.h4
-rw-r--r--drivers/acpi/acpica/acglobal.h2
-rw-r--r--drivers/acpi/acpica/hwregs.c4
-rw-r--r--drivers/acpi/acpica/hwxface.c4
-rw-r--r--drivers/acpi/acpica/utmutex.c4
-rw-r--r--drivers/ata/libata-sff.c4
-rw-r--r--drivers/block/brd.c1
-rw-r--r--drivers/block/zram/zcomp.c13
-rw-r--r--drivers/block/zram/zcomp.h1
-rw-r--r--drivers/block/zram/zram_drv.c31
-rw-r--r--drivers/block/zram/zram_drv.h3
-rw-r--r--drivers/char/random.c33
-rw-r--r--drivers/char/tpm/tpm_tis.c29
-rw-r--r--drivers/clocksource/tcb_clksrc.c69
-rw-r--r--drivers/clocksource/timer-atmel-pit.c24
-rw-r--r--drivers/clocksource/timer-atmel-st.c34
-rw-r--r--drivers/connector/cn_proc.c6
-rw-r--r--drivers/cpufreq/Kconfig.x862
-rw-r--r--drivers/gpu/drm/i915/i915_gem_timeline.c5
-rw-r--r--drivers/gpu/drm/i915/i915_irq.c2
-rw-r--r--drivers/gpu/drm/i915/intel_sprite.c11
-rw-r--r--drivers/gpu/drm/radeon/radeon_display.c2
-rw-r--r--drivers/hv/vmbus_drv.c4
-rw-r--r--drivers/ide/alim15x3.c4
-rw-r--r--drivers/ide/hpt366.c4
-rw-r--r--drivers/ide/ide-io-std.c8
-rw-r--r--drivers/ide/ide-io.c2
-rw-r--r--drivers/ide/ide-iops.c4
-rw-r--r--drivers/ide/ide-probe.c4
-rw-r--r--drivers/ide/ide-taskfile.c6
-rw-r--r--drivers/infiniband/hw/hfi1/affinity.c6
-rw-r--r--drivers/infiniband/hw/hfi1/sdma.c3
-rw-r--r--drivers/infiniband/hw/qib/qib_file_ops.c7
-rw-r--r--drivers/infiniband/ulp/ipoib/ipoib_multicast.c4
-rw-r--r--drivers/input/gameport/gameport.c12
-rw-r--r--drivers/iommu/amd_iommu.c254
-rw-r--r--drivers/iommu/amd_iommu_init.c2
-rw-r--r--drivers/iommu/amd_iommu_types.h6
-rw-r--r--drivers/iommu/iova.c4
-rw-r--r--drivers/leds/trigger/Kconfig2
-rw-r--r--drivers/md/bcache/Kconfig1
-rw-r--r--drivers/md/dm-rq.c2
-rw-r--r--drivers/md/raid5.c12
-rw-r--r--drivers/md/raid5.h1
-rw-r--r--drivers/mfd/atmel-smc.c1
-rw-r--r--drivers/misc/Kconfig13
-rw-r--r--drivers/mmc/host/mmci.c5
-rw-r--r--drivers/net/ethernet/3com/3c59x.c8
-rw-r--r--drivers/net/ethernet/marvell/mvpp2.c62
-rw-r--r--drivers/net/wireless/intersil/orinoco/orinoco_usb.c2
-rw-r--r--drivers/net/wireless/mac80211_hwsim.c44
-rw-r--r--drivers/pci/switch/switchtec.c22
-rw-r--r--drivers/scsi/fcoe/fcoe.c16
-rw-r--r--drivers/scsi/fcoe/fcoe_ctlr.c4
-rw-r--r--drivers/scsi/libfc/fc_exch.c4
-rw-r--r--drivers/scsi/libsas/sas_ata.c4
-rw-r--r--drivers/scsi/qla2xxx/qla_inline.h4
-rw-r--r--drivers/staging/greybus/audio_manager.c2
-rw-r--r--drivers/target/target_core_tmr.c2
-rw-r--r--drivers/target/target_core_transport.c6
-rw-r--r--drivers/thermal/x86_pkg_temp_thermal.c52
-rw-r--r--drivers/tty/serial/8250/8250_core.c11
-rw-r--r--drivers/tty/serial/8250/8250_port.c5
-rw-r--r--drivers/tty/serial/amba-pl011.c15
-rw-r--r--drivers/tty/serial/omap-serial.c12
-rw-r--r--drivers/usb/core/hcd.c4
-rw-r--r--drivers/usb/gadget/function/f_fs.c2
-rw-r--r--drivers/usb/gadget/function/f_ncm.c30
-rw-r--r--drivers/usb/gadget/legacy/inode.c4
-rw-r--r--fs/aio.c15
-rw-r--r--fs/autofs4/autofs_i.h1
-rw-r--r--fs/autofs4/expire.c2
-rw-r--r--fs/buffer.c21
-rw-r--r--fs/cifs/readdir.c2
-rw-r--r--fs/dcache.c69
-rw-r--r--fs/eventpoll.c4
-rw-r--r--fs/exec.c2
-rw-r--r--fs/ext4/page-io.c6
-rw-r--r--fs/fuse/dir.c2
-rw-r--r--fs/inode.c2
-rw-r--r--fs/libfs.c6
-rw-r--r--fs/locks.c32
-rw-r--r--fs/namei.c4
-rw-r--r--fs/namespace.c8
-rw-r--r--fs/nfs/delegation.c4
-rw-r--r--fs/nfs/dir.c12
-rw-r--r--fs/nfs/inode.c4
-rw-r--r--fs/nfs/nfs4_fs.h2
-rw-r--r--fs/nfs/nfs4proc.c4
-rw-r--r--fs/nfs/nfs4state.c22
-rw-r--r--fs/nfs/unlink.c35
-rw-r--r--fs/ntfs/aops.c18
-rw-r--r--fs/proc/array.c4
-rw-r--r--fs/proc/base.c2
-rw-r--r--fs/proc/proc_sysctl.c2
-rw-r--r--fs/timerfd.c5
-rw-r--r--fs/xfs/xfs_aops.c6
-rw-r--r--include/acpi/platform/aclinux.h15
-rw-r--r--include/asm-generic/bug.h14
-rw-r--r--include/linux/blk-mq.h2
-rw-r--r--include/linux/blkdev.h5
-rw-r--r--include/linux/bottom_half.h34
-rw-r--r--include/linux/buffer_head.h42
-rw-r--r--include/linux/cgroup-defs.h2
-rw-r--r--include/linux/completion.h10
-rw-r--r--include/linux/cpu.h5
-rw-r--r--include/linux/dcache.h4
-rw-r--r--include/linux/delay.h6
-rw-r--r--include/linux/fs.h2
-rw-r--r--include/linux/highmem.h32
-rw-r--r--include/linux/hrtimer.h151
-rw-r--r--include/linux/idr.h5
-rw-r--r--include/linux/init_task.h10
-rw-r--r--include/linux/interrupt.h93
-rw-r--r--include/linux/irq.h4
-rw-r--r--include/linux/irq_work.h7
-rw-r--r--include/linux/irqdesc.h1
-rw-r--r--include/linux/irqflags.h45
-rw-r--r--include/linux/jbd2.h24
-rw-r--r--include/linux/kdb.h2
-rw-r--r--include/linux/kernel.h5
-rw-r--r--include/linux/list_bl.h30
-rw-r--r--include/linux/locallock.h271
-rw-r--r--include/linux/mm_types.h4
-rw-r--r--include/linux/mutex.h20
-rw-r--r--include/linux/mutex_rt.h130
-rw-r--r--include/linux/netdevice.h108
-rw-r--r--include/linux/netfilter/x_tables.h7
-rw-r--r--include/linux/nfs_fs.h4
-rw-r--r--include/linux/nfs_xdr.h2
-rw-r--r--include/linux/notifier.h42
-rw-r--r--include/linux/percpu-rwsem.h24
-rw-r--r--include/linux/percpu.h29
-rw-r--r--include/linux/pid.h1
-rw-r--r--include/linux/posix-timers.h2
-rw-r--r--include/linux/preempt.h107
-rw-r--r--include/linux/printk.h2
-rw-r--r--include/linux/radix-tree.h7
-rw-r--r--include/linux/random.h2
-rw-r--r--include/linux/rbtree.h2
-rw-r--r--include/linux/rbtree_augmented.h1
-rw-r--r--include/linux/rbtree_latch.h1
-rw-r--r--include/linux/rcu_assign_pointer.h54
-rw-r--r--include/linux/rcupdate.h75
-rw-r--r--include/linux/rcutree.h8
-rw-r--r--include/linux/ring_buffer.h17
-rw-r--r--include/linux/rtmutex.h22
-rw-r--r--include/linux/rwlock_rt.h119
-rw-r--r--include/linux/rwlock_types.h4
-rw-r--r--include/linux/rwlock_types_rt.h55
-rw-r--r--include/linux/rwsem.h11
-rw-r--r--include/linux/rwsem_rt.h67
-rw-r--r--include/linux/sched.h168
-rw-r--r--include/linux/sched/mm.h11
-rw-r--r--include/linux/sched/task.h11
-rw-r--r--include/linux/sched/wake_q.h27
-rw-r--r--include/linux/seqlock.h65
-rw-r--r--include/linux/signal.h1
-rw-r--r--include/linux/skbuff.h7
-rw-r--r--include/linux/smp.h3
-rw-r--r--include/linux/spinlock.h12
-rw-r--r--include/linux/spinlock_api_smp.h4
-rw-r--r--include/linux/spinlock_rt.h159
-rw-r--r--include/linux/spinlock_types.h79
-rw-r--r--include/linux/spinlock_types_nort.h33
-rw-r--r--include/linux/spinlock_types_raw.h58
-rw-r--r--include/linux/spinlock_types_rt.h48
-rw-r--r--include/linux/spinlock_types_up.h4
-rw-r--r--include/linux/srcutiny.h6
-rw-r--r--include/linux/srcutree.h14
-rw-r--r--include/linux/suspend.h6
-rw-r--r--include/linux/swait.h2
-rw-r--r--include/linux/swap.h5
-rw-r--r--include/linux/swork.h24
-rw-r--r--include/linux/thread_info.h12
-rw-r--r--include/linux/timer.h2
-rw-r--r--include/linux/trace_events.h17
-rw-r--r--include/linux/uaccess.h2
-rw-r--r--include/linux/vmstat.h4
-rw-r--r--include/linux/wait.h5
-rw-r--r--include/net/gen_stats.h9
-rw-r--r--include/net/neighbour.h6
-rw-r--r--include/net/net_seq_lock.h15
-rw-r--r--include/net/sch_generic.h21
-rw-r--r--include/net/xfrm.h2
-rw-r--r--include/trace/events/timer.h19
-rw-r--r--init/Kconfig5
-rw-r--r--init/Makefile2
-rw-r--r--init/main.c1
-rw-r--r--kernel/Kconfig.locks4
-rw-r--r--kernel/Kconfig.preempt33
-rw-r--r--kernel/cgroup/cgroup.c9
-rw-r--r--kernel/cgroup/cpuset.c68
-rw-r--r--kernel/cpu.c67
-rw-r--r--kernel/debug/kdb/kdb_io.c2
-rw-r--r--kernel/events/core.c4
-rw-r--r--kernel/exit.c2
-rw-r--r--kernel/fork.c46
-rw-r--r--kernel/futex.c128
-rw-r--r--kernel/irq/handle.c8
-rw-r--r--kernel/irq/manage.c66
-rw-r--r--kernel/irq/settings.h12
-rw-r--r--kernel/irq/spurious.c8
-rw-r--r--kernel/irq_work.c56
-rw-r--r--kernel/ksysfs.c12
-rw-r--r--kernel/locking/Makefile9
-rw-r--r--kernel/locking/lockdep.c2
-rw-r--r--kernel/locking/locktorture.c1
-rw-r--r--kernel/locking/mutex-rt.c223
-rw-r--r--kernel/locking/rtmutex.c954
-rw-r--r--kernel/locking/rtmutex_common.h31
-rw-r--r--kernel/locking/rwlock-rt.c378
-rw-r--r--kernel/locking/rwsem-rt.c269
-rw-r--r--kernel/locking/spinlock.c7
-rw-r--r--kernel/locking/spinlock_debug.c5
-rw-r--r--kernel/panic.c2
-rw-r--r--kernel/power/hibernate.c14
-rw-r--r--kernel/power/suspend.c8
-rw-r--r--kernel/printk/printk.c142
-rw-r--r--kernel/ptrace.c9
-rw-r--r--kernel/rcu/Kconfig6
-rw-r--r--kernel/rcu/rcu.h14
-rw-r--r--kernel/rcu/rcu_segcblist.c1
-rw-r--r--kernel/rcu/rcutorture.c7
-rw-r--r--kernel/rcu/srcutree.c143
-rw-r--r--kernel/rcu/tree.c154
-rw-r--r--kernel/rcu/tree.h7
-rw-r--r--kernel/rcu/tree_plugin.h169
-rw-r--r--kernel/rcu/update.c4
-rw-r--r--kernel/sched/Makefile2
-rw-r--r--kernel/sched/completion.c34
-rw-r--r--kernel/sched/core.c568
-rw-r--r--kernel/sched/cpudeadline.c4
-rw-r--r--kernel/sched/cpupri.c4
-rw-r--r--kernel/sched/deadline.c8
-rw-r--r--kernel/sched/debug.c4
-rw-r--r--kernel/sched/fair.c44
-rw-r--r--kernel/sched/features.h8
-rw-r--r--kernel/sched/rt.c8
-rw-r--r--kernel/sched/sched.h10
-rw-r--r--kernel/sched/swait.c21
-rw-r--r--kernel/sched/swork.c173
-rw-r--r--kernel/sched/topology.c1
-rw-r--r--kernel/signal.c120
-rw-r--r--kernel/softirq.c832
-rw-r--r--kernel/stop_machine.c2
-rw-r--r--kernel/time/alarmtimer.c2
-rw-r--r--kernel/time/hrtimer.c802
-rw-r--r--kernel/time/itimer.c1
-rw-r--r--kernel/time/jiffies.c7
-rw-r--r--kernel/time/posix-cpu-timers.c157
-rw-r--r--kernel/time/posix-timers.c43
-rw-r--r--kernel/time/tick-broadcast-hrtimer.c2
-rw-r--r--kernel/time/tick-common.c10
-rw-r--r--kernel/time/tick-internal.h13
-rw-r--r--kernel/time/tick-sched.c33
-rw-r--r--kernel/time/timekeeping.c6
-rw-r--r--kernel/time/timekeeping.h3
-rw-r--r--kernel/time/timer.c147
-rw-r--r--kernel/trace/Kconfig5
-rw-r--r--kernel/trace/ring_buffer.c185
-rw-r--r--kernel/trace/trace.c225
-rw-r--r--kernel/trace/trace.h27
-rw-r--r--kernel/trace/trace_events.c33
-rw-r--r--kernel/trace/trace_events_hist.c4560
-rw-r--r--kernel/trace/trace_events_trigger.c53
-rw-r--r--kernel/trace/trace_hwlat.c2
-rw-r--r--kernel/trace/trace_kprobe.c18
-rw-r--r--kernel/trace/trace_output.c19
-rw-r--r--kernel/trace/trace_probe.c86
-rw-r--r--kernel/trace/trace_probe.h7
-rw-r--r--kernel/trace/trace_uprobe.c2
-rw-r--r--kernel/trace/tracing_map.c231
-rw-r--r--kernel/trace/tracing_map.h20
-rw-r--r--kernel/user.c4
-rw-r--r--kernel/watchdog.c2
-rw-r--r--kernel/watchdog_hld.c10
-rw-r--r--kernel/workqueue.c234
-rw-r--r--kernel/workqueue_internal.h5
-rw-r--r--lib/Kconfig1
-rw-r--r--lib/Kconfig.debug2
-rw-r--r--lib/debugobjects.c5
-rw-r--r--lib/irq_poll.c5
-rw-r--r--lib/locking-selftest.c50
-rw-r--r--lib/percpu_ida.c20
-rw-r--r--lib/radix-tree.c32
-rw-r--r--lib/scatterlist.c2
-rw-r--r--lib/smp_processor_id.c2
-rw-r--r--lib/timerqueue.c8
-rw-r--r--localversion-rt1
-rw-r--r--mm/Kconfig2
-rw-r--r--mm/backing-dev.c4
-rw-r--r--mm/compaction.c6
-rw-r--r--mm/filemap.c9
-rw-r--r--mm/highmem.c6
-rw-r--r--mm/memcontrol.c28
-rw-r--r--mm/mmu_context.c2
-rw-r--r--mm/page_alloc.c151
-rw-r--r--mm/slab.h4
-rw-r--r--mm/slub.c138
-rw-r--r--mm/swap.c74
-rw-r--r--mm/truncate.c4
-rw-r--r--mm/vmalloc.c13
-rw-r--r--mm/vmstat.c12
-rw-r--r--mm/workingset.c31
-rw-r--r--mm/zsmalloc.c80
-rw-r--r--net/9p/trans_xen.c1
-rw-r--r--net/Kconfig2
-rw-r--r--net/bluetooth/hci_sock.c17
-rw-r--r--net/can/bcm.c156
-rw-r--r--net/core/dev.c111
-rw-r--r--net/core/filter.c6
-rw-r--r--net/core/gen_estimator.c6
-rw-r--r--net/core/gen_stats.c8
-rw-r--r--net/core/pktgen.c4
-rw-r--r--net/core/skbuff.c35
-rw-r--r--net/core/sock.c3
-rw-r--r--net/ipv4/icmp.c8
-rw-r--r--net/ipv4/tcp_ipv4.c6
-rw-r--r--net/mac80211/rx.c2
-rw-r--r--net/netfilter/core.c6
-rw-r--r--net/packet/af_packet.c5
-rw-r--r--net/rds/ib_rdma.c3
-rw-r--r--net/rxrpc/security.c3
-rw-r--r--net/sched/sch_api.c2
-rw-r--r--net/sched/sch_generic.c14
-rw-r--r--net/sunrpc/svc_xprt.c6
-rw-r--r--net/xfrm/xfrm_state.c30
-rw-r--r--samples/trace_events/trace-events-sample.c2
-rwxr-xr-xscripts/mkcompile_h4
-rw-r--r--security/apparmor/include/path.h21
-rw-r--r--security/apparmor/lsm.c2
-rw-r--r--sound/core/pcm_native.c8
-rw-r--r--sound/drivers/dummy.c27
-rw-r--r--tools/testing/selftests/ftrace/test.d/functions7
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-extended-error-support.tc39
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-field-variable-support.tc54
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-inter-event-combined-hist.tc58
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-action-hist.tc50
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmatch-onmax-action-hist.tc50
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-onmax-action-hist.tc48
-rw-r--r--tools/testing/selftests/ftrace/test.d/trigger/inter-event/trigger-synthetic-event-createremove.tc54
-rw-r--r--virt/kvm/arm/arm.c8
453 files changed, 17073 insertions, 4966 deletions
diff --git a/Documentation/trace/events.txt b/Documentation/trace/events.txt
index 2cc08d4a326e..e28f7f29f2b3 100644
--- a/Documentation/trace/events.txt
+++ b/Documentation/trace/events.txt
@@ -517,1550 +517,4 @@ The following commands are supported:
totals derived from one or more trace event format fields and/or
event counts (hitcount).
- The format of a hist trigger is as follows:
-
- hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
- [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
- [:clear][:name=histname1] [if <filter>]
-
- When a matching event is hit, an entry is added to a hash table
- using the key(s) and value(s) named. Keys and values correspond to
- fields in the event's format description. Values must correspond to
- numeric fields - on an event hit, the value(s) will be added to a
- sum kept for that field. The special string 'hitcount' can be used
- in place of an explicit value field - this is simply a count of
- event hits. If 'values' isn't specified, an implicit 'hitcount'
- value will be automatically created and used as the only value.
- Keys can be any field, or the special string 'stacktrace', which
- will use the event's kernel stacktrace as the key. The keywords
- 'keys' or 'key' can be used to specify keys, and the keywords
- 'values', 'vals', or 'val' can be used to specify values. Compound
- keys consisting of up to two fields can be specified by the 'keys'
- keyword. Hashing a compound key produces a unique entry in the
- table for each unique combination of component keys, and can be
- useful for providing more fine-grained summaries of event data.
- Additionally, sort keys consisting of up to two fields can be
- specified by the 'sort' keyword. If more than one field is
- specified, the result will be a 'sort within a sort': the first key
- is taken to be the primary sort key and the second the secondary
- key. If a hist trigger is given a name using the 'name' parameter,
- its histogram data will be shared with other triggers of the same
- name, and trigger hits will update this common data. Only triggers
- with 'compatible' fields can be combined in this way; triggers are
- 'compatible' if the fields named in the trigger share the same
- number and type of fields and those fields also have the same names.
- Note that any two events always share the compatible 'hitcount' and
- 'stacktrace' fields and can therefore be combined using those
- fields, however pointless that may be.
-
- 'hist' triggers add a 'hist' file to each event's subdirectory.
- Reading the 'hist' file for the event will dump the hash table in
- its entirety to stdout. If there are multiple hist triggers
- attached to an event, there will be a table for each trigger in the
- output. The table displayed for a named trigger will be the same as
- any other instance having the same name. Each printed hash table
- entry is a simple list of the keys and values comprising the entry;
- keys are printed first and are delineated by curly braces, and are
- followed by the set of value fields for the entry. By default,
- numeric fields are displayed as base-10 integers. This can be
- modified by appending any of the following modifiers to the field
- name:
-
- .hex display a number as a hex value
- .sym display an address as a symbol
- .sym-offset display an address as a symbol and offset
- .syscall display a syscall id as a system call name
- .execname display a common_pid as a program name
-
- Note that in general the semantics of a given field aren't
- interpreted when applying a modifier to it, but there are some
- restrictions to be aware of in this regard:
-
- - only the 'hex' modifier can be used for values (because values
- are essentially sums, and the other modifiers don't make sense
- in that context).
- - the 'execname' modifier can only be used on a 'common_pid'. The
- reason for this is that the execname is simply the 'comm' value
- saved for the 'current' process when an event was triggered,
- which is the same as the common_pid value saved by the event
- tracing code. Trying to apply that comm value to other pid
- values wouldn't be correct, and typically events that care save
- pid-specific comm fields in the event itself.
-
- A typical usage scenario would be the following to enable a hist
- trigger, read its current contents, and then turn it off:
-
- # echo 'hist:keys=skbaddr.hex:vals=len' > \
- /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
- # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
- # echo '!hist:keys=skbaddr.hex:vals=len' > \
- /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
- The trigger file itself can be read to show the details of the
- currently attached hist trigger. This information is also displayed
- at the top of the 'hist' file when read.
-
- By default, the size of the hash table is 2048 entries. The 'size'
- parameter can be used to specify more or fewer than that. The units
- are in terms of hashtable entries - if a run uses more entries than
- specified, the results will show the number of 'drops', the number
- of hits that were ignored. The size should be a power of 2 between
- 128 and 131072 (any non- power-of-2 number specified will be rounded
- up).
-
- The 'sort' parameter can be used to specify a value field to sort
- on. The default if unspecified is 'hitcount' and the default sort
- order is 'ascending'. To sort in the opposite direction, append
- .descending' to the sort key.
-
- The 'pause' parameter can be used to pause an existing hist trigger
- or to start a hist trigger but not log any events until told to do
- so. 'continue' or 'cont' can be used to start or restart a paused
- hist trigger.
-
- The 'clear' parameter will clear the contents of a running hist
- trigger and leave its current paused/active state.
-
- Note that the 'pause', 'cont', and 'clear' parameters should be
- applied using 'append' shell operator ('>>') if applied to an
- existing trigger, rather than via the '>' operator, which will cause
- the trigger to be removed through truncation.
-
-- enable_hist/disable_hist
-
- The enable_hist and disable_hist triggers can be used to have one
- event conditionally start and stop another event's already-attached
- hist trigger. Any number of enable_hist and disable_hist triggers
- can be attached to a given event, allowing that event to kick off
- and stop aggregations on a host of other events.
-
- The format is very similar to the enable/disable_event triggers:
-
- enable_hist:<system>:<event>[:count]
- disable_hist:<system>:<event>[:count]
-
- Instead of enabling or disabling the tracing of the target event
- into the trace buffer as the enable/disable_event triggers do, the
- enable/disable_hist triggers enable or disable the aggregation of
- the target event into a hash table.
-
- A typical usage scenario for the enable_hist/disable_hist triggers
- would be to first set up a paused hist trigger on some event,
- followed by an enable_hist/disable_hist pair that turns the hist
- aggregation on and off when conditions of interest are hit:
-
- # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
- # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
- # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
- The above sets up an initially paused hist trigger which is unpaused
- and starts aggregating events when a given program is executed, and
- which stops aggregating when the process exits and the hist trigger
- is paused again.
-
- The examples below provide a more concrete illustration of the
- concepts and typical usage patterns discussed above.
-
-
-6.2 'hist' trigger examples
----------------------------
-
- The first set of examples creates aggregations using the kmalloc
- event. The fields that can be used for the hist trigger are listed
- in the kmalloc event's format file:
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
- name: kmalloc
- ID: 374
- format:
- field:unsigned short common_type; offset:0; size:2; signed:0;
- field:unsigned char common_flags; offset:2; size:1; signed:0;
- field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
- field:int common_pid; offset:4; size:4; signed:1;
-
- field:unsigned long call_site; offset:8; size:8; signed:0;
- field:const void * ptr; offset:16; size:8; signed:0;
- field:size_t bytes_req; offset:24; size:8; signed:0;
- field:size_t bytes_alloc; offset:32; size:8; signed:0;
- field:gfp_t gfp_flags; offset:40; size:4; signed:0;
-
- We'll start by creating a hist trigger that generates a simple table
- that lists the total number of bytes requested for each function in
- the kernel that made one or more calls to kmalloc:
-
- # echo 'hist:key=call_site:val=bytes_req' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- This tells the tracing system to create a 'hist' trigger using the
- call_site field of the kmalloc event as the key for the table, which
- just means that each unique call_site address will have an entry
- created for it in the table. The 'val=bytes_req' parameter tells
- the hist trigger that for each unique entry (call_site) in the
- table, it should keep a running total of the number of bytes
- requested by that call_site.
-
- We'll let it run for awhile and then dump the contents of the 'hist'
- file in the kmalloc event's subdirectory (for readability, a number
- of entries have been omitted):
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
- { call_site: 18446744072106379007 } hitcount: 1 bytes_req: 176
- { call_site: 18446744071579557049 } hitcount: 1 bytes_req: 1024
- { call_site: 18446744071580608289 } hitcount: 1 bytes_req: 16384
- { call_site: 18446744071581827654 } hitcount: 1 bytes_req: 24
- { call_site: 18446744071580700980 } hitcount: 1 bytes_req: 8
- { call_site: 18446744071579359876 } hitcount: 1 bytes_req: 152
- { call_site: 18446744071580795365 } hitcount: 3 bytes_req: 144
- { call_site: 18446744071581303129 } hitcount: 3 bytes_req: 144
- { call_site: 18446744071580713234 } hitcount: 4 bytes_req: 2560
- { call_site: 18446744071580933750 } hitcount: 4 bytes_req: 736
- .
- .
- .
- { call_site: 18446744072106047046 } hitcount: 69 bytes_req: 5576
- { call_site: 18446744071582116407 } hitcount: 73 bytes_req: 2336
- { call_site: 18446744072106054684 } hitcount: 136 bytes_req: 140504
- { call_site: 18446744072106224230 } hitcount: 136 bytes_req: 19584
- { call_site: 18446744072106078074 } hitcount: 153 bytes_req: 2448
- { call_site: 18446744072106062406 } hitcount: 153 bytes_req: 36720
- { call_site: 18446744071582507929 } hitcount: 153 bytes_req: 37088
- { call_site: 18446744072102520590 } hitcount: 273 bytes_req: 10920
- { call_site: 18446744071582143559 } hitcount: 358 bytes_req: 716
- { call_site: 18446744072106465852 } hitcount: 417 bytes_req: 56712
- { call_site: 18446744072102523378 } hitcount: 485 bytes_req: 27160
- { call_site: 18446744072099568646 } hitcount: 1676 bytes_req: 33520
-
- Totals:
- Hits: 4610
- Entries: 45
- Dropped: 0
-
- The output displays a line for each entry, beginning with the key
- specified in the trigger, followed by the value(s) also specified in
- the trigger. At the beginning of the output is a line that displays
- the trigger info, which can also be displayed by reading the
- 'trigger' file:
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
- hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
-
- At the end of the output are a few lines that display the overall
- totals for the run. The 'Hits' field shows the total number of
- times the event trigger was hit, the 'Entries' field shows the total
- number of used entries in the hash table, and the 'Dropped' field
- shows the number of hits that were dropped because the number of
- used entries for the run exceeded the maximum number of entries
- allowed for the table (normally 0, but if not a hint that you may
- want to increase the size of the table using the 'size' parameter).
-
- Notice in the above output that there's an extra field, 'hitcount',
- which wasn't specified in the trigger. Also notice that in the
- trigger info output, there's a parameter, 'sort=hitcount', which
- wasn't specified in the trigger either. The reason for that is that
- every trigger implicitly keeps a count of the total number of hits
- attributed to a given entry, called the 'hitcount'. That hitcount
- information is explicitly displayed in the output, and in the
- absence of a user-specified sort parameter, is used as the default
- sort field.
-
- The value 'hitcount' can be used in place of an explicit value in
- the 'values' parameter if you don't really need to have any
- particular field summed and are mainly interested in hit
- frequencies.
-
- To turn the hist trigger off, simply call up the trigger in the
- command history and re-execute it with a '!' prepended:
-
- # echo '!hist:key=call_site:val=bytes_req' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- Finally, notice that the call_site as displayed in the output above
- isn't really very useful. It's an address, but normally addresses
- are displayed in hex. To have a numeric field displayed as a hex
- value, simply append '.hex' to the field name in the trigger:
-
- # echo 'hist:key=call_site.hex:val=bytes_req' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
-
- { call_site: ffffffffa026b291 } hitcount: 1 bytes_req: 433
- { call_site: ffffffffa07186ff } hitcount: 1 bytes_req: 176
- { call_site: ffffffff811ae721 } hitcount: 1 bytes_req: 16384
- { call_site: ffffffff811c5134 } hitcount: 1 bytes_req: 8
- { call_site: ffffffffa04a9ebb } hitcount: 1 bytes_req: 511
- { call_site: ffffffff8122e0a6 } hitcount: 1 bytes_req: 12
- { call_site: ffffffff8107da84 } hitcount: 1 bytes_req: 152
- { call_site: ffffffff812d8246 } hitcount: 1 bytes_req: 24
- { call_site: ffffffff811dc1e5 } hitcount: 3 bytes_req: 144
- { call_site: ffffffffa02515e8 } hitcount: 3 bytes_req: 648
- { call_site: ffffffff81258159 } hitcount: 3 bytes_req: 144
- { call_site: ffffffff811c80f4 } hitcount: 4 bytes_req: 544
- .
- .
- .
- { call_site: ffffffffa06c7646 } hitcount: 106 bytes_req: 8024
- { call_site: ffffffffa06cb246 } hitcount: 132 bytes_req: 31680
- { call_site: ffffffffa06cef7a } hitcount: 132 bytes_req: 2112
- { call_site: ffffffff8137e399 } hitcount: 132 bytes_req: 23232
- { call_site: ffffffffa06c941c } hitcount: 185 bytes_req: 171360
- { call_site: ffffffffa06f2a66 } hitcount: 185 bytes_req: 26640
- { call_site: ffffffffa036a70e } hitcount: 265 bytes_req: 10600
- { call_site: ffffffff81325447 } hitcount: 292 bytes_req: 584
- { call_site: ffffffffa072da3c } hitcount: 446 bytes_req: 60656
- { call_site: ffffffffa036b1f2 } hitcount: 526 bytes_req: 29456
- { call_site: ffffffffa0099c06 } hitcount: 1780 bytes_req: 35600
-
- Totals:
- Hits: 4775
- Entries: 46
- Dropped: 0
-
- Even that's only marginally more useful - while hex values do look
- more like addresses, what users are typically more interested in
- when looking at text addresses are the corresponding symbols
- instead. To have an address displayed as symbolic value instead,
- simply append '.sym' or '.sym-offset' to the field name in the
- trigger:
-
- # echo 'hist:key=call_site.sym:val=bytes_req' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
-
- { call_site: [ffffffff810adcb9] syslog_print_all } hitcount: 1 bytes_req: 1024
- { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8
- { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7
- { call_site: [ffffffff8154acbe] usb_alloc_urb } hitcount: 1 bytes_req: 192
- { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7
- { call_site: [ffffffff811e3a25] __seq_open_private } hitcount: 1 bytes_req: 40
- { call_site: [ffffffff8109524a] alloc_fair_sched_group } hitcount: 2 bytes_req: 128
- { call_site: [ffffffff811febd5] fsnotify_alloc_group } hitcount: 2 bytes_req: 528
- { call_site: [ffffffff81440f58] __tty_buffer_request_room } hitcount: 2 bytes_req: 2624
- { call_site: [ffffffff81200ba6] inotify_new_group } hitcount: 2 bytes_req: 96
- { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211] } hitcount: 2 bytes_req: 464
- { call_site: [ffffffff81672406] tcp_get_metrics } hitcount: 2 bytes_req: 304
- { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128
- { call_site: [ffffffff81089b05] sched_create_group } hitcount: 2 bytes_req: 1424
- .
- .
- .
- { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 1185 bytes_req: 123240
- { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm] } hitcount: 1185 bytes_req: 104280
- { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 1402 bytes_req: 190672
- { call_site: [ffffffff812891ca] ext4_find_extent } hitcount: 1518 bytes_req: 146208
- { call_site: [ffffffffa029070e] drm_vma_node_allow [drm] } hitcount: 1746 bytes_req: 69840
- { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 2021 bytes_req: 792312
- { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 2592 bytes_req: 145152
- { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 2629 bytes_req: 378576
- { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 2629 bytes_req: 3783248
- { call_site: [ffffffff81325607] apparmor_file_alloc_security } hitcount: 5192 bytes_req: 10384
- { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 5529 bytes_req: 110584
- { call_site: [ffffffff8131ebf7] aa_alloc_task_context } hitcount: 21943 bytes_req: 702176
- { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 55759 bytes_req: 5074265
-
- Totals:
- Hits: 109928
- Entries: 71
- Dropped: 0
-
- Because the default sort key above is 'hitcount', the above shows a
- the list of call_sites by increasing hitcount, so that at the bottom
- we see the functions that made the most kmalloc calls during the
- run. If instead we we wanted to see the top kmalloc callers in
- terms of the number of bytes requested rather than the number of
- calls, and we wanted the top caller to appear at the top, we can use
- the 'sort' parameter, along with the 'descending' modifier:
-
- # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
- { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 2186 bytes_req: 3397464
- { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 1790 bytes_req: 712176
- { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 8132 bytes_req: 513135
- { call_site: [ffffffff811e2a1b] seq_buf_alloc } hitcount: 106 bytes_req: 440128
- { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 2186 bytes_req: 314784
- { call_site: [ffffffff812891ca] ext4_find_extent } hitcount: 2174 bytes_req: 208992
- { call_site: [ffffffff811ae8e1] __kmalloc } hitcount: 8 bytes_req: 131072
- { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 859 bytes_req: 116824
- { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 1834 bytes_req: 102704
- { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 972 bytes_req: 101088
- { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm] } hitcount: 972 bytes_req: 85536
- { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 3333 bytes_req: 66664
- { call_site: [ffffffff8137e559] sg_kmalloc } hitcount: 209 bytes_req: 61632
- .
- .
- .
- { call_site: [ffffffff81095225] alloc_fair_sched_group } hitcount: 2 bytes_req: 128
- { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128
- { call_site: [ffffffff812d8406] copy_semundo } hitcount: 2 bytes_req: 48
- { call_site: [ffffffff81200ba6] inotify_new_group } hitcount: 1 bytes_req: 48
- { call_site: [ffffffffa027121a] drm_getmagic [drm] } hitcount: 1 bytes_req: 48
- { call_site: [ffffffff811e3a25] __seq_open_private } hitcount: 1 bytes_req: 40
- { call_site: [ffffffff811c52f4] bprm_change_interp } hitcount: 2 bytes_req: 16
- { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8
- { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7
- { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7
-
- Totals:
- Hits: 32133
- Entries: 81
- Dropped: 0
-
- To display the offset and size information in addition to the symbol
- name, just use 'sym-offset' instead:
-
- # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
-
- { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915] } hitcount: 4569 bytes_req: 3163720
- { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915] } hitcount: 4569 bytes_req: 657936
- { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915] } hitcount: 1519 bytes_req: 472936
- { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915] } hitcount: 3050 bytes_req: 211832
- { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50 } hitcount: 34 bytes_req: 148384
- { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915] } hitcount: 1385 bytes_req: 144040
- { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0 } hitcount: 8 bytes_req: 131072
- { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm] } hitcount: 1385 bytes_req: 121880
- { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm] } hitcount: 1848 bytes_req: 103488
- { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915] } hitcount: 461 bytes_req: 62696
- { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm] } hitcount: 1541 bytes_req: 61640
- { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0 } hitcount: 57 bytes_req: 57456
- .
- .
- .
- { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0 } hitcount: 2 bytes_req: 128
- { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm] } hitcount: 3 bytes_req: 96
- { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0 } hitcount: 8 bytes_req: 96
- { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650 } hitcount: 3 bytes_req: 84
- { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110 } hitcount: 1 bytes_req: 8
- { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid] } hitcount: 1 bytes_req: 7
- { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid] } hitcount: 1 bytes_req: 7
-
- Totals:
- Hits: 26098
- Entries: 64
- Dropped: 0
-
- We can also add multiple fields to the 'values' parameter. For
- example, we might want to see the total number of bytes allocated
- alongside bytes requested, and display the result sorted by bytes
- allocated in a descending order:
-
- # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
-
- { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 7403 bytes_req: 4084360 bytes_alloc: 5958016
- { call_site: [ffffffff811e2a1b] seq_buf_alloc } hitcount: 541 bytes_req: 2213968 bytes_alloc: 2228224
- { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 7404 bytes_req: 1066176 bytes_alloc: 1421568
- { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 1565 bytes_req: 557368 bytes_alloc: 1037760
- { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 9557 bytes_req: 595778 bytes_alloc: 695744
- { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 5839 bytes_req: 430680 bytes_alloc: 470400
- { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 2388 bytes_req: 324768 bytes_alloc: 458496
- { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 3911 bytes_req: 219016 bytes_alloc: 250304
- { call_site: [ffffffff815f8d7b] sk_prot_alloc } hitcount: 235 bytes_req: 236880 bytes_alloc: 240640
- { call_site: [ffffffff8137e559] sg_kmalloc } hitcount: 557 bytes_req: 169024 bytes_alloc: 221760
- { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 9378 bytes_req: 187548 bytes_alloc: 206312
- { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 1519 bytes_req: 157976 bytes_alloc: 194432
- .
- .
- .
- { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach } hitcount: 2 bytes_req: 144 bytes_alloc: 192
- { call_site: [ffffffff81097ee8] alloc_rt_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
- { call_site: [ffffffff8109524a] alloc_fair_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
- { call_site: [ffffffff81095225] alloc_fair_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
- { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
- { call_site: [ffffffff81213e80] load_elf_binary } hitcount: 3 bytes_req: 84 bytes_alloc: 96
- { call_site: [ffffffff81079a2e] kthread_create_on_node } hitcount: 1 bytes_req: 56 bytes_alloc: 64
- { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7 bytes_alloc: 8
- { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8 bytes_alloc: 8
- { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7 bytes_alloc: 8
-
- Totals:
- Hits: 66598
- Entries: 65
- Dropped: 0
-
- Finally, to finish off our kmalloc example, instead of simply having
- the hist trigger display symbolic call_sites, we can have the hist
- trigger additionally display the complete set of kernel stack traces
- that led to each call_site. To do that, we simply use the special
- value 'stacktrace' for the key parameter:
-
- # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
- /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
-
- The above trigger will use the kernel stack trace in effect when an
- event is triggered as the key for the hash table. This allows the
- enumeration of every kernel callpath that led up to a particular
- event, along with a running total of any of the event fields for
- that event. Here we tally bytes requested and bytes allocated for
- every callpath in the system that led up to a kmalloc (in this case
- every callpath to a kmalloc for a kernel compile):
-
- # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
- # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
-
- { stacktrace:
- __kmalloc_track_caller+0x10b/0x1a0
- kmemdup+0x20/0x50
- hidraw_report_event+0x8a/0x120 [hid]
- hid_report_raw_event+0x3ea/0x440 [hid]
- hid_input_report+0x112/0x190 [hid]
- hid_irq_in+0xc2/0x260 [usbhid]
- __usb_hcd_giveback_urb+0x72/0x120
- usb_giveback_urb_bh+0x9e/0xe0
- tasklet_hi_action+0xf8/0x100
- __do_softirq+0x114/0x2c0
- irq_exit+0xa5/0xb0
- do_IRQ+0x5a/0xf0
- ret_from_intr+0x0/0x30
- cpuidle_enter+0x17/0x20
- cpu_startup_entry+0x315/0x3e0
- rest_init+0x7c/0x80
- } hitcount: 3 bytes_req: 21 bytes_alloc: 24
- { stacktrace:
- __kmalloc_track_caller+0x10b/0x1a0
- kmemdup+0x20/0x50
- hidraw_report_event+0x8a/0x120 [hid]
- hid_report_raw_event+0x3ea/0x440 [hid]
- hid_input_report+0x112/0x190 [hid]
- hid_irq_in+0xc2/0x260 [usbhid]
- __usb_hcd_giveback_urb+0x72/0x120
- usb_giveback_urb_bh+0x9e/0xe0
- tasklet_hi_action+0xf8/0x100
- __do_softirq+0x114/0x2c0
- irq_exit+0xa5/0xb0
- do_IRQ+0x5a/0xf0
- ret_from_intr+0x0/0x30
- } hitcount: 3 bytes_req: 21 bytes_alloc: 24
- { stacktrace:
- kmem_cache_alloc_trace+0xeb/0x150
- aa_alloc_task_context+0x27/0x40
- apparmor_cred_prepare+0x1f/0x50
- security_prepare_creds+0x16/0x20
- prepare_creds+0xdf/0x1a0
- SyS_capset+0xb5/0x200
- system_call_fastpath+0x12/0x6a
- } hitcount: 1 bytes_req: 32 bytes_alloc: 32
- .
- .
- .
- { stacktrace:
- __kmalloc+0x11b/0x1b0
- i915_gem_execbuffer2+0x6c/0x2c0 [i915]
- drm_ioctl+0x349/0x670 [drm]
- do_vfs_ioctl+0x2f0/0x4f0
- SyS_ioctl+0x81/0xa0
- system_call_fastpath+0x12/0x6a
- } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808
- { stacktrace:
- __kmalloc+0x11b/0x1b0
- load_elf_phdrs+0x76/0xa0
- load_elf_binary+0x102/0x1650
- search_binary_handler+0x97/0x1d0
- do_execveat_common.isra.34+0x551/0x6e0
- SyS_execve+0x3a/0x50
- return_from_execve+0x0/0x23
- } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048
- { stacktrace:
- kmem_cache_alloc_trace+0xeb/0x150
- apparmor_file_alloc_security+0x27/0x40
- security_file_alloc+0x16/0x20
- get_empty_filp+0x93/0x1c0
- path_openat+0x31/0x5f0
- do_filp_open+0x3a/0x90
- do_sys_open+0x128/0x220
- SyS_open+0x1e/0x20
- system_call_fastpath+0x12/0x6a
- } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376
- { stacktrace:
- __kmalloc+0x11b/0x1b0
- seq_buf_alloc+0x1b/0x50
- seq_read+0x2cc/0x370
- proc_reg_read+0x3d/0x80
- __vfs_read+0x28/0xe0
- vfs_read+0x86/0x140
- SyS_read+0x46/0xb0
- system_call_fastpath+0x12/0x6a
- } hitcount: 19133 bytes_req: 78368768 bytes_alloc: 78368768
-
- Totals:
- Hits: 6085872
- Entries: 253
- Dropped: 0
-
- If you key a hist trigger on common_pid, in order for example to
- gather and display sorted totals for each process, you can use the
- special .execname modifier to display the executable names for the
- processes in the table rather than raw pids. The example below
- keeps a per-process sum of total bytes read:
-
- # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
- /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
-
- # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
- # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
-
- { common_pid: gnome-terminal [ 3196] } hitcount: 280 count: 1093512
- { common_pid: Xorg [ 1309] } hitcount: 525 count: 256640
- { common_pid: compiz [ 2889] } hitcount: 59 count: 254400
- { common_pid: bash [ 8710] } hitcount: 3 count: 66369
- { common_pid: dbus-daemon-lau [ 8703] } hitcount: 49 count: 47739
- { common_pid: irqbalance [ 1252] } hitcount: 27 count: 27648
- { common_pid: 01ifupdown [ 8705] } hitcount: 3 count: 17216
- { common_pid: dbus-daemon [ 772] } hitcount: 10 count: 12396
- { common_pid: Socket Thread [ 8342] } hitcount: 11 count: 11264
- { common_pid: nm-dhcp-client. [ 8701] } hitcount: 6 count: 7424
- { common_pid: gmain [ 1315] } hitcount: 18 count: 6336
- .
- .
- .
- { common_pid: postgres [ 1892] } hitcount: 2 count: 32
- { common_pid: postgres [ 1891] } hitcount: 2 count: 32
- { common_pid: gmain [ 8704] } hitcount: 2 count: 32
- { common_pid: upstart-dbus-br [ 2740] } hitcount: 21 count: 21
- { common_pid: nm-dispatcher.a [ 8696] } hitcount: 1 count: 16
- { common_pid: indicator-datet [ 2904] } hitcount: 1 count: 16
- { common_pid: gdbus [ 2998] } hitcount: 1 count: 16
- { common_pid: rtkit-daemon [ 2052] } hitcount: 1 count: 8
- { common_pid: init [ 1] } hitcount: 2 count: 2
-
- Totals:
- Hits: 2116
- Entries: 51
- Dropped: 0
-
- Similarly, if you key a hist trigger on syscall id, for example to
- gather and display a list of systemwide syscall hits, you can use
- the special .syscall modifier to display the syscall names rather
- than raw ids. The example below keeps a running total of syscall
- counts for the system during the run:
-
- # echo 'hist:key=id.syscall:val=hitcount' > \
- /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
- # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
- # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
-
- { id: sys_fsync [ 74] } hitcount: 1
- { id: sys_newuname [ 63] } hitcount: 1
- { id: sys_prctl [157] } hitcount: 1
- { id: sys_statfs [137] } hitcount: 1
- { id: sys_symlink [ 88] } hitcount: 1
- { id: sys_sendmmsg [307] } hitcount: 1
- { id: sys_semctl [ 66] } hitcount: 1
- { id: sys_readlink [ 89] } hitcount: 3
- { id: sys_bind [ 49] } hitcount: 3
- { id: sys_getsockname [ 51] } hitcount: 3
- { id: sys_unlink [ 87] } hitcount: 3
- { id: sys_rename [ 82] } hitcount: 4
- { id: unknown_syscall [ 58] } hitcount: 4
- { id: sys_connect [ 42] } hitcount: 4
- { id: sys_getpid [ 39] } hitcount: 4
- .
- .
- .
- { id: sys_rt_sigprocmask [ 14] } hitcount: 952
- { id: sys_futex [202] } hitcount: 1534
- { id: sys_write [ 1] } hitcount: 2689
- { id: sys_setitimer [ 38] } hitcount: 2797
- { id: sys_read [ 0] } hitcount: 3202
- { id: sys_select [ 23] } hitcount: 3773
- { id: sys_writev [ 20] } hitcount: 4531
- { id: sys_poll [ 7] } hitcount: 8314
- { id: sys_recvmsg [ 47] } hitcount: 13738
- { id: sys_ioctl [ 16] } hitcount: 21843
-
- Totals:
- Hits: 67612
- Entries: 72
- Dropped: 0
-
- The syscall counts above provide a rough overall picture of system
- call activity on the system; we can see for example that the most
- popular system call on this system was the 'sys_ioctl' system call.
-
- We can use 'compound' keys to refine that number and provide some
- further insight as to which processes exactly contribute to the
- overall ioctl count.
-
- The command below keeps a hitcount for every unique combination of
- system call id and pid - the end result is essentially a table
- that keeps a per-pid sum of system call hits. The results are
- sorted using the system call id as the primary key, and the
- hitcount sum as the secondary key:
-
- # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
- /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
- # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
- # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
-
- { id: sys_read [ 0], common_pid: rtkit-daemon [ 1877] } hitcount: 1
- { id: sys_read [ 0], common_pid: gdbus [ 2976] } hitcount: 1
- { id: sys_read [ 0], common_pid: console-kit-dae [ 3400] } hitcount: 1
- { id: sys_read [ 0], common_pid: postgres [ 1865] } hitcount: 1
- { id: sys_read [ 0], common_pid: deja-dup-monito [ 3543] } hitcount: 2
- { id: sys_read [ 0], common_pid: NetworkManager [ 890] } hitcount: 2
- { id: sys_read [ 0], common_pid: evolution-calen [ 3048] } hitcount: 2
- { id: sys_read [ 0], common_pid: postgres [ 1864] } hitcount: 2
- { id: sys_read [ 0], common_pid: nm-applet [ 3022] } hitcount: 2
- { id: sys_read [ 0], common_pid: whoopsie [ 1212] } hitcount: 2
- .
- .
- .
- { id: sys_ioctl [ 16], common_pid: bash [ 8479] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: bash [ 3472] } hitcount: 12
- { id: sys_ioctl [ 16], common_pid: gnome-terminal [ 3199] } hitcount: 16
- { id: sys_ioctl [ 16], common_pid: Xorg [ 1267] } hitcount: 1808
- { id: sys_ioctl [ 16], common_pid: compiz [ 2994] } hitcount: 5580
- .
- .
- .
- { id: sys_waitid [247], common_pid: upstart-dbus-br [ 2690] } hitcount: 3
- { id: sys_waitid [247], common_pid: upstart-dbus-br [ 2688] } hitcount: 16
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 975] } hitcount: 2
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 3204] } hitcount: 4
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 2888] } hitcount: 4
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 3003] } hitcount: 4
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 2873] } hitcount: 4
- { id: sys_inotify_add_watch [254], common_pid: gmain [ 3196] } hitcount: 6
- { id: sys_openat [257], common_pid: java [ 2623] } hitcount: 2
- { id: sys_eventfd2 [290], common_pid: ibus-ui-gtk3 [ 2760] } hitcount: 4
- { id: sys_eventfd2 [290], common_pid: compiz [ 2994] } hitcount: 6
-
- Totals:
- Hits: 31536
- Entries: 323
- Dropped: 0
-
- The above list does give us a breakdown of the ioctl syscall by
- pid, but it also gives us quite a bit more than that, which we
- don't really care about at the moment. Since we know the syscall
- id for sys_ioctl (16, displayed next to the sys_ioctl name), we
- can use that to filter out all the other syscalls:
-
- # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
- /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
-
- # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
- # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
-
- { id: sys_ioctl [ 16], common_pid: gmain [ 2769] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: evolution-addre [ 8571] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: gmain [ 3003] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: gmain [ 2781] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: gmain [ 2829] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: bash [ 8726] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: bash [ 8508] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: gmain [ 2970] } hitcount: 1
- { id: sys_ioctl [ 16], common_pid: gmain [ 2768] } hitcount: 1
- .
- .
- .
- { id: sys_ioctl [ 16], common_pid: pool [ 8559] } hitcount: 45
- { id: sys_ioctl [ 16], common_pid: pool [ 8555] } hitcount: 48
- { id: sys_ioctl [ 16], common_pid: pool [ 8551] } hitcount: 48
- { id: sys_ioctl [ 16], common_pid: avahi-daemon [ 896] } hitcount: 66
- { id: sys_ioctl [ 16], common_pid: Xorg [ 1267] } hitcount: 26674
- { id: sys_ioctl [ 16], common_pid: compiz [ 2994] } hitcount: 73443
-
- Totals:
- Hits: 101162
- Entries: 103
- Dropped: 0
-
- The above output shows that 'compiz' and 'Xorg' are far and away
- the heaviest ioctl callers (which might lead to questions about
- whether they really need to be making all those calls and to
- possible avenues for further investigation.)
-
- The compound key examples used a key and a sum value (hitcount) to
- sort the output, but we can just as easily use two keys instead.
- Here's an example where we use a compound key composed of the the
- common_pid and size event fields. Sorting with pid as the primary
- key and 'size' as the secondary key allows us to display an
- ordered summary of the recvfrom sizes, with counts, received by
- each process:
-
- # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
- /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
-
- # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
- # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
-
- { common_pid: smbd [ 784], size: 4 } hitcount: 1
- { common_pid: dnsmasq [ 1412], size: 4096 } hitcount: 672
- { common_pid: postgres [ 1796], size: 1000 } hitcount: 6
- { common_pid: postgres [ 1867], size: 1000 } hitcount: 10
- { common_pid: bamfdaemon [ 2787], size: 28 } hitcount: 2
- { common_pid: bamfdaemon [ 2787], size: 14360 } hitcount: 1
- { common_pid: compiz [ 2994], size: 8 } hitcount: 1
- { common_pid: compiz [ 2994], size: 20 } hitcount: 11
- { common_pid: gnome-terminal [ 3199], size: 4 } hitcount: 2
- { common_pid: firefox [ 8817], size: 4 } hitcount: 1
- { common_pid: firefox [ 8817], size: 8 } hitcount: 5
- { common_pid: firefox [ 8817], size: 588 } hitcount: 2
- { common_pid: firefox [ 8817], size: 628 } hitcount: 1
- { common_pid: firefox [ 8817], size: 6944 } hitcount: 1
- { common_pid: firefox [ 8817], size: 408880 } hitcount: 2
- { common_pid: firefox [ 8822], size: 8 } hitcount: 2
- { common_pid: firefox [ 8822], size: 160 } hitcount: 2
- { common_pid: firefox [ 8822], size: 320 } hitcount: 2
- { common_pid: firefox [ 8822], size: 352 } hitcount: 1
- .
- .
- .
- { common_pid: pool [ 8923], size: 1960 } hitcount: 10
- { common_pid: pool [ 8923], size: 2048 } hitcount: 10
- { common_pid: pool [ 8924], size: 1960 } hitcount: 10
- { common_pid: pool [ 8924], size: 2048 } hitcount: 10
- { common_pid: pool [ 8928], size: 1964 } hitcount: 4
- { common_pid: pool [ 8928], size: 1965 } hitcount: 2
- { common_pid: pool [ 8928], size: 2048 } hitcount: 6
- { common_pid: pool [ 8929], size: 1982 } hitcount: 1
- { common_pid: pool [ 8929], size: 2048 } hitcount: 1
-
- Totals:
- Hits: 2016
- Entries: 224
- Dropped: 0
-
- The above example also illustrates the fact that although a compound
- key is treated as a single entity for hashing purposes, the sub-keys
- it's composed of can be accessed independently.
-
- The next example uses a string field as the hash key and
- demonstrates how you can manually pause and continue a hist trigger.
- In this example, we'll aggregate fork counts and don't expect a
- large number of entries in the hash table, so we'll drop it to a
- much smaller number, say 256:
-
- # echo 'hist:key=child_comm:val=hitcount:size=256' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
- # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
- { child_comm: dconf worker } hitcount: 1
- { child_comm: ibus-daemon } hitcount: 1
- { child_comm: whoopsie } hitcount: 1
- { child_comm: smbd } hitcount: 1
- { child_comm: gdbus } hitcount: 1
- { child_comm: kthreadd } hitcount: 1
- { child_comm: dconf worker } hitcount: 1
- { child_comm: evolution-alarm } hitcount: 2
- { child_comm: Socket Thread } hitcount: 2
- { child_comm: postgres } hitcount: 2
- { child_comm: bash } hitcount: 3
- { child_comm: compiz } hitcount: 3
- { child_comm: evolution-sourc } hitcount: 4
- { child_comm: dhclient } hitcount: 4
- { child_comm: pool } hitcount: 5
- { child_comm: nm-dispatcher.a } hitcount: 8
- { child_comm: firefox } hitcount: 8
- { child_comm: dbus-daemon } hitcount: 8
- { child_comm: glib-pacrunner } hitcount: 10
- { child_comm: evolution } hitcount: 23
-
- Totals:
- Hits: 89
- Entries: 20
- Dropped: 0
-
- If we want to pause the hist trigger, we can simply append :pause to
- the command that started the trigger. Notice that the trigger info
- displays as [paused]:
-
- # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
- /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
- # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
-
- { child_comm: dconf worker } hitcount: 1
- { child_comm: kthreadd } hitcount: 1
- { child_comm: dconf worker } hitcount: 1
- { child_comm: gdbus } hitcount: 1
- { child_comm: ibus-daemon } hitcount: 1
- { child_comm: Socket Thread } hitcount: 2
- { child_comm: evolution-alarm } hitcount: 2
- { child_comm: smbd } hitcount: 2
- { child_comm: bash } hitcount: 3
- { child_comm: whoopsie } hitcount: 3
- { child_comm: compiz } hitcount: 3
- { child_comm: evolution-sourc } hitcount: 4
- { child_comm: pool } hitcount: 5
- { child_comm: postgres } hitcount: 6
- { child_comm: firefox } hitcount: 8
- { child_comm: dhclient } hitcount: 10
- { child_comm: emacs } hitcount: 12
- { child_comm: dbus-daemon } hitcount: 20
- { child_comm: nm-dispatcher.a } hitcount: 20
- { child_comm: evolution } hitcount: 35
- { child_comm: glib-pacrunner } hitcount: 59
-
- Totals:
- Hits: 199
- Entries: 21
- Dropped: 0
-
- To manually continue having the trigger aggregate events, append
- :cont instead. Notice that the trigger info displays as [active]
- again, and the data has changed:
-
- # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
- /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
- # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
-
- { child_comm: dconf worker } hitcount: 1
- { child_comm: dconf worker } hitcount: 1
- { child_comm: kthreadd } hitcount: 1
- { child_comm: gdbus } hitcount: 1
- { child_comm: ibus-daemon } hitcount: 1
- { child_comm: Socket Thread } hitcount: 2
- { child_comm: evolution-alarm } hitcount: 2
- { child_comm: smbd } hitcount: 2
- { child_comm: whoopsie } hitcount: 3
- { child_comm: compiz } hitcount: 3
- { child_comm: evolution-sourc } hitcount: 4
- { child_comm: bash } hitcount: 5
- { child_comm: pool } hitcount: 5
- { child_comm: postgres } hitcount: 6
- { child_comm: firefox } hitcount: 8
- { child_comm: dhclient } hitcount: 11
- { child_comm: emacs } hitcount: 12
- { child_comm: dbus-daemon } hitcount: 22
- { child_comm: nm-dispatcher.a } hitcount: 22
- { child_comm: evolution } hitcount: 35
- { child_comm: glib-pacrunner } hitcount: 59
-
- Totals:
- Hits: 206
- Entries: 21
- Dropped: 0
-
- The previous example showed how to start and stop a hist trigger by
- appending 'pause' and 'continue' to the hist trigger command. A
- hist trigger can also be started in a paused state by initially
- starting the trigger with ':pause' appended. This allows you to
- start the trigger only when you're ready to start collecting data
- and not before. For example, you could start the trigger in a
- paused state, then unpause it and do something you want to measure,
- then pause the trigger again when done.
-
- Of course, doing this manually can be difficult and error-prone, but
- it is possible to automatically start and stop a hist trigger based
- on some condition, via the enable_hist and disable_hist triggers.
-
- For example, suppose we wanted to take a look at the relative
- weights in terms of skb length for each callpath that leads to a
- netif_receieve_skb event when downloading a decent-sized file using
- wget.
-
- First we set up an initially paused stacktrace trigger on the
- netif_receive_skb event:
-
- # echo 'hist:key=stacktrace:vals=len:pause' > \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
- Next, we set up an 'enable_hist' trigger on the sched_process_exec
- event, with an 'if filename==/usr/bin/wget' filter. The effect of
- this new trigger is that it will 'unpause' the hist trigger we just
- set up on netif_receive_skb if and only if it sees a
- sched_process_exec event with a filename of '/usr/bin/wget'. When
- that happens, all netif_receive_skb events are aggregated into a
- hash table keyed on stacktrace:
-
- # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
- The aggregation continues until the netif_receive_skb is paused
- again, which is what the following disable_hist event does by
- creating a similar setup on the sched_process_exit event, using the
- filter 'comm==wget':
-
- # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
- Whenever a process exits and the comm field of the disable_hist
- trigger filter matches 'comm==wget', the netif_receive_skb hist
- trigger is disabled.
-
- The overall effect is that netif_receive_skb events are aggregated
- into the hash table for only the duration of the wget. Executing a
- wget command and then listing the 'hist' file will display the
- output generated by the wget command:
-
- $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
- # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
- # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
- { stacktrace:
- __netif_receive_skb_core+0x46d/0x990
- __netif_receive_skb+0x18/0x60
- netif_receive_skb_internal+0x23/0x90
- napi_gro_receive+0xc8/0x100
- ieee80211_deliver_skb+0xd6/0x270 [mac80211]
- ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
- ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
- ieee80211_rx+0x31d/0x900 [mac80211]
- iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
- iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
- iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
- irq_thread_fn+0x20/0x50
- irq_thread+0x11f/0x150
- kthread+0xd2/0xf0
- ret_from_fork+0x42/0x70
- } hitcount: 85 len: 28884
- { stacktrace:
- __netif_receive_skb_core+0x46d/0x990
- __netif_receive_skb+0x18/0x60
- netif_receive_skb_internal+0x23/0x90
- napi_gro_complete+0xa4/0xe0
- dev_gro_receive+0x23a/0x360
- napi_gro_receive+0x30/0x100
- ieee80211_deliver_skb+0xd6/0x270 [mac80211]
- ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
- ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
- ieee80211_rx+0x31d/0x900 [mac80211]
- iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
- iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
- iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
- irq_thread_fn+0x20/0x50
- irq_thread+0x11f/0x150
- kthread+0xd2/0xf0
- } hitcount: 98 len: 664329
- { stacktrace:
- __netif_receive_skb_core+0x46d/0x990
- __netif_receive_skb+0x18/0x60
- process_backlog+0xa8/0x150
- net_rx_action+0x15d/0x340
- __do_softirq+0x114/0x2c0
- do_softirq_own_stack+0x1c/0x30
- do_softirq+0x65/0x70
- __local_bh_enable_ip+0xb5/0xc0
- ip_finish_output+0x1f4/0x840
- ip_output+0x6b/0xc0
- ip_local_out_sk+0x31/0x40
- ip_send_skb+0x1a/0x50
- udp_send_skb+0x173/0x2a0
- udp_sendmsg+0x2bf/0x9f0
- inet_sendmsg+0x64/0xa0
- sock_sendmsg+0x3d/0x50
- } hitcount: 115 len: 13030
- { stacktrace:
- __netif_receive_skb_core+0x46d/0x990
- __netif_receive_skb+0x18/0x60
- netif_receive_skb_internal+0x23/0x90
- napi_gro_complete+0xa4/0xe0
- napi_gro_flush+0x6d/0x90
- iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
- irq_thread_fn+0x20/0x50
- irq_thread+0x11f/0x150
- kthread+0xd2/0xf0
- ret_from_fork+0x42/0x70
- } hitcount: 934 len: 5512212
-
- Totals:
- Hits: 1232
- Entries: 4
- Dropped: 0
-
- The above shows all the netif_receive_skb callpaths and their total
- lengths for the duration of the wget command.
-
- The 'clear' hist trigger param can be used to clear the hash table.
- Suppose we wanted to try another run of the previous example but
- this time also wanted to see the complete list of events that went
- into the histogram. In order to avoid having to set everything up
- again, we can just clear the histogram first:
-
- # echo 'hist:key=stacktrace:vals=len:clear' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
- Just to verify that it is in fact cleared, here's what we now see in
- the hist file:
-
- # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
- # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
-
- Totals:
- Hits: 0
- Entries: 0
- Dropped: 0
-
- Since we want to see the detailed list of every netif_receive_skb
- event occurring during the new run, which are in fact the same
- events being aggregated into the hash table, we add some additional
- 'enable_event' events to the triggering sched_process_exec and
- sched_process_exit events as such:
-
- # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
-
- # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
-
- If you read the trigger files for the sched_process_exec and
- sched_process_exit triggers, you should see two triggers for each:
- one enabling/disabling the hist aggregation and the other
- enabling/disabling the logging of events:
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
- enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
- enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
- enable_event:net:netif_receive_skb:unlimited if comm==wget
- disable_hist:net:netif_receive_skb:unlimited if comm==wget
-
- In other words, whenever either of the sched_process_exec or
- sched_process_exit events is hit and matches 'wget', it enables or
- disables both the histogram and the event log, and what you end up
- with is a hash table and set of events just covering the specified
- duration. Run the wget command again:
-
- $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
-
- Displaying the 'hist' file should show something similar to what you
- saw in the last run, but this time you should also see the
- individual events in the trace file:
-
- # cat /sys/kernel/debug/tracing/trace
-
- # tracer: nop
- #
- # entries-in-buffer/entries-written: 183/1426 #P:4
- #
- # _-----=> irqs-off
- # / _----=> need-resched
- # | / _---=> hardirq/softirq
- # || / _--=> preempt-depth
- # ||| / delay
- # TASK-PID CPU# |||| TIMESTAMP FUNCTION
- # | | | |||| | |
- wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
- wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
- dnsmasq-1382 [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
- dnsmasq-1382 [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
- ##### CPU 2 buffer started ####
- irq/29-iwlwifi-559 [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
- irq/29-iwlwifi-559 [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
- irq/29-iwlwifi-559 [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
- irq/29-iwlwifi-559 [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
- irq/29-iwlwifi-559 [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
- .
- .
- .
-
- The following example demonstrates how multiple hist triggers can be
- attached to a given event. This capability can be useful for
- creating a set of different summaries derived from the same set of
- events, or for comparing the effects of different filters, among
- other things.
-
- # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
- # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
- # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
- # echo 'hist:keys=skbaddr.hex:vals=len' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
- # echo 'hist:keys=len:vals=common_preempt_count' >> \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
-
- The above set of commands create four triggers differing only in
- their filters, along with a completely different though fairly
- nonsensical trigger. Note that in order to append multiple hist
- triggers to the same file, you should use the '>>' operator to
- append them ('>' will also add the new hist trigger, but will remove
- any existing hist triggers beforehand).
-
- Displaying the contents of the 'hist' file for the event shows the
- contents of all five histograms:
-
- # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
-
- # event histogram
- #
- # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
- #
-
- { len: 176 } hitcount: 1 common_preempt_count: 0
- { len: 223 } hitcount: 1 common_preempt_count: 0
- { len: 4854 } hitcount: 1 common_preempt_count: 0
- { len: 395 } hitcount: 1 common_preempt_count: 0
- { len: 177 } hitcount: 1 common_preempt_count: 0
- { len: 446 } hitcount: 1 common_preempt_count: 0
- { len: 1601 } hitcount: 1 common_preempt_count: 0
- .
- .
- .
- { len: 1280 } hitcount: 66 common_preempt_count: 0
- { len: 116 } hitcount: 81 common_preempt_count: 40
- { len: 708 } hitcount: 112 common_preempt_count: 0
- { len: 46 } hitcount: 221 common_preempt_count: 0
- { len: 1264 } hitcount: 458 common_preempt_count: 0
-
- Totals:
- Hits: 1428
- Entries: 147
- Dropped: 0
-
-
- # event histogram
- #
- # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
- #
-
- { skbaddr: ffff8800baee5e00 } hitcount: 1 len: 130
- { skbaddr: ffff88005f3d5600 } hitcount: 1 len: 1280
- { skbaddr: ffff88005f3d4900 } hitcount: 1 len: 1280
- { skbaddr: ffff88009fed6300 } hitcount: 1 len: 115
- { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 115
- { skbaddr: ffff88008cdb1900 } hitcount: 1 len: 46
- { skbaddr: ffff880064b5ef00 } hitcount: 1 len: 118
- { skbaddr: ffff880044e3c700 } hitcount: 1 len: 60
- { skbaddr: ffff880100065900 } hitcount: 1 len: 46
- { skbaddr: ffff8800d46bd500 } hitcount: 1 len: 116
- { skbaddr: ffff88005f3d5f00 } hitcount: 1 len: 1280
- { skbaddr: ffff880100064700 } hitcount: 1 len: 365
- { skbaddr: ffff8800badb6f00 } hitcount: 1 len: 60
- .
- .
- .
- { skbaddr: ffff88009fe0be00 } hitcount: 27 len: 24677
- { skbaddr: ffff88009fe0a400 } hitcount: 27 len: 23052
- { skbaddr: ffff88009fe0b700 } hitcount: 31 len: 25589
- { skbaddr: ffff88009fe0b600 } hitcount: 32 len: 27326
- { skbaddr: ffff88006a462800 } hitcount: 68 len: 71678
- { skbaddr: ffff88006a463700 } hitcount: 70 len: 72678
- { skbaddr: ffff88006a462b00 } hitcount: 71 len: 77589
- { skbaddr: ffff88006a463600 } hitcount: 73 len: 71307
- { skbaddr: ffff88006a462200 } hitcount: 81 len: 81032
-
- Totals:
- Hits: 1451
- Entries: 318
- Dropped: 0
-
-
- # event histogram
- #
- # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
- #
-
-
- Totals:
- Hits: 0
- Entries: 0
- Dropped: 0
-
-
- # event histogram
- #
- # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
- #
-
- { skbaddr: ffff88009fd2c300 } hitcount: 1 len: 7212
- { skbaddr: ffff8800d2bcce00 } hitcount: 1 len: 7212
- { skbaddr: ffff8800d2bcd700 } hitcount: 1 len: 7212
- { skbaddr: ffff8800d2bcda00 } hitcount: 1 len: 21492
- { skbaddr: ffff8800ae2e2d00 } hitcount: 1 len: 7212
- { skbaddr: ffff8800d2bcdb00 } hitcount: 1 len: 7212
- { skbaddr: ffff88006a4df500 } hitcount: 1 len: 4854
- { skbaddr: ffff88008ce47b00 } hitcount: 1 len: 18636
- { skbaddr: ffff8800ae2e2200 } hitcount: 1 len: 12924
- { skbaddr: ffff88005f3e1000 } hitcount: 1 len: 4356
- { skbaddr: ffff8800d2bcdc00 } hitcount: 2 len: 24420
- { skbaddr: ffff8800d2bcc200 } hitcount: 2 len: 12996
-
- Totals:
- Hits: 14
- Entries: 12
- Dropped: 0
-
-
- # event histogram
- #
- # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
- #
-
-
- Totals:
- Hits: 0
- Entries: 0
- Dropped: 0
-
- Named triggers can be used to have triggers share a common set of
- histogram data. This capability is mostly useful for combining the
- output of events generated by tracepoints contained inside inline
- functions, but names can be used in a hist trigger on any event.
- For example, these two triggers when hit will update the same 'len'
- field in the shared 'foo' histogram data:
-
- # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
- /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
- # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
- /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
- You can see that they're updating common histogram data by reading
- each event's hist files at the same time:
-
- # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
- cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
- # event histogram
- #
- # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
- #
-
- { skbaddr: ffff88000ad53500 } hitcount: 1 len: 46
- { skbaddr: ffff8800af5a1500 } hitcount: 1 len: 76
- { skbaddr: ffff8800d62a1900 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bccb00 } hitcount: 1 len: 468
- { skbaddr: ffff8800d3c69900 } hitcount: 1 len: 46
- { skbaddr: ffff88009ff09100 } hitcount: 1 len: 52
- { skbaddr: ffff88010f13ab00 } hitcount: 1 len: 168
- { skbaddr: ffff88006a54f400 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcc500 } hitcount: 1 len: 260
- { skbaddr: ffff880064505000 } hitcount: 1 len: 46
- { skbaddr: ffff8800baf24e00 } hitcount: 1 len: 32
- { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 46
- { skbaddr: ffff8800d3edff00 } hitcount: 1 len: 44
- { skbaddr: ffff88009fe0b400 } hitcount: 1 len: 168
- { skbaddr: ffff8800a1c55a00 } hitcount: 1 len: 40
- { skbaddr: ffff8800d2bcd100 } hitcount: 1 len: 40
- { skbaddr: ffff880064505f00 } hitcount: 1 len: 174
- { skbaddr: ffff8800a8bff200 } hitcount: 1 len: 160
- { skbaddr: ffff880044e3cc00 } hitcount: 1 len: 76
- { skbaddr: ffff8800a8bfe700 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcdc00 } hitcount: 1 len: 32
- { skbaddr: ffff8800a1f64800 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcde00 } hitcount: 1 len: 988
- { skbaddr: ffff88006a5dea00 } hitcount: 1 len: 46
- { skbaddr: ffff88002e37a200 } hitcount: 1 len: 44
- { skbaddr: ffff8800a1f32c00 } hitcount: 2 len: 676
- { skbaddr: ffff88000ad52600 } hitcount: 2 len: 107
- { skbaddr: ffff8800a1f91e00 } hitcount: 2 len: 92
- { skbaddr: ffff8800af5a0200 } hitcount: 2 len: 142
- { skbaddr: ffff8800d2bcc600 } hitcount: 2 len: 220
- { skbaddr: ffff8800ba36f500 } hitcount: 2 len: 92
- { skbaddr: ffff8800d021f800 } hitcount: 2 len: 92
- { skbaddr: ffff8800a1f33600 } hitcount: 2 len: 675
- { skbaddr: ffff8800a8bfff00 } hitcount: 3 len: 138
- { skbaddr: ffff8800d62a1300 } hitcount: 3 len: 138
- { skbaddr: ffff88002e37a100 } hitcount: 4 len: 184
- { skbaddr: ffff880064504400 } hitcount: 4 len: 184
- { skbaddr: ffff8800a8bfec00 } hitcount: 4 len: 184
- { skbaddr: ffff88000ad53700 } hitcount: 5 len: 230
- { skbaddr: ffff8800d2bcdb00 } hitcount: 5 len: 196
- { skbaddr: ffff8800a1f90000 } hitcount: 6 len: 276
- { skbaddr: ffff88006a54f900 } hitcount: 6 len: 276
-
- Totals:
- Hits: 81
- Entries: 42
- Dropped: 0
- # event histogram
- #
- # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
- #
-
- { skbaddr: ffff88000ad53500 } hitcount: 1 len: 46
- { skbaddr: ffff8800af5a1500 } hitcount: 1 len: 76
- { skbaddr: ffff8800d62a1900 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bccb00 } hitcount: 1 len: 468
- { skbaddr: ffff8800d3c69900 } hitcount: 1 len: 46
- { skbaddr: ffff88009ff09100 } hitcount: 1 len: 52
- { skbaddr: ffff88010f13ab00 } hitcount: 1 len: 168
- { skbaddr: ffff88006a54f400 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcc500 } hitcount: 1 len: 260
- { skbaddr: ffff880064505000 } hitcount: 1 len: 46
- { skbaddr: ffff8800baf24e00 } hitcount: 1 len: 32
- { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 46
- { skbaddr: ffff8800d3edff00 } hitcount: 1 len: 44
- { skbaddr: ffff88009fe0b400 } hitcount: 1 len: 168
- { skbaddr: ffff8800a1c55a00 } hitcount: 1 len: 40
- { skbaddr: ffff8800d2bcd100 } hitcount: 1 len: 40
- { skbaddr: ffff880064505f00 } hitcount: 1 len: 174
- { skbaddr: ffff8800a8bff200 } hitcount: 1 len: 160
- { skbaddr: ffff880044e3cc00 } hitcount: 1 len: 76
- { skbaddr: ffff8800a8bfe700 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcdc00 } hitcount: 1 len: 32
- { skbaddr: ffff8800a1f64800 } hitcount: 1 len: 46
- { skbaddr: ffff8800d2bcde00 } hitcount: 1 len: 988
- { skbaddr: ffff88006a5dea00 } hitcount: 1 len: 46
- { skbaddr: ffff88002e37a200 } hitcount: 1 len: 44
- { skbaddr: ffff8800a1f32c00 } hitcount: 2 len: 676
- { skbaddr: ffff88000ad52600 } hitcount: 2 len: 107
- { skbaddr: ffff8800a1f91e00 } hitcount: 2 len: 92
- { skbaddr: ffff8800af5a0200 } hitcount: 2 len: 142
- { skbaddr: ffff8800d2bcc600 } hitcount: 2 len: 220
- { skbaddr: ffff8800ba36f500 } hitcount: 2 len: 92
- { skbaddr: ffff8800d021f800 } hitcount: 2 len: 92
- { skbaddr: ffff8800a1f33600 } hitcount: 2 len: 675
- { skbaddr: ffff8800a8bfff00 } hitcount: 3 len: 138
- { skbaddr: ffff8800d62a1300 } hitcount: 3 len: 138
- { skbaddr: ffff88002e37a100 } hitcount: 4 len: 184
- { skbaddr: ffff880064504400 } hitcount: 4 len: 184
- { skbaddr: ffff8800a8bfec00 } hitcount: 4 len: 184
- { skbaddr: ffff88000ad53700 } hitcount: 5 len: 230
- { skbaddr: ffff8800d2bcdb00 } hitcount: 5 len: 196
- { skbaddr: ffff8800a1f90000 } hitcount: 6 len: 276
- { skbaddr: ffff88006a54f900 } hitcount: 6 len: 276
-
- Totals:
- Hits: 81
- Entries: 42
- Dropped: 0
-
- And here's an example that shows how to combine histogram data from
- any two events even if they don't share any 'compatible' fields
- other than 'hitcount' and 'stacktrace'. These commands create a
- couple of triggers named 'bar' using those fields:
-
- # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
- /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
- # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
- /sys/kernel/debug/tracing/events/net/netif_rx/trigger
-
- And displaying the output of either shows some interesting if
- somewhat confusing output:
-
- # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
- # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
-
- # event histogram
- #
- # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
- #
-
- { stacktrace:
- _do_fork+0x18e/0x330
- kernel_thread+0x29/0x30
- kthreadd+0x154/0x1b0
- ret_from_fork+0x3f/0x70
- } hitcount: 1
- { stacktrace:
- netif_rx_internal+0xb2/0xd0
- netif_rx_ni+0x20/0x70
- dev_loopback_xmit+0xaa/0xd0
- ip_mc_output+0x126/0x240
- ip_local_out_sk+0x31/0x40
- igmp_send_report+0x1e9/0x230
- igmp_timer_expire+0xe9/0x120
- call_timer_fn+0x39/0xf0
- run_timer_softirq+0x1e1/0x290
- __do_softirq+0xfd/0x290
- irq_exit+0x98/0xb0
- smp_apic_timer_interrupt+0x4a/0x60
- apic_timer_interrupt+0x6d/0x80
- cpuidle_enter+0x17/0x20
- call_cpuidle+0x3b/0x60
- cpu_startup_entry+0x22d/0x310
- } hitcount: 1
- { stacktrace:
- netif_rx_internal+0xb2/0xd0
- netif_rx_ni+0x20/0x70
- dev_loopback_xmit+0xaa/0xd0
- ip_mc_output+0x17f/0x240
- ip_local_out_sk+0x31/0x40
- ip_send_skb+0x1a/0x50
- udp_send_skb+0x13e/0x270
- udp_sendmsg+0x2bf/0x980
- inet_sendmsg+0x67/0xa0
- sock_sendmsg+0x38/0x50
- SYSC_sendto+0xef/0x170
- SyS_sendto+0xe/0x10
- entry_SYSCALL_64_fastpath+0x12/0x6a
- } hitcount: 2
- { stacktrace:
- netif_rx_internal+0xb2/0xd0
- netif_rx+0x1c/0x60
- loopback_xmit+0x6c/0xb0
- dev_hard_start_xmit+0x219/0x3a0
- __dev_queue_xmit+0x415/0x4f0
- dev_queue_xmit_sk+0x13/0x20
- ip_finish_output2+0x237/0x340
- ip_finish_output+0x113/0x1d0
- ip_output+0x66/0xc0
- ip_local_out_sk+0x31/0x40
- ip_send_skb+0x1a/0x50
- udp_send_skb+0x16d/0x270
- udp_sendmsg+0x2bf/0x980
- inet_sendmsg+0x67/0xa0
- sock_sendmsg+0x38/0x50
- ___sys_sendmsg+0x14e/0x270
- } hitcount: 76
- { stacktrace:
- netif_rx_internal+0xb2/0xd0
- netif_rx+0x1c/0x60
- loopback_xmit+0x6c/0xb0
- dev_hard_start_xmit+0x219/0x3a0
- __dev_queue_xmit+0x415/0x4f0
- dev_queue_xmit_sk+0x13/0x20
- ip_finish_output2+0x237/0x340
- ip_finish_output+0x113/0x1d0
- ip_output+0x66/0xc0
- ip_local_out_sk+0x31/0x40
- ip_send_skb+0x1a/0x50
- udp_send_skb+0x16d/0x270
- udp_sendmsg+0x2bf/0x980
- inet_sendmsg+0x67/0xa0
- sock_sendmsg+0x38/0x50
- ___sys_sendmsg+0x269/0x270
- } hitcount: 77
- { stacktrace:
- netif_rx_internal+0xb2/0xd0
- netif_rx+0x1c/0x60
- loopback_xmit+0x6c/0xb0
- dev_hard_start_xmit+0x219/0x3a0
- __dev_queue_xmit+0x415/0x4f0
- dev_queue_xmit_sk+0x13/0x20
- ip_finish_output2+0x237/0x340
- ip_finish_output+0x113/0x1d0
- ip_output+0x66/0xc0
- ip_local_out_sk+0x31/0x40
- ip_send_skb+0x1a/0x50
- udp_send_skb+0x16d/0x270
- udp_sendmsg+0x2bf/0x980
- inet_sendmsg+0x67/0xa0
- sock_sendmsg+0x38/0x50
- SYSC_sendto+0xef/0x170
- } hitcount: 88
- { stacktrace:
- _do_fork+0x18e/0x330
- SyS_clone+0x19/0x20
- entry_SYSCALL_64_fastpath+0x12/0x6a
- } hitcount: 244
-
- Totals:
- Hits: 489
- Entries: 7
- Dropped: 0
+ See Documentation/trace/histogram.txt for details and examples.
diff --git a/Documentation/trace/ftrace.txt b/Documentation/trace/ftrace.txt
index d4601df6e72e..54213e5c23f6 100644
--- a/Documentation/trace/ftrace.txt
+++ b/Documentation/trace/ftrace.txt
@@ -539,6 +539,30 @@ of ftrace. Here is a list of some of the key files:
See events.txt for more information.
+ timestamp_mode:
+
+ Certain tracers may change the timestamp mode used when
+ logging trace events into the event buffer. Events with
+ different modes can coexist within a buffer but the mode in
+ effect when an event is logged determines which timestamp mode
+ is used for that event. The default timestamp mode is
+ 'delta'.
+
+ Usual timestamp modes for tracing:
+
+ # cat timestamp_mode
+ [delta] absolute
+
+ The timestamp mode with the square brackets around it is the
+ one in effect.
+
+ delta: Default timestamp mode - timestamp is a delta against
+ a per-buffer timestamp.
+
+ absolute: The timestamp is a full timestamp, not a delta
+ against some other value. As such it takes up more
+ space and is less efficient.
+
hwlat_detector:
Directory for the Hardware Latency Detector.
diff --git a/Documentation/trace/histogram.txt b/Documentation/trace/histogram.txt
new file mode 100644
index 000000000000..6e05510afc28
--- /dev/null
+++ b/Documentation/trace/histogram.txt
@@ -0,0 +1,1995 @@
+ Event Histograms
+
+ Documentation written by Tom Zanussi
+
+1. Introduction
+===============
+
+ Histogram triggers are special event triggers that can be used to
+ aggregate trace event data into histograms. For information on
+ trace events and event triggers, see Documentation/trace/events.txt.
+
+
+2. Histogram Trigger Command
+============================
+
+ A histogram trigger command is an event trigger command that
+ aggregates event hits into a hash table keyed on one or more trace
+ event format fields (or stacktrace) and a set of running totals
+ derived from one or more trace event format fields and/or event
+ counts (hitcount).
+
+ The format of a hist trigger is as follows:
+
+ hist:keys=<field1[,field2,...]>[:values=<field1[,field2,...]>]
+ [:sort=<field1[,field2,...]>][:size=#entries][:pause][:continue]
+ [:clear][:name=histname1] [if <filter>]
+
+ When a matching event is hit, an entry is added to a hash table
+ using the key(s) and value(s) named. Keys and values correspond to
+ fields in the event's format description. Values must correspond to
+ numeric fields - on an event hit, the value(s) will be added to a
+ sum kept for that field. The special string 'hitcount' can be used
+ in place of an explicit value field - this is simply a count of
+ event hits. If 'values' isn't specified, an implicit 'hitcount'
+ value will be automatically created and used as the only value.
+ Keys can be any field, or the special string 'stacktrace', which
+ will use the event's kernel stacktrace as the key. The keywords
+ 'keys' or 'key' can be used to specify keys, and the keywords
+ 'values', 'vals', or 'val' can be used to specify values. Compound
+ keys consisting of up to two fields can be specified by the 'keys'
+ keyword. Hashing a compound key produces a unique entry in the
+ table for each unique combination of component keys, and can be
+ useful for providing more fine-grained summaries of event data.
+ Additionally, sort keys consisting of up to two fields can be
+ specified by the 'sort' keyword. If more than one field is
+ specified, the result will be a 'sort within a sort': the first key
+ is taken to be the primary sort key and the second the secondary
+ key. If a hist trigger is given a name using the 'name' parameter,
+ its histogram data will be shared with other triggers of the same
+ name, and trigger hits will update this common data. Only triggers
+ with 'compatible' fields can be combined in this way; triggers are
+ 'compatible' if the fields named in the trigger share the same
+ number and type of fields and those fields also have the same names.
+ Note that any two events always share the compatible 'hitcount' and
+ 'stacktrace' fields and can therefore be combined using those
+ fields, however pointless that may be.
+
+ 'hist' triggers add a 'hist' file to each event's subdirectory.
+ Reading the 'hist' file for the event will dump the hash table in
+ its entirety to stdout. If there are multiple hist triggers
+ attached to an event, there will be a table for each trigger in the
+ output. The table displayed for a named trigger will be the same as
+ any other instance having the same name. Each printed hash table
+ entry is a simple list of the keys and values comprising the entry;
+ keys are printed first and are delineated by curly braces, and are
+ followed by the set of value fields for the entry. By default,
+ numeric fields are displayed as base-10 integers. This can be
+ modified by appending any of the following modifiers to the field
+ name:
+
+ .hex display a number as a hex value
+ .sym display an address as a symbol
+ .sym-offset display an address as a symbol and offset
+ .syscall display a syscall id as a system call name
+ .execname display a common_pid as a program name
+ .log2 display log2 value rather than raw number
+ .usecs display a common_timestamp in microseconds
+
+ Note that in general the semantics of a given field aren't
+ interpreted when applying a modifier to it, but there are some
+ restrictions to be aware of in this regard:
+
+ - only the 'hex' modifier can be used for values (because values
+ are essentially sums, and the other modifiers don't make sense
+ in that context).
+ - the 'execname' modifier can only be used on a 'common_pid'. The
+ reason for this is that the execname is simply the 'comm' value
+ saved for the 'current' process when an event was triggered,
+ which is the same as the common_pid value saved by the event
+ tracing code. Trying to apply that comm value to other pid
+ values wouldn't be correct, and typically events that care save
+ pid-specific comm fields in the event itself.
+
+ A typical usage scenario would be the following to enable a hist
+ trigger, read its current contents, and then turn it off:
+
+ # echo 'hist:keys=skbaddr.hex:vals=len' > \
+ /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+ # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+ # echo '!hist:keys=skbaddr.hex:vals=len' > \
+ /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+ The trigger file itself can be read to show the details of the
+ currently attached hist trigger. This information is also displayed
+ at the top of the 'hist' file when read.
+
+ By default, the size of the hash table is 2048 entries. The 'size'
+ parameter can be used to specify more or fewer than that. The units
+ are in terms of hashtable entries - if a run uses more entries than
+ specified, the results will show the number of 'drops', the number
+ of hits that were ignored. The size should be a power of 2 between
+ 128 and 131072 (any non- power-of-2 number specified will be rounded
+ up).
+
+ The 'sort' parameter can be used to specify a value field to sort
+ on. The default if unspecified is 'hitcount' and the default sort
+ order is 'ascending'. To sort in the opposite direction, append
+ .descending' to the sort key.
+
+ The 'pause' parameter can be used to pause an existing hist trigger
+ or to start a hist trigger but not log any events until told to do
+ so. 'continue' or 'cont' can be used to start or restart a paused
+ hist trigger.
+
+ The 'clear' parameter will clear the contents of a running hist
+ trigger and leave its current paused/active state.
+
+ Note that the 'pause', 'cont', and 'clear' parameters should be
+ applied using 'append' shell operator ('>>') if applied to an
+ existing trigger, rather than via the '>' operator, which will cause
+ the trigger to be removed through truncation.
+
+- enable_hist/disable_hist
+
+ The enable_hist and disable_hist triggers can be used to have one
+ event conditionally start and stop another event's already-attached
+ hist trigger. Any number of enable_hist and disable_hist triggers
+ can be attached to a given event, allowing that event to kick off
+ and stop aggregations on a host of other events.
+
+ The format is very similar to the enable/disable_event triggers:
+
+ enable_hist:<system>:<event>[:count]
+ disable_hist:<system>:<event>[:count]
+
+ Instead of enabling or disabling the tracing of the target event
+ into the trace buffer as the enable/disable_event triggers do, the
+ enable/disable_hist triggers enable or disable the aggregation of
+ the target event into a hash table.
+
+ A typical usage scenario for the enable_hist/disable_hist triggers
+ would be to first set up a paused hist trigger on some event,
+ followed by an enable_hist/disable_hist pair that turns the hist
+ aggregation on and off when conditions of interest are hit:
+
+ # echo 'hist:keys=skbaddr.hex:vals=len:pause' > \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+ # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+ # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+ The above sets up an initially paused hist trigger which is unpaused
+ and starts aggregating events when a given program is executed, and
+ which stops aggregating when the process exits and the hist trigger
+ is paused again.
+
+ The examples below provide a more concrete illustration of the
+ concepts and typical usage patterns discussed above.
+
+ 'special' event fields
+ ------------------------
+
+ There are a number of 'special event fields' available for use as
+ keys or values in a hist trigger. These look like and behave as if
+ they were actual event fields, but aren't really part of the event's
+ field definition or format file. They are however available for any
+ event, and can be used anywhere an actual event field could be.
+ They are:
+
+ common_timestamp u64 - timestamp (from ring buffer) associated
+ with the event, in nanoseconds. May be
+ modified by .usecs to have timestamps
+ interpreted as microseconds.
+ cpu int - the cpu on which the event occurred.
+
+ Extended error information
+ --------------------------
+
+ For some error conditions encountered when invoking a hist trigger
+ command, extended error information is available via the
+ corresponding event's 'hist' file. Reading the hist file after an
+ error will display more detailed information about what went wrong,
+ if information is available. This extended error information will
+ be available until the next hist trigger command for that event.
+
+ If available for a given error condition, the extended error
+ information and usage takes the following form:
+
+ # echo xxx > /sys/kernel/debug/tracing/events/sched/sched_wakeup/trigger
+ echo: write error: Invalid argument
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_wakeup/hist
+ ERROR: Couldn't yyy: zzz
+ Last command: xxx
+
+6.2 'hist' trigger examples
+---------------------------
+
+ The first set of examples creates aggregations using the kmalloc
+ event. The fields that can be used for the hist trigger are listed
+ in the kmalloc event's format file:
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/format
+ name: kmalloc
+ ID: 374
+ format:
+ field:unsigned short common_type; offset:0; size:2; signed:0;
+ field:unsigned char common_flags; offset:2; size:1; signed:0;
+ field:unsigned char common_preempt_count; offset:3; size:1; signed:0;
+ field:int common_pid; offset:4; size:4; signed:1;
+
+ field:unsigned long call_site; offset:8; size:8; signed:0;
+ field:const void * ptr; offset:16; size:8; signed:0;
+ field:size_t bytes_req; offset:24; size:8; signed:0;
+ field:size_t bytes_alloc; offset:32; size:8; signed:0;
+ field:gfp_t gfp_flags; offset:40; size:4; signed:0;
+
+ We'll start by creating a hist trigger that generates a simple table
+ that lists the total number of bytes requested for each function in
+ the kernel that made one or more calls to kmalloc:
+
+ # echo 'hist:key=call_site:val=bytes_req' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ This tells the tracing system to create a 'hist' trigger using the
+ call_site field of the kmalloc event as the key for the table, which
+ just means that each unique call_site address will have an entry
+ created for it in the table. The 'val=bytes_req' parameter tells
+ the hist trigger that for each unique entry (call_site) in the
+ table, it should keep a running total of the number of bytes
+ requested by that call_site.
+
+ We'll let it run for awhile and then dump the contents of the 'hist'
+ file in the kmalloc event's subdirectory (for readability, a number
+ of entries have been omitted):
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+ { call_site: 18446744072106379007 } hitcount: 1 bytes_req: 176
+ { call_site: 18446744071579557049 } hitcount: 1 bytes_req: 1024
+ { call_site: 18446744071580608289 } hitcount: 1 bytes_req: 16384
+ { call_site: 18446744071581827654 } hitcount: 1 bytes_req: 24
+ { call_site: 18446744071580700980 } hitcount: 1 bytes_req: 8
+ { call_site: 18446744071579359876 } hitcount: 1 bytes_req: 152
+ { call_site: 18446744071580795365 } hitcount: 3 bytes_req: 144
+ { call_site: 18446744071581303129 } hitcount: 3 bytes_req: 144
+ { call_site: 18446744071580713234 } hitcount: 4 bytes_req: 2560
+ { call_site: 18446744071580933750 } hitcount: 4 bytes_req: 736
+ .
+ .
+ .
+ { call_site: 18446744072106047046 } hitcount: 69 bytes_req: 5576
+ { call_site: 18446744071582116407 } hitcount: 73 bytes_req: 2336
+ { call_site: 18446744072106054684 } hitcount: 136 bytes_req: 140504
+ { call_site: 18446744072106224230 } hitcount: 136 bytes_req: 19584
+ { call_site: 18446744072106078074 } hitcount: 153 bytes_req: 2448
+ { call_site: 18446744072106062406 } hitcount: 153 bytes_req: 36720
+ { call_site: 18446744071582507929 } hitcount: 153 bytes_req: 37088
+ { call_site: 18446744072102520590 } hitcount: 273 bytes_req: 10920
+ { call_site: 18446744071582143559 } hitcount: 358 bytes_req: 716
+ { call_site: 18446744072106465852 } hitcount: 417 bytes_req: 56712
+ { call_site: 18446744072102523378 } hitcount: 485 bytes_req: 27160
+ { call_site: 18446744072099568646 } hitcount: 1676 bytes_req: 33520
+
+ Totals:
+ Hits: 4610
+ Entries: 45
+ Dropped: 0
+
+ The output displays a line for each entry, beginning with the key
+ specified in the trigger, followed by the value(s) also specified in
+ the trigger. At the beginning of the output is a line that displays
+ the trigger info, which can also be displayed by reading the
+ 'trigger' file:
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+ hist:keys=call_site:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+ At the end of the output are a few lines that display the overall
+ totals for the run. The 'Hits' field shows the total number of
+ times the event trigger was hit, the 'Entries' field shows the total
+ number of used entries in the hash table, and the 'Dropped' field
+ shows the number of hits that were dropped because the number of
+ used entries for the run exceeded the maximum number of entries
+ allowed for the table (normally 0, but if not a hint that you may
+ want to increase the size of the table using the 'size' parameter).
+
+ Notice in the above output that there's an extra field, 'hitcount',
+ which wasn't specified in the trigger. Also notice that in the
+ trigger info output, there's a parameter, 'sort=hitcount', which
+ wasn't specified in the trigger either. The reason for that is that
+ every trigger implicitly keeps a count of the total number of hits
+ attributed to a given entry, called the 'hitcount'. That hitcount
+ information is explicitly displayed in the output, and in the
+ absence of a user-specified sort parameter, is used as the default
+ sort field.
+
+ The value 'hitcount' can be used in place of an explicit value in
+ the 'values' parameter if you don't really need to have any
+ particular field summed and are mainly interested in hit
+ frequencies.
+
+ To turn the hist trigger off, simply call up the trigger in the
+ command history and re-execute it with a '!' prepended:
+
+ # echo '!hist:key=call_site:val=bytes_req' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ Finally, notice that the call_site as displayed in the output above
+ isn't really very useful. It's an address, but normally addresses
+ are displayed in hex. To have a numeric field displayed as a hex
+ value, simply append '.hex' to the field name in the trigger:
+
+ # echo 'hist:key=call_site.hex:val=bytes_req' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site.hex:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+ { call_site: ffffffffa026b291 } hitcount: 1 bytes_req: 433
+ { call_site: ffffffffa07186ff } hitcount: 1 bytes_req: 176
+ { call_site: ffffffff811ae721 } hitcount: 1 bytes_req: 16384
+ { call_site: ffffffff811c5134 } hitcount: 1 bytes_req: 8
+ { call_site: ffffffffa04a9ebb } hitcount: 1 bytes_req: 511
+ { call_site: ffffffff8122e0a6 } hitcount: 1 bytes_req: 12
+ { call_site: ffffffff8107da84 } hitcount: 1 bytes_req: 152
+ { call_site: ffffffff812d8246 } hitcount: 1 bytes_req: 24
+ { call_site: ffffffff811dc1e5 } hitcount: 3 bytes_req: 144
+ { call_site: ffffffffa02515e8 } hitcount: 3 bytes_req: 648
+ { call_site: ffffffff81258159 } hitcount: 3 bytes_req: 144
+ { call_site: ffffffff811c80f4 } hitcount: 4 bytes_req: 544
+ .
+ .
+ .
+ { call_site: ffffffffa06c7646 } hitcount: 106 bytes_req: 8024
+ { call_site: ffffffffa06cb246 } hitcount: 132 bytes_req: 31680
+ { call_site: ffffffffa06cef7a } hitcount: 132 bytes_req: 2112
+ { call_site: ffffffff8137e399 } hitcount: 132 bytes_req: 23232
+ { call_site: ffffffffa06c941c } hitcount: 185 bytes_req: 171360
+ { call_site: ffffffffa06f2a66 } hitcount: 185 bytes_req: 26640
+ { call_site: ffffffffa036a70e } hitcount: 265 bytes_req: 10600
+ { call_site: ffffffff81325447 } hitcount: 292 bytes_req: 584
+ { call_site: ffffffffa072da3c } hitcount: 446 bytes_req: 60656
+ { call_site: ffffffffa036b1f2 } hitcount: 526 bytes_req: 29456
+ { call_site: ffffffffa0099c06 } hitcount: 1780 bytes_req: 35600
+
+ Totals:
+ Hits: 4775
+ Entries: 46
+ Dropped: 0
+
+ Even that's only marginally more useful - while hex values do look
+ more like addresses, what users are typically more interested in
+ when looking at text addresses are the corresponding symbols
+ instead. To have an address displayed as symbolic value instead,
+ simply append '.sym' or '.sym-offset' to the field name in the
+ trigger:
+
+ # echo 'hist:key=call_site.sym:val=bytes_req' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=hitcount:size=2048 [active]
+
+ { call_site: [ffffffff810adcb9] syslog_print_all } hitcount: 1 bytes_req: 1024
+ { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8
+ { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7
+ { call_site: [ffffffff8154acbe] usb_alloc_urb } hitcount: 1 bytes_req: 192
+ { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7
+ { call_site: [ffffffff811e3a25] __seq_open_private } hitcount: 1 bytes_req: 40
+ { call_site: [ffffffff8109524a] alloc_fair_sched_group } hitcount: 2 bytes_req: 128
+ { call_site: [ffffffff811febd5] fsnotify_alloc_group } hitcount: 2 bytes_req: 528
+ { call_site: [ffffffff81440f58] __tty_buffer_request_room } hitcount: 2 bytes_req: 2624
+ { call_site: [ffffffff81200ba6] inotify_new_group } hitcount: 2 bytes_req: 96
+ { call_site: [ffffffffa05e19af] ieee80211_start_tx_ba_session [mac80211] } hitcount: 2 bytes_req: 464
+ { call_site: [ffffffff81672406] tcp_get_metrics } hitcount: 2 bytes_req: 304
+ { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128
+ { call_site: [ffffffff81089b05] sched_create_group } hitcount: 2 bytes_req: 1424
+ .
+ .
+ .
+ { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 1185 bytes_req: 123240
+ { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm] } hitcount: 1185 bytes_req: 104280
+ { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 1402 bytes_req: 190672
+ { call_site: [ffffffff812891ca] ext4_find_extent } hitcount: 1518 bytes_req: 146208
+ { call_site: [ffffffffa029070e] drm_vma_node_allow [drm] } hitcount: 1746 bytes_req: 69840
+ { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 2021 bytes_req: 792312
+ { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 2592 bytes_req: 145152
+ { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 2629 bytes_req: 378576
+ { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 2629 bytes_req: 3783248
+ { call_site: [ffffffff81325607] apparmor_file_alloc_security } hitcount: 5192 bytes_req: 10384
+ { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 5529 bytes_req: 110584
+ { call_site: [ffffffff8131ebf7] aa_alloc_task_context } hitcount: 21943 bytes_req: 702176
+ { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 55759 bytes_req: 5074265
+
+ Totals:
+ Hits: 109928
+ Entries: 71
+ Dropped: 0
+
+ Because the default sort key above is 'hitcount', the above shows a
+ the list of call_sites by increasing hitcount, so that at the bottom
+ we see the functions that made the most kmalloc calls during the
+ run. If instead we we wanted to see the top kmalloc callers in
+ terms of the number of bytes requested rather than the number of
+ calls, and we wanted the top caller to appear at the top, we can use
+ the 'sort' parameter, along with the 'descending' modifier:
+
+ # echo 'hist:key=call_site.sym:val=bytes_req:sort=bytes_req.descending' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site.sym:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+ { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 2186 bytes_req: 3397464
+ { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 1790 bytes_req: 712176
+ { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 8132 bytes_req: 513135
+ { call_site: [ffffffff811e2a1b] seq_buf_alloc } hitcount: 106 bytes_req: 440128
+ { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 2186 bytes_req: 314784
+ { call_site: [ffffffff812891ca] ext4_find_extent } hitcount: 2174 bytes_req: 208992
+ { call_site: [ffffffff811ae8e1] __kmalloc } hitcount: 8 bytes_req: 131072
+ { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 859 bytes_req: 116824
+ { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 1834 bytes_req: 102704
+ { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 972 bytes_req: 101088
+ { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl [drm] } hitcount: 972 bytes_req: 85536
+ { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 3333 bytes_req: 66664
+ { call_site: [ffffffff8137e559] sg_kmalloc } hitcount: 209 bytes_req: 61632
+ .
+ .
+ .
+ { call_site: [ffffffff81095225] alloc_fair_sched_group } hitcount: 2 bytes_req: 128
+ { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128
+ { call_site: [ffffffff812d8406] copy_semundo } hitcount: 2 bytes_req: 48
+ { call_site: [ffffffff81200ba6] inotify_new_group } hitcount: 1 bytes_req: 48
+ { call_site: [ffffffffa027121a] drm_getmagic [drm] } hitcount: 1 bytes_req: 48
+ { call_site: [ffffffff811e3a25] __seq_open_private } hitcount: 1 bytes_req: 40
+ { call_site: [ffffffff811c52f4] bprm_change_interp } hitcount: 2 bytes_req: 16
+ { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8
+ { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7
+ { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7
+
+ Totals:
+ Hits: 32133
+ Entries: 81
+ Dropped: 0
+
+ To display the offset and size information in addition to the symbol
+ name, just use 'sym-offset' instead:
+
+ # echo 'hist:key=call_site.sym-offset:val=bytes_req:sort=bytes_req.descending' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site.sym-offset:vals=bytes_req:sort=bytes_req.descending:size=2048 [active]
+
+ { call_site: [ffffffffa046041c] i915_gem_execbuffer2+0x6c/0x2c0 [i915] } hitcount: 4569 bytes_req: 3163720
+ { call_site: [ffffffffa0489a66] intel_ring_begin+0xc6/0x1f0 [i915] } hitcount: 4569 bytes_req: 657936
+ { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23+0x694/0x1020 [i915] } hitcount: 1519 bytes_req: 472936
+ { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23+0x516/0x1020 [i915] } hitcount: 3050 bytes_req: 211832
+ { call_site: [ffffffff811e2a1b] seq_buf_alloc+0x1b/0x50 } hitcount: 34 bytes_req: 148384
+ { call_site: [ffffffffa04a580c] intel_crtc_page_flip+0xbc/0x870 [i915] } hitcount: 1385 bytes_req: 144040
+ { call_site: [ffffffff811ae8e1] __kmalloc+0x191/0x1b0 } hitcount: 8 bytes_req: 131072
+ { call_site: [ffffffffa0287592] drm_mode_page_flip_ioctl+0x282/0x360 [drm] } hitcount: 1385 bytes_req: 121880
+ { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc+0x32/0x100 [drm] } hitcount: 1848 bytes_req: 103488
+ { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state+0x2c/0xa0 [i915] } hitcount: 461 bytes_req: 62696
+ { call_site: [ffffffffa029070e] drm_vma_node_allow+0x2e/0xd0 [drm] } hitcount: 1541 bytes_req: 61640
+ { call_site: [ffffffff815f8d7b] sk_prot_alloc+0xcb/0x1b0 } hitcount: 57 bytes_req: 57456
+ .
+ .
+ .
+ { call_site: [ffffffff8109524a] alloc_fair_sched_group+0x5a/0x1a0 } hitcount: 2 bytes_req: 128
+ { call_site: [ffffffffa027b921] drm_vm_open_locked+0x31/0xa0 [drm] } hitcount: 3 bytes_req: 96
+ { call_site: [ffffffff8122e266] proc_self_follow_link+0x76/0xb0 } hitcount: 8 bytes_req: 96
+ { call_site: [ffffffff81213e80] load_elf_binary+0x240/0x1650 } hitcount: 3 bytes_req: 84
+ { call_site: [ffffffff8154bc62] usb_control_msg+0x42/0x110 } hitcount: 1 bytes_req: 8
+ { call_site: [ffffffffa00bf6fe] hidraw_send_report+0x7e/0x1a0 [hid] } hitcount: 1 bytes_req: 7
+ { call_site: [ffffffffa00bf1ca] hidraw_report_event+0x8a/0x120 [hid] } hitcount: 1 bytes_req: 7
+
+ Totals:
+ Hits: 26098
+ Entries: 64
+ Dropped: 0
+
+ We can also add multiple fields to the 'values' parameter. For
+ example, we might want to see the total number of bytes allocated
+ alongside bytes requested, and display the result sorted by bytes
+ allocated in a descending order:
+
+ # echo 'hist:keys=call_site.sym:values=bytes_req,bytes_alloc:sort=bytes_alloc.descending' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=call_site.sym:vals=bytes_req,bytes_alloc:sort=bytes_alloc.descending:size=2048 [active]
+
+ { call_site: [ffffffffa046041c] i915_gem_execbuffer2 [i915] } hitcount: 7403 bytes_req: 4084360 bytes_alloc: 5958016
+ { call_site: [ffffffff811e2a1b] seq_buf_alloc } hitcount: 541 bytes_req: 2213968 bytes_alloc: 2228224
+ { call_site: [ffffffffa0489a66] intel_ring_begin [i915] } hitcount: 7404 bytes_req: 1066176 bytes_alloc: 1421568
+ { call_site: [ffffffffa045e7c4] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 1565 bytes_req: 557368 bytes_alloc: 1037760
+ { call_site: [ffffffff8125847d] ext4_htree_store_dirent } hitcount: 9557 bytes_req: 595778 bytes_alloc: 695744
+ { call_site: [ffffffffa045e646] i915_gem_do_execbuffer.isra.23 [i915] } hitcount: 5839 bytes_req: 430680 bytes_alloc: 470400
+ { call_site: [ffffffffa04c4a3c] intel_plane_duplicate_state [i915] } hitcount: 2388 bytes_req: 324768 bytes_alloc: 458496
+ { call_site: [ffffffffa02911f2] drm_modeset_lock_crtc [drm] } hitcount: 3911 bytes_req: 219016 bytes_alloc: 250304
+ { call_site: [ffffffff815f8d7b] sk_prot_alloc } hitcount: 235 bytes_req: 236880 bytes_alloc: 240640
+ { call_site: [ffffffff8137e559] sg_kmalloc } hitcount: 557 bytes_req: 169024 bytes_alloc: 221760
+ { call_site: [ffffffffa00b7c06] hid_report_raw_event [hid] } hitcount: 9378 bytes_req: 187548 bytes_alloc: 206312
+ { call_site: [ffffffffa04a580c] intel_crtc_page_flip [i915] } hitcount: 1519 bytes_req: 157976 bytes_alloc: 194432
+ .
+ .
+ .
+ { call_site: [ffffffff8109bd3b] sched_autogroup_create_attach } hitcount: 2 bytes_req: 144 bytes_alloc: 192
+ { call_site: [ffffffff81097ee8] alloc_rt_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
+ { call_site: [ffffffff8109524a] alloc_fair_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
+ { call_site: [ffffffff81095225] alloc_fair_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
+ { call_site: [ffffffff81097ec2] alloc_rt_sched_group } hitcount: 2 bytes_req: 128 bytes_alloc: 128
+ { call_site: [ffffffff81213e80] load_elf_binary } hitcount: 3 bytes_req: 84 bytes_alloc: 96
+ { call_site: [ffffffff81079a2e] kthread_create_on_node } hitcount: 1 bytes_req: 56 bytes_alloc: 64
+ { call_site: [ffffffffa00bf6fe] hidraw_send_report [hid] } hitcount: 1 bytes_req: 7 bytes_alloc: 8
+ { call_site: [ffffffff8154bc62] usb_control_msg } hitcount: 1 bytes_req: 8 bytes_alloc: 8
+ { call_site: [ffffffffa00bf1ca] hidraw_report_event [hid] } hitcount: 1 bytes_req: 7 bytes_alloc: 8
+
+ Totals:
+ Hits: 66598
+ Entries: 65
+ Dropped: 0
+
+ Finally, to finish off our kmalloc example, instead of simply having
+ the hist trigger display symbolic call_sites, we can have the hist
+ trigger additionally display the complete set of kernel stack traces
+ that led to each call_site. To do that, we simply use the special
+ value 'stacktrace' for the key parameter:
+
+ # echo 'hist:keys=stacktrace:values=bytes_req,bytes_alloc:sort=bytes_alloc' > \
+ /sys/kernel/debug/tracing/events/kmem/kmalloc/trigger
+
+ The above trigger will use the kernel stack trace in effect when an
+ event is triggered as the key for the hash table. This allows the
+ enumeration of every kernel callpath that led up to a particular
+ event, along with a running total of any of the event fields for
+ that event. Here we tally bytes requested and bytes allocated for
+ every callpath in the system that led up to a kmalloc (in this case
+ every callpath to a kmalloc for a kernel compile):
+
+ # cat /sys/kernel/debug/tracing/events/kmem/kmalloc/hist
+ # trigger info: hist:keys=stacktrace:vals=bytes_req,bytes_alloc:sort=bytes_alloc:size=2048 [active]
+
+ { stacktrace:
+ __kmalloc_track_caller+0x10b/0x1a0
+ kmemdup+0x20/0x50
+ hidraw_report_event+0x8a/0x120 [hid]
+ hid_report_raw_event+0x3ea/0x440 [hid]
+ hid_input_report+0x112/0x190 [hid]
+ hid_irq_in+0xc2/0x260 [usbhid]
+ __usb_hcd_giveback_urb+0x72/0x120
+ usb_giveback_urb_bh+0x9e/0xe0
+ tasklet_hi_action+0xf8/0x100
+ __do_softirq+0x114/0x2c0
+ irq_exit+0xa5/0xb0
+ do_IRQ+0x5a/0xf0
+ ret_from_intr+0x0/0x30
+ cpuidle_enter+0x17/0x20
+ cpu_startup_entry+0x315/0x3e0
+ rest_init+0x7c/0x80
+ } hitcount: 3 bytes_req: 21 bytes_alloc: 24
+ { stacktrace:
+ __kmalloc_track_caller+0x10b/0x1a0
+ kmemdup+0x20/0x50
+ hidraw_report_event+0x8a/0x120 [hid]
+ hid_report_raw_event+0x3ea/0x440 [hid]
+ hid_input_report+0x112/0x190 [hid]
+ hid_irq_in+0xc2/0x260 [usbhid]
+ __usb_hcd_giveback_urb+0x72/0x120
+ usb_giveback_urb_bh+0x9e/0xe0
+ tasklet_hi_action+0xf8/0x100
+ __do_softirq+0x114/0x2c0
+ irq_exit+0xa5/0xb0
+ do_IRQ+0x5a/0xf0
+ ret_from_intr+0x0/0x30
+ } hitcount: 3 bytes_req: 21 bytes_alloc: 24
+ { stacktrace:
+ kmem_cache_alloc_trace+0xeb/0x150
+ aa_alloc_task_context+0x27/0x40
+ apparmor_cred_prepare+0x1f/0x50
+ security_prepare_creds+0x16/0x20
+ prepare_creds+0xdf/0x1a0
+ SyS_capset+0xb5/0x200
+ system_call_fastpath+0x12/0x6a
+ } hitcount: 1 bytes_req: 32 bytes_alloc: 32
+ .
+ .
+ .
+ { stacktrace:
+ __kmalloc+0x11b/0x1b0
+ i915_gem_execbuffer2+0x6c/0x2c0 [i915]
+ drm_ioctl+0x349/0x670 [drm]
+ do_vfs_ioctl+0x2f0/0x4f0
+ SyS_ioctl+0x81/0xa0
+ system_call_fastpath+0x12/0x6a
+ } hitcount: 17726 bytes_req: 13944120 bytes_alloc: 19593808
+ { stacktrace:
+ __kmalloc+0x11b/0x1b0
+ load_elf_phdrs+0x76/0xa0
+ load_elf_binary+0x102/0x1650
+ search_binary_handler+0x97/0x1d0
+ do_execveat_common.isra.34+0x551/0x6e0
+ SyS_execve+0x3a/0x50
+ return_from_execve+0x0/0x23
+ } hitcount: 33348 bytes_req: 17152128 bytes_alloc: 20226048
+ { stacktrace:
+ kmem_cache_alloc_trace+0xeb/0x150
+ apparmor_file_alloc_security+0x27/0x40
+ security_file_alloc+0x16/0x20
+ get_empty_filp+0x93/0x1c0
+ path_openat+0x31/0x5f0
+ do_filp_open+0x3a/0x90
+ do_sys_open+0x128/0x220
+ SyS_open+0x1e/0x20
+ system_call_fastpath+0x12/0x6a
+ } hitcount: 4766422 bytes_req: 9532844 bytes_alloc: 38131376
+ { stacktrace:
+ __kmalloc+0x11b/0x1b0
+ seq_buf_alloc+0x1b/0x50
+ seq_read+0x2cc/0x370
+ proc_reg_read+0x3d/0x80
+ __vfs_read+0x28/0xe0
+ vfs_read+0x86/0x140
+ SyS_read+0x46/0xb0
+ system_call_fastpath+0x12/0x6a
+ } hitcount: 19133 bytes_req: 78368768 bytes_alloc: 78368768
+
+ Totals:
+ Hits: 6085872
+ Entries: 253
+ Dropped: 0
+
+ If you key a hist trigger on common_pid, in order for example to
+ gather and display sorted totals for each process, you can use the
+ special .execname modifier to display the executable names for the
+ processes in the table rather than raw pids. The example below
+ keeps a per-process sum of total bytes read:
+
+ # echo 'hist:key=common_pid.execname:val=count:sort=count.descending' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/trigger
+
+ # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_read/hist
+ # trigger info: hist:keys=common_pid.execname:vals=count:sort=count.descending:size=2048 [active]
+
+ { common_pid: gnome-terminal [ 3196] } hitcount: 280 count: 1093512
+ { common_pid: Xorg [ 1309] } hitcount: 525 count: 256640
+ { common_pid: compiz [ 2889] } hitcount: 59 count: 254400
+ { common_pid: bash [ 8710] } hitcount: 3 count: 66369
+ { common_pid: dbus-daemon-lau [ 8703] } hitcount: 49 count: 47739
+ { common_pid: irqbalance [ 1252] } hitcount: 27 count: 27648
+ { common_pid: 01ifupdown [ 8705] } hitcount: 3 count: 17216
+ { common_pid: dbus-daemon [ 772] } hitcount: 10 count: 12396
+ { common_pid: Socket Thread [ 8342] } hitcount: 11 count: 11264
+ { common_pid: nm-dhcp-client. [ 8701] } hitcount: 6 count: 7424
+ { common_pid: gmain [ 1315] } hitcount: 18 count: 6336
+ .
+ .
+ .
+ { common_pid: postgres [ 1892] } hitcount: 2 count: 32
+ { common_pid: postgres [ 1891] } hitcount: 2 count: 32
+ { common_pid: gmain [ 8704] } hitcount: 2 count: 32
+ { common_pid: upstart-dbus-br [ 2740] } hitcount: 21 count: 21
+ { common_pid: nm-dispatcher.a [ 8696] } hitcount: 1 count: 16
+ { common_pid: indicator-datet [ 2904] } hitcount: 1 count: 16
+ { common_pid: gdbus [ 2998] } hitcount: 1 count: 16
+ { common_pid: rtkit-daemon [ 2052] } hitcount: 1 count: 8
+ { common_pid: init [ 1] } hitcount: 2 count: 2
+
+ Totals:
+ Hits: 2116
+ Entries: 51
+ Dropped: 0
+
+ Similarly, if you key a hist trigger on syscall id, for example to
+ gather and display a list of systemwide syscall hits, you can use
+ the special .syscall modifier to display the syscall names rather
+ than raw ids. The example below keeps a running total of syscall
+ counts for the system during the run:
+
+ # echo 'hist:key=id.syscall:val=hitcount' > \
+ /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+ # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+ # trigger info: hist:keys=id.syscall:vals=hitcount:sort=hitcount:size=2048 [active]
+
+ { id: sys_fsync [ 74] } hitcount: 1
+ { id: sys_newuname [ 63] } hitcount: 1
+ { id: sys_prctl [157] } hitcount: 1
+ { id: sys_statfs [137] } hitcount: 1
+ { id: sys_symlink [ 88] } hitcount: 1
+ { id: sys_sendmmsg [307] } hitcount: 1
+ { id: sys_semctl [ 66] } hitcount: 1
+ { id: sys_readlink [ 89] } hitcount: 3
+ { id: sys_bind [ 49] } hitcount: 3
+ { id: sys_getsockname [ 51] } hitcount: 3
+ { id: sys_unlink [ 87] } hitcount: 3
+ { id: sys_rename [ 82] } hitcount: 4
+ { id: unknown_syscall [ 58] } hitcount: 4
+ { id: sys_connect [ 42] } hitcount: 4
+ { id: sys_getpid [ 39] } hitcount: 4
+ .
+ .
+ .
+ { id: sys_rt_sigprocmask [ 14] } hitcount: 952
+ { id: sys_futex [202] } hitcount: 1534
+ { id: sys_write [ 1] } hitcount: 2689
+ { id: sys_setitimer [ 38] } hitcount: 2797
+ { id: sys_read [ 0] } hitcount: 3202
+ { id: sys_select [ 23] } hitcount: 3773
+ { id: sys_writev [ 20] } hitcount: 4531
+ { id: sys_poll [ 7] } hitcount: 8314
+ { id: sys_recvmsg [ 47] } hitcount: 13738
+ { id: sys_ioctl [ 16] } hitcount: 21843
+
+ Totals:
+ Hits: 67612
+ Entries: 72
+ Dropped: 0
+
+ The syscall counts above provide a rough overall picture of system
+ call activity on the system; we can see for example that the most
+ popular system call on this system was the 'sys_ioctl' system call.
+
+ We can use 'compound' keys to refine that number and provide some
+ further insight as to which processes exactly contribute to the
+ overall ioctl count.
+
+ The command below keeps a hitcount for every unique combination of
+ system call id and pid - the end result is essentially a table
+ that keeps a per-pid sum of system call hits. The results are
+ sorted using the system call id as the primary key, and the
+ hitcount sum as the secondary key:
+
+ # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount' > \
+ /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+ # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+ # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 [active]
+
+ { id: sys_read [ 0], common_pid: rtkit-daemon [ 1877] } hitcount: 1
+ { id: sys_read [ 0], common_pid: gdbus [ 2976] } hitcount: 1
+ { id: sys_read [ 0], common_pid: console-kit-dae [ 3400] } hitcount: 1
+ { id: sys_read [ 0], common_pid: postgres [ 1865] } hitcount: 1
+ { id: sys_read [ 0], common_pid: deja-dup-monito [ 3543] } hitcount: 2
+ { id: sys_read [ 0], common_pid: NetworkManager [ 890] } hitcount: 2
+ { id: sys_read [ 0], common_pid: evolution-calen [ 3048] } hitcount: 2
+ { id: sys_read [ 0], common_pid: postgres [ 1864] } hitcount: 2
+ { id: sys_read [ 0], common_pid: nm-applet [ 3022] } hitcount: 2
+ { id: sys_read [ 0], common_pid: whoopsie [ 1212] } hitcount: 2
+ .
+ .
+ .
+ { id: sys_ioctl [ 16], common_pid: bash [ 8479] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: bash [ 3472] } hitcount: 12
+ { id: sys_ioctl [ 16], common_pid: gnome-terminal [ 3199] } hitcount: 16
+ { id: sys_ioctl [ 16], common_pid: Xorg [ 1267] } hitcount: 1808
+ { id: sys_ioctl [ 16], common_pid: compiz [ 2994] } hitcount: 5580
+ .
+ .
+ .
+ { id: sys_waitid [247], common_pid: upstart-dbus-br [ 2690] } hitcount: 3
+ { id: sys_waitid [247], common_pid: upstart-dbus-br [ 2688] } hitcount: 16
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 975] } hitcount: 2
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 3204] } hitcount: 4
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 2888] } hitcount: 4
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 3003] } hitcount: 4
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 2873] } hitcount: 4
+ { id: sys_inotify_add_watch [254], common_pid: gmain [ 3196] } hitcount: 6
+ { id: sys_openat [257], common_pid: java [ 2623] } hitcount: 2
+ { id: sys_eventfd2 [290], common_pid: ibus-ui-gtk3 [ 2760] } hitcount: 4
+ { id: sys_eventfd2 [290], common_pid: compiz [ 2994] } hitcount: 6
+
+ Totals:
+ Hits: 31536
+ Entries: 323
+ Dropped: 0
+
+ The above list does give us a breakdown of the ioctl syscall by
+ pid, but it also gives us quite a bit more than that, which we
+ don't really care about at the moment. Since we know the syscall
+ id for sys_ioctl (16, displayed next to the sys_ioctl name), we
+ can use that to filter out all the other syscalls:
+
+ # echo 'hist:key=id.syscall,common_pid.execname:val=hitcount:sort=id,hitcount if id == 16' > \
+ /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/trigger
+
+ # cat /sys/kernel/debug/tracing/events/raw_syscalls/sys_enter/hist
+ # trigger info: hist:keys=id.syscall,common_pid.execname:vals=hitcount:sort=id.syscall,hitcount:size=2048 if id == 16 [active]
+
+ { id: sys_ioctl [ 16], common_pid: gmain [ 2769] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: evolution-addre [ 8571] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: gmain [ 3003] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: gmain [ 2781] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: gmain [ 2829] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: bash [ 8726] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: bash [ 8508] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: gmain [ 2970] } hitcount: 1
+ { id: sys_ioctl [ 16], common_pid: gmain [ 2768] } hitcount: 1
+ .
+ .
+ .
+ { id: sys_ioctl [ 16], common_pid: pool [ 8559] } hitcount: 45
+ { id: sys_ioctl [ 16], common_pid: pool [ 8555] } hitcount: 48
+ { id: sys_ioctl [ 16], common_pid: pool [ 8551] } hitcount: 48
+ { id: sys_ioctl [ 16], common_pid: avahi-daemon [ 896] } hitcount: 66
+ { id: sys_ioctl [ 16], common_pid: Xorg [ 1267] } hitcount: 26674
+ { id: sys_ioctl [ 16], common_pid: compiz [ 2994] } hitcount: 73443
+
+ Totals:
+ Hits: 101162
+ Entries: 103
+ Dropped: 0
+
+ The above output shows that 'compiz' and 'Xorg' are far and away
+ the heaviest ioctl callers (which might lead to questions about
+ whether they really need to be making all those calls and to
+ possible avenues for further investigation.)
+
+ The compound key examples used a key and a sum value (hitcount) to
+ sort the output, but we can just as easily use two keys instead.
+ Here's an example where we use a compound key composed of the the
+ common_pid and size event fields. Sorting with pid as the primary
+ key and 'size' as the secondary key allows us to display an
+ ordered summary of the recvfrom sizes, with counts, received by
+ each process:
+
+ # echo 'hist:key=common_pid.execname,size:val=hitcount:sort=common_pid,size' > \
+ /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/trigger
+
+ # cat /sys/kernel/debug/tracing/events/syscalls/sys_enter_recvfrom/hist
+ # trigger info: hist:keys=common_pid.execname,size:vals=hitcount:sort=common_pid.execname,size:size=2048 [active]
+
+ { common_pid: smbd [ 784], size: 4 } hitcount: 1
+ { common_pid: dnsmasq [ 1412], size: 4096 } hitcount: 672
+ { common_pid: postgres [ 1796], size: 1000 } hitcount: 6
+ { common_pid: postgres [ 1867], size: 1000 } hitcount: 10
+ { common_pid: bamfdaemon [ 2787], size: 28 } hitcount: 2
+ { common_pid: bamfdaemon [ 2787], size: 14360 } hitcount: 1
+ { common_pid: compiz [ 2994], size: 8 } hitcount: 1
+ { common_pid: compiz [ 2994], size: 20 } hitcount: 11
+ { common_pid: gnome-terminal [ 3199], size: 4 } hitcount: 2
+ { common_pid: firefox [ 8817], size: 4 } hitcount: 1
+ { common_pid: firefox [ 8817], size: 8 } hitcount: 5
+ { common_pid: firefox [ 8817], size: 588 } hitcount: 2
+ { common_pid: firefox [ 8817], size: 628 } hitcount: 1
+ { common_pid: firefox [ 8817], size: 6944 } hitcount: 1
+ { common_pid: firefox [ 8817], size: 408880 } hitcount: 2
+ { common_pid: firefox [ 8822], size: 8 } hitcount: 2
+ { common_pid: firefox [ 8822], size: 160 } hitcount: 2
+ { common_pid: firefox [ 8822], size: 320 } hitcount: 2
+ { common_pid: firefox [ 8822], size: 352 } hitcount: 1
+ .
+ .
+ .
+ { common_pid: pool [ 8923], size: 1960 } hitcount: 10
+ { common_pid: pool [ 8923], size: 2048 } hitcount: 10
+ { common_pid: pool [ 8924], size: 1960 } hitcount: 10
+ { common_pid: pool [ 8924], size: 2048 } hitcount: 10
+ { common_pid: pool [ 8928], size: 1964 } hitcount: 4
+ { common_pid: pool [ 8928], size: 1965 } hitcount: 2
+ { common_pid: pool [ 8928], size: 2048 } hitcount: 6
+ { common_pid: pool [ 8929], size: 1982 } hitcount: 1
+ { common_pid: pool [ 8929], size: 2048 } hitcount: 1
+
+ Totals:
+ Hits: 2016
+ Entries: 224
+ Dropped: 0
+
+ The above example also illustrates the fact that although a compound
+ key is treated as a single entity for hashing purposes, the sub-keys
+ it's composed of can be accessed independently.
+
+ The next example uses a string field as the hash key and
+ demonstrates how you can manually pause and continue a hist trigger.
+ In this example, we'll aggregate fork counts and don't expect a
+ large number of entries in the hash table, so we'll drop it to a
+ much smaller number, say 256:
+
+ # echo 'hist:key=child_comm:val=hitcount:size=256' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+ # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: ibus-daemon } hitcount: 1
+ { child_comm: whoopsie } hitcount: 1
+ { child_comm: smbd } hitcount: 1
+ { child_comm: gdbus } hitcount: 1
+ { child_comm: kthreadd } hitcount: 1
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: evolution-alarm } hitcount: 2
+ { child_comm: Socket Thread } hitcount: 2
+ { child_comm: postgres } hitcount: 2
+ { child_comm: bash } hitcount: 3
+ { child_comm: compiz } hitcount: 3
+ { child_comm: evolution-sourc } hitcount: 4
+ { child_comm: dhclient } hitcount: 4
+ { child_comm: pool } hitcount: 5
+ { child_comm: nm-dispatcher.a } hitcount: 8
+ { child_comm: firefox } hitcount: 8
+ { child_comm: dbus-daemon } hitcount: 8
+ { child_comm: glib-pacrunner } hitcount: 10
+ { child_comm: evolution } hitcount: 23
+
+ Totals:
+ Hits: 89
+ Entries: 20
+ Dropped: 0
+
+ If we want to pause the hist trigger, we can simply append :pause to
+ the command that started the trigger. Notice that the trigger info
+ displays as [paused]:
+
+ # echo 'hist:key=child_comm:val=hitcount:size=256:pause' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+ # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [paused]
+
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: kthreadd } hitcount: 1
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: gdbus } hitcount: 1
+ { child_comm: ibus-daemon } hitcount: 1
+ { child_comm: Socket Thread } hitcount: 2
+ { child_comm: evolution-alarm } hitcount: 2
+ { child_comm: smbd } hitcount: 2
+ { child_comm: bash } hitcount: 3
+ { child_comm: whoopsie } hitcount: 3
+ { child_comm: compiz } hitcount: 3
+ { child_comm: evolution-sourc } hitcount: 4
+ { child_comm: pool } hitcount: 5
+ { child_comm: postgres } hitcount: 6
+ { child_comm: firefox } hitcount: 8
+ { child_comm: dhclient } hitcount: 10
+ { child_comm: emacs } hitcount: 12
+ { child_comm: dbus-daemon } hitcount: 20
+ { child_comm: nm-dispatcher.a } hitcount: 20
+ { child_comm: evolution } hitcount: 35
+ { child_comm: glib-pacrunner } hitcount: 59
+
+ Totals:
+ Hits: 199
+ Entries: 21
+ Dropped: 0
+
+ To manually continue having the trigger aggregate events, append
+ :cont instead. Notice that the trigger info displays as [active]
+ again, and the data has changed:
+
+ # echo 'hist:key=child_comm:val=hitcount:size=256:cont' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+ # trigger info: hist:keys=child_comm:vals=hitcount:sort=hitcount:size=256 [active]
+
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: dconf worker } hitcount: 1
+ { child_comm: kthreadd } hitcount: 1
+ { child_comm: gdbus } hitcount: 1
+ { child_comm: ibus-daemon } hitcount: 1
+ { child_comm: Socket Thread } hitcount: 2
+ { child_comm: evolution-alarm } hitcount: 2
+ { child_comm: smbd } hitcount: 2
+ { child_comm: whoopsie } hitcount: 3
+ { child_comm: compiz } hitcount: 3
+ { child_comm: evolution-sourc } hitcount: 4
+ { child_comm: bash } hitcount: 5
+ { child_comm: pool } hitcount: 5
+ { child_comm: postgres } hitcount: 6
+ { child_comm: firefox } hitcount: 8
+ { child_comm: dhclient } hitcount: 11
+ { child_comm: emacs } hitcount: 12
+ { child_comm: dbus-daemon } hitcount: 22
+ { child_comm: nm-dispatcher.a } hitcount: 22
+ { child_comm: evolution } hitcount: 35
+ { child_comm: glib-pacrunner } hitcount: 59
+
+ Totals:
+ Hits: 206
+ Entries: 21
+ Dropped: 0
+
+ The previous example showed how to start and stop a hist trigger by
+ appending 'pause' and 'continue' to the hist trigger command. A
+ hist trigger can also be started in a paused state by initially
+ starting the trigger with ':pause' appended. This allows you to
+ start the trigger only when you're ready to start collecting data
+ and not before. For example, you could start the trigger in a
+ paused state, then unpause it and do something you want to measure,
+ then pause the trigger again when done.
+
+ Of course, doing this manually can be difficult and error-prone, but
+ it is possible to automatically start and stop a hist trigger based
+ on some condition, via the enable_hist and disable_hist triggers.
+
+ For example, suppose we wanted to take a look at the relative
+ weights in terms of skb length for each callpath that leads to a
+ netif_receieve_skb event when downloading a decent-sized file using
+ wget.
+
+ First we set up an initially paused stacktrace trigger on the
+ netif_receive_skb event:
+
+ # echo 'hist:key=stacktrace:vals=len:pause' > \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+ Next, we set up an 'enable_hist' trigger on the sched_process_exec
+ event, with an 'if filename==/usr/bin/wget' filter. The effect of
+ this new trigger is that it will 'unpause' the hist trigger we just
+ set up on netif_receive_skb if and only if it sees a
+ sched_process_exec event with a filename of '/usr/bin/wget'. When
+ that happens, all netif_receive_skb events are aggregated into a
+ hash table keyed on stacktrace:
+
+ # echo 'enable_hist:net:netif_receive_skb if filename==/usr/bin/wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+ The aggregation continues until the netif_receive_skb is paused
+ again, which is what the following disable_hist event does by
+ creating a similar setup on the sched_process_exit event, using the
+ filter 'comm==wget':
+
+ # echo 'disable_hist:net:netif_receive_skb if comm==wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+ Whenever a process exits and the comm field of the disable_hist
+ trigger filter matches 'comm==wget', the netif_receive_skb hist
+ trigger is disabled.
+
+ The overall effect is that netif_receive_skb events are aggregated
+ into the hash table for only the duration of the wget. Executing a
+ wget command and then listing the 'hist' file will display the
+ output generated by the wget command:
+
+ $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+ # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+ # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+ { stacktrace:
+ __netif_receive_skb_core+0x46d/0x990
+ __netif_receive_skb+0x18/0x60
+ netif_receive_skb_internal+0x23/0x90
+ napi_gro_receive+0xc8/0x100
+ ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+ ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+ ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+ ieee80211_rx+0x31d/0x900 [mac80211]
+ iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+ iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+ iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+ irq_thread_fn+0x20/0x50
+ irq_thread+0x11f/0x150
+ kthread+0xd2/0xf0
+ ret_from_fork+0x42/0x70
+ } hitcount: 85 len: 28884
+ { stacktrace:
+ __netif_receive_skb_core+0x46d/0x990
+ __netif_receive_skb+0x18/0x60
+ netif_receive_skb_internal+0x23/0x90
+ napi_gro_complete+0xa4/0xe0
+ dev_gro_receive+0x23a/0x360
+ napi_gro_receive+0x30/0x100
+ ieee80211_deliver_skb+0xd6/0x270 [mac80211]
+ ieee80211_rx_handlers+0xccf/0x22f0 [mac80211]
+ ieee80211_prepare_and_rx_handle+0x4e7/0xc40 [mac80211]
+ ieee80211_rx+0x31d/0x900 [mac80211]
+ iwlagn_rx_reply_rx+0x3db/0x6f0 [iwldvm]
+ iwl_rx_dispatch+0x8e/0xf0 [iwldvm]
+ iwl_pcie_irq_handler+0xe3c/0x12f0 [iwlwifi]
+ irq_thread_fn+0x20/0x50
+ irq_thread+0x11f/0x150
+ kthread+0xd2/0xf0
+ } hitcount: 98 len: 664329
+ { stacktrace:
+ __netif_receive_skb_core+0x46d/0x990
+ __netif_receive_skb+0x18/0x60
+ process_backlog+0xa8/0x150
+ net_rx_action+0x15d/0x340
+ __do_softirq+0x114/0x2c0
+ do_softirq_own_stack+0x1c/0x30
+ do_softirq+0x65/0x70
+ __local_bh_enable_ip+0xb5/0xc0
+ ip_finish_output+0x1f4/0x840
+ ip_output+0x6b/0xc0
+ ip_local_out_sk+0x31/0x40
+ ip_send_skb+0x1a/0x50
+ udp_send_skb+0x173/0x2a0
+ udp_sendmsg+0x2bf/0x9f0
+ inet_sendmsg+0x64/0xa0
+ sock_sendmsg+0x3d/0x50
+ } hitcount: 115 len: 13030
+ { stacktrace:
+ __netif_receive_skb_core+0x46d/0x990
+ __netif_receive_skb+0x18/0x60
+ netif_receive_skb_internal+0x23/0x90
+ napi_gro_complete+0xa4/0xe0
+ napi_gro_flush+0x6d/0x90
+ iwl_pcie_irq_handler+0x92a/0x12f0 [iwlwifi]
+ irq_thread_fn+0x20/0x50
+ irq_thread+0x11f/0x150
+ kthread+0xd2/0xf0
+ ret_from_fork+0x42/0x70
+ } hitcount: 934 len: 5512212
+
+ Totals:
+ Hits: 1232
+ Entries: 4
+ Dropped: 0
+
+ The above shows all the netif_receive_skb callpaths and their total
+ lengths for the duration of the wget command.
+
+ The 'clear' hist trigger param can be used to clear the hash table.
+ Suppose we wanted to try another run of the previous example but
+ this time also wanted to see the complete list of events that went
+ into the histogram. In order to avoid having to set everything up
+ again, we can just clear the histogram first:
+
+ # echo 'hist:key=stacktrace:vals=len:clear' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+ Just to verify that it is in fact cleared, here's what we now see in
+ the hist file:
+
+ # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+ # trigger info: hist:keys=stacktrace:vals=len:sort=hitcount:size=2048 [paused]
+
+ Totals:
+ Hits: 0
+ Entries: 0
+ Dropped: 0
+
+ Since we want to see the detailed list of every netif_receive_skb
+ event occurring during the new run, which are in fact the same
+ events being aggregated into the hash table, we add some additional
+ 'enable_event' events to the triggering sched_process_exec and
+ sched_process_exit events as such:
+
+ # echo 'enable_event:net:netif_receive_skb if filename==/usr/bin/wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+
+ # echo 'disable_event:net:netif_receive_skb if comm==wget' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+
+ If you read the trigger files for the sched_process_exec and
+ sched_process_exit triggers, you should see two triggers for each:
+ one enabling/disabling the hist aggregation and the other
+ enabling/disabling the logging of events:
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_exec/trigger
+ enable_event:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+ enable_hist:net:netif_receive_skb:unlimited if filename==/usr/bin/wget
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_exit/trigger
+ enable_event:net:netif_receive_skb:unlimited if comm==wget
+ disable_hist:net:netif_receive_skb:unlimited if comm==wget
+
+ In other words, whenever either of the sched_process_exec or
+ sched_process_exit events is hit and matches 'wget', it enables or
+ disables both the histogram and the event log, and what you end up
+ with is a hash table and set of events just covering the specified
+ duration. Run the wget command again:
+
+ $ wget https://www.kernel.org/pub/linux/kernel/v3.x/patch-3.19.xz
+
+ Displaying the 'hist' file should show something similar to what you
+ saw in the last run, but this time you should also see the
+ individual events in the trace file:
+
+ # cat /sys/kernel/debug/tracing/trace
+
+ # tracer: nop
+ #
+ # entries-in-buffer/entries-written: 183/1426 #P:4
+ #
+ # _-----=> irqs-off
+ # / _----=> need-resched
+ # | / _---=> hardirq/softirq
+ # || / _--=> preempt-depth
+ # ||| / delay
+ # TASK-PID CPU# |||| TIMESTAMP FUNCTION
+ # | | | |||| | |
+ wget-15108 [000] ..s1 31769.606929: netif_receive_skb: dev=lo skbaddr=ffff88009c353100 len=60
+ wget-15108 [000] ..s1 31769.606999: netif_receive_skb: dev=lo skbaddr=ffff88009c353200 len=60
+ dnsmasq-1382 [000] ..s1 31769.677652: netif_receive_skb: dev=lo skbaddr=ffff88009c352b00 len=130
+ dnsmasq-1382 [000] ..s1 31769.685917: netif_receive_skb: dev=lo skbaddr=ffff88009c352200 len=138
+ ##### CPU 2 buffer started ####
+ irq/29-iwlwifi-559 [002] ..s. 31772.031529: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433d00 len=2948
+ irq/29-iwlwifi-559 [002] ..s. 31772.031572: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432200 len=1500
+ irq/29-iwlwifi-559 [002] ..s. 31772.032196: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433100 len=2948
+ irq/29-iwlwifi-559 [002] ..s. 31772.032761: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d433000 len=2948
+ irq/29-iwlwifi-559 [002] ..s. 31772.033220: netif_receive_skb: dev=wlan0 skbaddr=ffff88009d432e00 len=1500
+ .
+ .
+ .
+
+ The following example demonstrates how multiple hist triggers can be
+ attached to a given event. This capability can be useful for
+ creating a set of different summaries derived from the same set of
+ events, or for comparing the effects of different filters, among
+ other things.
+
+ # echo 'hist:keys=skbaddr.hex:vals=len if len < 0' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+ # echo 'hist:keys=skbaddr.hex:vals=len if len > 4096' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+ # echo 'hist:keys=skbaddr.hex:vals=len if len == 256' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+ # echo 'hist:keys=skbaddr.hex:vals=len' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+ # echo 'hist:keys=len:vals=common_preempt_count' >> \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+
+ The above set of commands create four triggers differing only in
+ their filters, along with a completely different though fairly
+ nonsensical trigger. Note that in order to append multiple hist
+ triggers to the same file, you should use the '>>' operator to
+ append them ('>' will also add the new hist trigger, but will remove
+ any existing hist triggers beforehand).
+
+ Displaying the contents of the 'hist' file for the event shows the
+ contents of all five histograms:
+
+ # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist
+
+ # event histogram
+ #
+ # trigger info: hist:keys=len:vals=hitcount,common_preempt_count:sort=hitcount:size=2048 [active]
+ #
+
+ { len: 176 } hitcount: 1 common_preempt_count: 0
+ { len: 223 } hitcount: 1 common_preempt_count: 0
+ { len: 4854 } hitcount: 1 common_preempt_count: 0
+ { len: 395 } hitcount: 1 common_preempt_count: 0
+ { len: 177 } hitcount: 1 common_preempt_count: 0
+ { len: 446 } hitcount: 1 common_preempt_count: 0
+ { len: 1601 } hitcount: 1 common_preempt_count: 0
+ .
+ .
+ .
+ { len: 1280 } hitcount: 66 common_preempt_count: 0
+ { len: 116 } hitcount: 81 common_preempt_count: 40
+ { len: 708 } hitcount: 112 common_preempt_count: 0
+ { len: 46 } hitcount: 221 common_preempt_count: 0
+ { len: 1264 } hitcount: 458 common_preempt_count: 0
+
+ Totals:
+ Hits: 1428
+ Entries: 147
+ Dropped: 0
+
+
+ # event histogram
+ #
+ # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+ #
+
+ { skbaddr: ffff8800baee5e00 } hitcount: 1 len: 130
+ { skbaddr: ffff88005f3d5600 } hitcount: 1 len: 1280
+ { skbaddr: ffff88005f3d4900 } hitcount: 1 len: 1280
+ { skbaddr: ffff88009fed6300 } hitcount: 1 len: 115
+ { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 115
+ { skbaddr: ffff88008cdb1900 } hitcount: 1 len: 46
+ { skbaddr: ffff880064b5ef00 } hitcount: 1 len: 118
+ { skbaddr: ffff880044e3c700 } hitcount: 1 len: 60
+ { skbaddr: ffff880100065900 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d46bd500 } hitcount: 1 len: 116
+ { skbaddr: ffff88005f3d5f00 } hitcount: 1 len: 1280
+ { skbaddr: ffff880100064700 } hitcount: 1 len: 365
+ { skbaddr: ffff8800badb6f00 } hitcount: 1 len: 60
+ .
+ .
+ .
+ { skbaddr: ffff88009fe0be00 } hitcount: 27 len: 24677
+ { skbaddr: ffff88009fe0a400 } hitcount: 27 len: 23052
+ { skbaddr: ffff88009fe0b700 } hitcount: 31 len: 25589
+ { skbaddr: ffff88009fe0b600 } hitcount: 32 len: 27326
+ { skbaddr: ffff88006a462800 } hitcount: 68 len: 71678
+ { skbaddr: ffff88006a463700 } hitcount: 70 len: 72678
+ { skbaddr: ffff88006a462b00 } hitcount: 71 len: 77589
+ { skbaddr: ffff88006a463600 } hitcount: 73 len: 71307
+ { skbaddr: ffff88006a462200 } hitcount: 81 len: 81032
+
+ Totals:
+ Hits: 1451
+ Entries: 318
+ Dropped: 0
+
+
+ # event histogram
+ #
+ # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len == 256 [active]
+ #
+
+
+ Totals:
+ Hits: 0
+ Entries: 0
+ Dropped: 0
+
+
+ # event histogram
+ #
+ # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len > 4096 [active]
+ #
+
+ { skbaddr: ffff88009fd2c300 } hitcount: 1 len: 7212
+ { skbaddr: ffff8800d2bcce00 } hitcount: 1 len: 7212
+ { skbaddr: ffff8800d2bcd700 } hitcount: 1 len: 7212
+ { skbaddr: ffff8800d2bcda00 } hitcount: 1 len: 21492
+ { skbaddr: ffff8800ae2e2d00 } hitcount: 1 len: 7212
+ { skbaddr: ffff8800d2bcdb00 } hitcount: 1 len: 7212
+ { skbaddr: ffff88006a4df500 } hitcount: 1 len: 4854
+ { skbaddr: ffff88008ce47b00 } hitcount: 1 len: 18636
+ { skbaddr: ffff8800ae2e2200 } hitcount: 1 len: 12924
+ { skbaddr: ffff88005f3e1000 } hitcount: 1 len: 4356
+ { skbaddr: ffff8800d2bcdc00 } hitcount: 2 len: 24420
+ { skbaddr: ffff8800d2bcc200 } hitcount: 2 len: 12996
+
+ Totals:
+ Hits: 14
+ Entries: 12
+ Dropped: 0
+
+
+ # event histogram
+ #
+ # trigger info: hist:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 if len < 0 [active]
+ #
+
+
+ Totals:
+ Hits: 0
+ Entries: 0
+ Dropped: 0
+
+ Named triggers can be used to have triggers share a common set of
+ histogram data. This capability is mostly useful for combining the
+ output of events generated by tracepoints contained inside inline
+ functions, but names can be used in a hist trigger on any event.
+ For example, these two triggers when hit will update the same 'len'
+ field in the shared 'foo' histogram data:
+
+ # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+ /sys/kernel/debug/tracing/events/net/netif_receive_skb/trigger
+ # echo 'hist:name=foo:keys=skbaddr.hex:vals=len' > \
+ /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+ You can see that they're updating common histogram data by reading
+ each event's hist files at the same time:
+
+ # cat /sys/kernel/debug/tracing/events/net/netif_receive_skb/hist;
+ cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+ # event histogram
+ #
+ # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+ #
+
+ { skbaddr: ffff88000ad53500 } hitcount: 1 len: 46
+ { skbaddr: ffff8800af5a1500 } hitcount: 1 len: 76
+ { skbaddr: ffff8800d62a1900 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bccb00 } hitcount: 1 len: 468
+ { skbaddr: ffff8800d3c69900 } hitcount: 1 len: 46
+ { skbaddr: ffff88009ff09100 } hitcount: 1 len: 52
+ { skbaddr: ffff88010f13ab00 } hitcount: 1 len: 168
+ { skbaddr: ffff88006a54f400 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcc500 } hitcount: 1 len: 260
+ { skbaddr: ffff880064505000 } hitcount: 1 len: 46
+ { skbaddr: ffff8800baf24e00 } hitcount: 1 len: 32
+ { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d3edff00 } hitcount: 1 len: 44
+ { skbaddr: ffff88009fe0b400 } hitcount: 1 len: 168
+ { skbaddr: ffff8800a1c55a00 } hitcount: 1 len: 40
+ { skbaddr: ffff8800d2bcd100 } hitcount: 1 len: 40
+ { skbaddr: ffff880064505f00 } hitcount: 1 len: 174
+ { skbaddr: ffff8800a8bff200 } hitcount: 1 len: 160
+ { skbaddr: ffff880044e3cc00 } hitcount: 1 len: 76
+ { skbaddr: ffff8800a8bfe700 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcdc00 } hitcount: 1 len: 32
+ { skbaddr: ffff8800a1f64800 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcde00 } hitcount: 1 len: 988
+ { skbaddr: ffff88006a5dea00 } hitcount: 1 len: 46
+ { skbaddr: ffff88002e37a200 } hitcount: 1 len: 44
+ { skbaddr: ffff8800a1f32c00 } hitcount: 2 len: 676
+ { skbaddr: ffff88000ad52600 } hitcount: 2 len: 107
+ { skbaddr: ffff8800a1f91e00 } hitcount: 2 len: 92
+ { skbaddr: ffff8800af5a0200 } hitcount: 2 len: 142
+ { skbaddr: ffff8800d2bcc600 } hitcount: 2 len: 220
+ { skbaddr: ffff8800ba36f500 } hitcount: 2 len: 92
+ { skbaddr: ffff8800d021f800 } hitcount: 2 len: 92
+ { skbaddr: ffff8800a1f33600 } hitcount: 2 len: 675
+ { skbaddr: ffff8800a8bfff00 } hitcount: 3 len: 138
+ { skbaddr: ffff8800d62a1300 } hitcount: 3 len: 138
+ { skbaddr: ffff88002e37a100 } hitcount: 4 len: 184
+ { skbaddr: ffff880064504400 } hitcount: 4 len: 184
+ { skbaddr: ffff8800a8bfec00 } hitcount: 4 len: 184
+ { skbaddr: ffff88000ad53700 } hitcount: 5 len: 230
+ { skbaddr: ffff8800d2bcdb00 } hitcount: 5 len: 196
+ { skbaddr: ffff8800a1f90000 } hitcount: 6 len: 276
+ { skbaddr: ffff88006a54f900 } hitcount: 6 len: 276
+
+ Totals:
+ Hits: 81
+ Entries: 42
+ Dropped: 0
+ # event histogram
+ #
+ # trigger info: hist:name=foo:keys=skbaddr.hex:vals=hitcount,len:sort=hitcount:size=2048 [active]
+ #
+
+ { skbaddr: ffff88000ad53500 } hitcount: 1 len: 46
+ { skbaddr: ffff8800af5a1500 } hitcount: 1 len: 76
+ { skbaddr: ffff8800d62a1900 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bccb00 } hitcount: 1 len: 468
+ { skbaddr: ffff8800d3c69900 } hitcount: 1 len: 46
+ { skbaddr: ffff88009ff09100 } hitcount: 1 len: 52
+ { skbaddr: ffff88010f13ab00 } hitcount: 1 len: 168
+ { skbaddr: ffff88006a54f400 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcc500 } hitcount: 1 len: 260
+ { skbaddr: ffff880064505000 } hitcount: 1 len: 46
+ { skbaddr: ffff8800baf24e00 } hitcount: 1 len: 32
+ { skbaddr: ffff88009fe0ad00 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d3edff00 } hitcount: 1 len: 44
+ { skbaddr: ffff88009fe0b400 } hitcount: 1 len: 168
+ { skbaddr: ffff8800a1c55a00 } hitcount: 1 len: 40
+ { skbaddr: ffff8800d2bcd100 } hitcount: 1 len: 40
+ { skbaddr: ffff880064505f00 } hitcount: 1 len: 174
+ { skbaddr: ffff8800a8bff200 } hitcount: 1 len: 160
+ { skbaddr: ffff880044e3cc00 } hitcount: 1 len: 76
+ { skbaddr: ffff8800a8bfe700 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcdc00 } hitcount: 1 len: 32
+ { skbaddr: ffff8800a1f64800 } hitcount: 1 len: 46
+ { skbaddr: ffff8800d2bcde00 } hitcount: 1 len: 988
+ { skbaddr: ffff88006a5dea00 } hitcount: 1 len: 46
+ { skbaddr: ffff88002e37a200 } hitcount: 1 len: 44
+ { skbaddr: ffff8800a1f32c00 } hitcount: 2 len: 676
+ { skbaddr: ffff88000ad52600 } hitcount: 2 len: 107
+ { skbaddr: ffff8800a1f91e00 } hitcount: 2 len: 92
+ { skbaddr: ffff8800af5a0200 } hitcount: 2 len: 142
+ { skbaddr: ffff8800d2bcc600 } hitcount: 2 len: 220
+ { skbaddr: ffff8800ba36f500 } hitcount: 2 len: 92
+ { skbaddr: ffff8800d021f800 } hitcount: 2 len: 92
+ { skbaddr: ffff8800a1f33600 } hitcount: 2 len: 675
+ { skbaddr: ffff8800a8bfff00 } hitcount: 3 len: 138
+ { skbaddr: ffff8800d62a1300 } hitcount: 3 len: 138
+ { skbaddr: ffff88002e37a100 } hitcount: 4 len: 184
+ { skbaddr: ffff880064504400 } hitcount: 4 len: 184
+ { skbaddr: ffff8800a8bfec00 } hitcount: 4 len: 184
+ { skbaddr: ffff88000ad53700 } hitcount: 5 len: 230
+ { skbaddr: ffff8800d2bcdb00 } hitcount: 5 len: 196
+ { skbaddr: ffff8800a1f90000 } hitcount: 6 len: 276
+ { skbaddr: ffff88006a54f900 } hitcount: 6 len: 276
+
+ Totals:
+ Hits: 81
+ Entries: 42
+ Dropped: 0
+
+ And here's an example that shows how to combine histogram data from
+ any two events even if they don't share any 'compatible' fields
+ other than 'hitcount' and 'stacktrace'. These commands create a
+ couple of triggers named 'bar' using those fields:
+
+ # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+ /sys/kernel/debug/tracing/events/sched/sched_process_fork/trigger
+ # echo 'hist:name=bar:key=stacktrace:val=hitcount' > \
+ /sys/kernel/debug/tracing/events/net/netif_rx/trigger
+
+ And displaying the output of either shows some interesting if
+ somewhat confusing output:
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_process_fork/hist
+ # cat /sys/kernel/debug/tracing/events/net/netif_rx/hist
+
+ # event histogram
+ #
+ # trigger info: hist:name=bar:keys=stacktrace:vals=hitcount:sort=hitcount:size=2048 [active]
+ #
+
+ { stacktrace:
+ _do_fork+0x18e/0x330
+ kernel_thread+0x29/0x30
+ kthreadd+0x154/0x1b0
+ ret_from_fork+0x3f/0x70
+ } hitcount: 1
+ { stacktrace:
+ netif_rx_internal+0xb2/0xd0
+ netif_rx_ni+0x20/0x70
+ dev_loopback_xmit+0xaa/0xd0
+ ip_mc_output+0x126/0x240
+ ip_local_out_sk+0x31/0x40
+ igmp_send_report+0x1e9/0x230
+ igmp_timer_expire+0xe9/0x120
+ call_timer_fn+0x39/0xf0
+ run_timer_softirq+0x1e1/0x290
+ __do_softirq+0xfd/0x290
+ irq_exit+0x98/0xb0
+ smp_apic_timer_interrupt+0x4a/0x60
+ apic_timer_interrupt+0x6d/0x80
+ cpuidle_enter+0x17/0x20
+ call_cpuidle+0x3b/0x60
+ cpu_startup_entry+0x22d/0x310
+ } hitcount: 1
+ { stacktrace:
+ netif_rx_internal+0xb2/0xd0
+ netif_rx_ni+0x20/0x70
+ dev_loopback_xmit+0xaa/0xd0
+ ip_mc_output+0x17f/0x240
+ ip_local_out_sk+0x31/0x40
+ ip_send_skb+0x1a/0x50
+ udp_send_skb+0x13e/0x270
+ udp_sendmsg+0x2bf/0x980
+ inet_sendmsg+0x67/0xa0
+ sock_sendmsg+0x38/0x50
+ SYSC_sendto+0xef/0x170
+ SyS_sendto+0xe/0x10
+ entry_SYSCALL_64_fastpath+0x12/0x6a
+ } hitcount: 2
+ { stacktrace:
+ netif_rx_internal+0xb2/0xd0
+ netif_rx+0x1c/0x60
+ loopback_xmit+0x6c/0xb0
+ dev_hard_start_xmit+0x219/0x3a0
+ __dev_queue_xmit+0x415/0x4f0
+ dev_queue_xmit_sk+0x13/0x20
+ ip_finish_output2+0x237/0x340
+ ip_finish_output+0x113/0x1d0
+ ip_output+0x66/0xc0
+ ip_local_out_sk+0x31/0x40
+ ip_send_skb+0x1a/0x50
+ udp_send_skb+0x16d/0x270
+ udp_sendmsg+0x2bf/0x980
+ inet_sendmsg+0x67/0xa0
+ sock_sendmsg+0x38/0x50
+ ___sys_sendmsg+0x14e/0x270
+ } hitcount: 76
+ { stacktrace:
+ netif_rx_internal+0xb2/0xd0
+ netif_rx+0x1c/0x60
+ loopback_xmit+0x6c/0xb0
+ dev_hard_start_xmit+0x219/0x3a0
+ __dev_queue_xmit+0x415/0x4f0
+ dev_queue_xmit_sk+0x13/0x20
+ ip_finish_output2+0x237/0x340
+ ip_finish_output+0x113/0x1d0
+ ip_output+0x66/0xc0
+ ip_local_out_sk+0x31/0x40
+ ip_send_skb+0x1a/0x50
+ udp_send_skb+0x16d/0x270
+ udp_sendmsg+0x2bf/0x980
+ inet_sendmsg+0x67/0xa0
+ sock_sendmsg+0x38/0x50
+ ___sys_sendmsg+0x269/0x270
+ } hitcount: 77
+ { stacktrace:
+ netif_rx_internal+0xb2/0xd0
+ netif_rx+0x1c/0x60
+ loopback_xmit+0x6c/0xb0
+ dev_hard_start_xmit+0x219/0x3a0
+ __dev_queue_xmit+0x415/0x4f0
+ dev_queue_xmit_sk+0x13/0x20
+ ip_finish_output2+0x237/0x340
+ ip_finish_output+0x113/0x1d0
+ ip_output+0x66/0xc0
+ ip_local_out_sk+0x31/0x40
+ ip_send_skb+0x1a/0x50
+ udp_send_skb+0x16d/0x270
+ udp_sendmsg+0x2bf/0x980
+ inet_sendmsg+0x67/0xa0
+ sock_sendmsg+0x38/0x50
+ SYSC_sendto+0xef/0x170
+ } hitcount: 88
+ { stacktrace:
+ _do_fork+0x18e/0x330
+ SyS_clone+0x19/0x20
+ entry_SYSCALL_64_fastpath+0x12/0x6a
+ } hitcount: 244
+
+ Totals:
+ Hits: 489
+ Entries: 7
+ Dropped: 0
+
+
+2.2 Inter-event hist triggers
+-----------------------------
+
+Inter-event hist triggers are hist triggers that combine values from
+one or more other events and create a histogram using that data. Data
+from an inter-event histogram can in turn become the source for
+further combined histograms, thus providing a chain of related
+histograms, which is important for some applications.
+
+The most important example of an inter-event quantity that can be used
+in this manner is latency, which is simply a difference in timestamps
+between two events. Although latency is the most important
+inter-event quantity, note that because the support is completely
+general across the trace event subsystem, any event field can be used
+in an inter-event quantity.
+
+An example of a histogram that combines data from other histograms
+into a useful chain would be a 'wakeupswitch latency' histogram that
+combines a 'wakeup latency' histogram and a 'switch latency'
+histogram.
+
+Normally, a hist trigger specification consists of a (possibly
+compound) key along with one or more numeric values, which are
+continually updated sums associated with that key. A histogram
+specification in this case consists of individual key and value
+specifications that refer to trace event fields associated with a
+single event type.
+
+The inter-event hist trigger extension allows fields from multiple
+events to be referenced and combined into a multi-event histogram
+specification. In support of this overall goal, a few enabling
+features have been added to the hist trigger support:
+
+ - In order to compute an inter-event quantity, a value from one
+ event needs to saved and then referenced from another event. This
+ requires the introduction of support for histogram 'variables'.
+
+ - The computation of inter-event quantities and their combination
+ require some minimal amount of support for applying simple
+ expressions to variables (+ and -).
+
+ - A histogram consisting of inter-event quantities isn't logically a
+ histogram on either event (so having the 'hist' file for either
+ event host the histogram output doesn't really make sense). To
+ address the idea that the histogram is associated with a
+ combination of events, support is added allowing the creation of
+ 'synthetic' events that are events derived from other events.
+ These synthetic events are full-fledged events just like any other
+ and can be used as such, as for instance to create the
+ 'combination' histograms mentioned previously.
+
+ - A set of 'actions' can be associated with histogram entries -
+ these can be used to generate the previously mentioned synthetic
+ events, but can also be used for other purposes, such as for
+ example saving context when a 'max' latency has been hit.
+
+ - Trace events don't have a 'timestamp' associated with them, but
+ there is an implicit timestamp saved along with an event in the
+ underlying ftrace ring buffer. This timestamp is now exposed as a
+ a synthetic field named 'common_timestamp' which can be used in
+ histograms as if it were any other event field; it isn't an actual
+ field in the trace format but rather is a synthesized value that
+ nonetheless can be used as if it were an actual field. By default
+ it is in units of nanoseconds; appending '.usecs' to a
+ common_timestamp field changes the units to microseconds.
+
+A note on inter-event timestamps: If common_timestamp is used in a
+histogram, the trace buffer is automatically switched over to using
+absolute timestamps and the "global" trace clock, in order to avoid
+bogus timestamp differences with other clocks that aren't coherent
+across CPUs. This can be overridden by specifying one of the other
+trace clocks instead, using the "clock=XXX" hist trigger attribute,
+where XXX is any of the clocks listed in the tracing/trace_clock
+pseudo-file.
+
+These features are described in more detail in the following sections.
+
+2.2.1 Histogram Variables
+-------------------------
+
+Variables are simply named locations used for saving and retrieving
+values between matching events. A 'matching' event is defined as an
+event that has a matching key - if a variable is saved for a histogram
+entry corresponding to that key, any subsequent event with a matching
+key can access that variable.
+
+A variable's value is normally available to any subsequent event until
+it is set to something else by a subsequent event. The one exception
+to that rule is that any variable used in an expression is essentially
+'read-once' - once it's used by an expression in a subsequent event,
+it's reset to its 'unset' state, which means it can't be used again
+unless it's set again. This ensures not only that an event doesn't
+use an uninitialized variable in a calculation, but that that variable
+is used only once and not for any unrelated subsequent match.
+
+The basic syntax for saving a variable is to simply prefix a unique
+variable name not corresponding to any keyword along with an '=' sign
+to any event field.
+
+Either keys or values can be saved and retrieved in this way. This
+creates a variable named 'ts0' for a histogram entry with the key
+'next_pid':
+
+ # echo 'hist:keys=next_pid:vals=$ts0:ts0=common_timestamp ... >> \
+ event/trigger
+
+The ts0 variable can be accessed by any subsequent event having the
+same pid as 'next_pid'.
+
+Variable references are formed by prepending the variable name with
+the '$' sign. Thus for example, the ts0 variable above would be
+referenced as '$ts0' in expressions.
+
+Because 'vals=' is used, the common_timestamp variable value above
+will also be summed as a normal histogram value would (though for a
+timestamp it makes little sense).
+
+The below shows that a key value can also be saved in the same way:
+
+ # echo 'hist:timer_pid=common_pid:key=timer_pid ...' >> event/trigger
+
+If a variable isn't a key variable or prefixed with 'vals=', the
+associated event field will be saved in a variable but won't be summed
+as a value:
+
+ # echo 'hist:keys=next_pid:ts1=common_timestamp ... >> event/trigger
+
+Multiple variables can be assigned at the same time. The below would
+result in both ts0 and b being created as variables, with both
+common_timestamp and field1 additionally being summed as values:
+
+ # echo 'hist:keys=pid:vals=$ts0,$b:ts0=common_timestamp,b=field1 ... >> \
+ event/trigger
+
+Note that variable assignments can appear either preceding or
+following their use. The command below behaves identically to the
+command above:
+
+ # echo 'hist:keys=pid:ts0=common_timestamp,b=field1:vals=$ts0,$b ... >> \
+ event/trigger
+
+Any number of variables not bound to a 'vals=' prefix can also be
+assigned by simply separating them with colons. Below is the same
+thing but without the values being summed in the histogram:
+
+ # echo 'hist:keys=pid:ts0=common_timestamp:b=field1 ... >> event/trigger
+
+Variables set as above can be referenced and used in expressions on
+another event.
+
+For example, here's how a latency can be calculated:
+
+ # echo 'hist:keys=pid,prio:ts0=common_timestamp ... >> event1/trigger
+ # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp-$ts0 ... >> event2/trigger
+
+In the first line above, the event's timetamp is saved into the
+variable ts0. In the next line, ts0 is subtracted from the second
+event's timestamp to produce the latency, which is then assigned into
+yet another variable, 'wakeup_lat'. The hist trigger below in turn
+makes use of the wakeup_lat variable to compute a combined latency
+using the same key and variable from yet another event:
+
+ # echo 'hist:key=pid:wakeupswitch_lat=$wakeup_lat+$switchtime_lat ... >> event3/trigger
+
+2.2.2 Synthetic Events
+----------------------
+
+Synthetic events are user-defined events generated from hist trigger
+variables or fields associated with one or more other events. Their
+purpose is to provide a mechanism for displaying data spanning
+multiple events consistent with the existing and already familiar
+usage for normal events.
+
+To define a synthetic event, the user writes a simple specification
+consisting of the name of the new event along with one or more
+variables and their types, which can be any valid field type,
+separated by semicolons, to the tracing/synthetic_events file.
+
+For instance, the following creates a new event named 'wakeup_latency'
+with 3 fields: lat, pid, and prio. Each of those fields is simply a
+variable reference to a variable on another event:
+
+ # echo 'wakeup_latency \
+ u64 lat; \
+ pid_t pid; \
+ int prio' >> \
+ /sys/kernel/debug/tracing/synthetic_events
+
+Reading the tracing/synthetic_events file lists all the currently
+defined synthetic events, in this case the event defined above:
+
+ # cat /sys/kernel/debug/tracing/synthetic_events
+ wakeup_latency u64 lat; pid_t pid; int prio
+
+An existing synthetic event definition can be removed by prepending
+the command that defined it with a '!':
+
+ # echo '!wakeup_latency u64 lat pid_t pid int prio' >> \
+ /sys/kernel/debug/tracing/synthetic_events
+
+At this point, there isn't yet an actual 'wakeup_latency' event
+instantiated in the event subsytem - for this to happen, a 'hist
+trigger action' needs to be instantiated and bound to actual fields
+and variables defined on other events (see Section 6.3.3 below).
+
+Once that is done, an event instance is created, and a histogram can
+be defined using it:
+
+ # echo 'hist:keys=pid,prio,lat.log2:sort=pid,lat' >> \
+ /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+The new event is created under the tracing/events/synthetic/ directory
+and looks and behaves just like any other event:
+
+ # ls /sys/kernel/debug/tracing/events/synthetic/wakeup_latency
+ enable filter format hist id trigger
+
+Like any other event, once a histogram is enabled for the event, the
+output can be displayed by reading the event's 'hist' file.
+
+2.2.3 Hist trigger 'actions'
+----------------------------
+
+A hist trigger 'action' is a function that's executed whenever a
+histogram entry is added or updated.
+
+The default 'action' if no special function is explicity specified is
+as it always has been, to simply update the set of values associated
+with an entry. Some applications, however, may want to perform
+additional actions at that point, such as generate another event, or
+compare and save a maximum.
+
+The following additional actions are available. To specify an action
+for a given event, simply specify the action between colons in the
+hist trigger specification.
+
+ - onmatch(matching.event).<synthetic_event_name>(param list)
+
+ The 'onmatch(matching.event).<synthetic_event_name>(params)' hist
+ trigger action is invoked whenever an event matches and the
+ histogram entry would be added or updated. It causes the named
+ synthetic event to be generated with the values given in the
+ 'param list'. The result is the generation of a synthetic event
+ that consists of the values contained in those variables at the
+ time the invoking event was hit.
+
+ The 'param list' consists of one or more parameters which may be
+ either variables or fields defined on either the 'matching.event'
+ or the target event. The variables or fields specified in the
+ param list may be either fully-qualified or unqualified. If a
+ variable is specified as unqualified, it must be unique between
+ the two events. A field name used as a param can be unqualified
+ if it refers to the target event, but must be fully qualified if
+ it refers to the matching event. A fully-qualified name is of the
+ form 'system.event_name.$var_name' or 'system.event_name.field'.
+
+ The 'matching.event' specification is simply the fully qualified
+ event name of the event that matches the target event for the
+ onmatch() functionality, in the form 'system.event_name'.
+
+ Finally, the number and type of variables/fields in the 'param
+ list' must match the number and types of the fields in the
+ synthetic event being generated.
+
+ As an example the below defines a simple synthetic event and uses
+ a variable defined on the sched_wakeup_new event as a parameter
+ when invoking the synthetic event. Here we define the synthetic
+ event:
+
+ # echo 'wakeup_new_test pid_t pid' >> \
+ /sys/kernel/debug/tracing/synthetic_events
+
+ # cat /sys/kernel/debug/tracing/synthetic_events
+ wakeup_new_test pid_t pid
+
+ The following hist trigger both defines the missing testpid
+ variable and specifies an onmatch() action that generates a
+ wakeup_new_test synthetic event whenever a sched_wakeup_new event
+ occurs, which because of the 'if comm == "cyclictest"' filter only
+ happens when the executable is cyclictest:
+
+ # echo 'hist:keys=$testpid:testpid=pid:onmatch(sched.sched_wakeup_new).\
+ wakeup_new_test($testpid) if comm=="cyclictest"' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_wakeup_new/trigger
+
+ Creating and displaying a histogram based on those events is now
+ just a matter of using the fields and new synthetic event in the
+ tracing/events/synthetic directory, as usual:
+
+ # echo 'hist:keys=pid:sort=pid' >> \
+ /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/trigger
+
+ Running 'cyclictest' should cause wakeup_new events to generate
+ wakeup_new_test synthetic events which should result in histogram
+ output in the wakeup_new_test event's hist file:
+
+ # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_new_test/hist
+
+ A more typical usage would be to use two events to calculate a
+ latency. The following example uses a set of hist triggers to
+ produce a 'wakeup_latency' histogram:
+
+ First, we define a 'wakeup_latency' synthetic event:
+
+ # echo 'wakeup_latency u64 lat; pid_t pid; int prio' >> \
+ /sys/kernel/debug/tracing/synthetic_events
+
+ Next, we specify that whenever we see a sched_waking event for a
+ cyclictest thread, save the timestamp in a 'ts0' variable:
+
+ # echo 'hist:keys=$saved_pid:saved_pid=pid:ts0=common_timestamp.usecs \
+ if comm=="cyclictest"' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+ Then, when the corresponding thread is actually scheduled onto the
+ CPU by a sched_switch event, calculate the latency and use that
+ along with another variable and an event field to generate a
+ wakeup_latency synthetic event:
+
+ # echo 'hist:keys=next_pid:wakeup_lat=common_timestamp.usecs-$ts0:\
+ onmatch(sched.sched_waking).wakeup_latency($wakeup_lat,\
+ $saved_pid,next_prio) if next_comm=="cyclictest"' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+ We also need to create a histogram on the wakeup_latency synthetic
+ event in order to aggregate the generated synthetic event data:
+
+ # echo 'hist:keys=pid,prio,lat:sort=pid,lat' >> \
+ /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/trigger
+
+ Finally, once we've run cyclictest to actually generate some
+ events, we can see the output by looking at the wakeup_latency
+ synthetic event's hist file:
+
+ # cat /sys/kernel/debug/tracing/events/synthetic/wakeup_latency/hist
+
+ - onmax(var).save(field,.. .)
+
+ The 'onmax(var).save(field,...)' hist trigger action is invoked
+ whenever the value of 'var' associated with a histogram entry
+ exceeds the current maximum contained in that variable.
+
+ The end result is that the trace event fields specified as the
+ onmax.save() params will be saved if 'var' exceeds the current
+ maximum for that hist trigger entry. This allows context from the
+ event that exhibited the new maximum to be saved for later
+ reference. When the histogram is displayed, additional fields
+ displaying the saved values will be printed.
+
+ As an example the below defines a couple of hist triggers, one for
+ sched_waking and another for sched_switch, keyed on pid. Whenever
+ a sched_waking occurs, the timestamp is saved in the entry
+ corresponding to the current pid, and when the scheduler switches
+ back to that pid, the timestamp difference is calculated. If the
+ resulting latency, stored in wakeup_lat, exceeds the current
+ maximum latency, the values specified in the save() fields are
+ recoreded:
+
+ # echo 'hist:keys=pid:ts0=common_timestamp.usecs \
+ if comm=="cyclictest"' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_waking/trigger
+
+ # echo 'hist:keys=next_pid:\
+ wakeup_lat=common_timestamp.usecs-$ts0:\
+ onmax($wakeup_lat).save(next_comm,prev_pid,prev_prio,prev_comm) \
+ if next_comm=="cyclictest"' >> \
+ /sys/kernel/debug/tracing/events/sched/sched_switch/trigger
+
+ When the histogram is displayed, the max value and the saved
+ values corresponding to the max are displayed following the rest
+ of the fields:
+
+ # cat /sys/kernel/debug/tracing/events/sched/sched_switch/hist
+ { next_pid: 2255 } hitcount: 239
+ common_timestamp-ts0: 0
+ max: 27
+ next_comm: cyclictest
+ prev_pid: 0 prev_prio: 120 prev_comm: swapper/1
+
+ { next_pid: 2256 } hitcount: 2355
+ common_timestamp-ts0: 0
+ max: 49 next_comm: cyclictest
+ prev_pid: 0 prev_prio: 120 prev_comm: swapper/0
+
+ Totals:
+ Hits: 12970
+ Entries: 2
+ Dropped: 0
diff --git a/arch/Kconfig b/arch/Kconfig
index 400b9e1b2f27..2f99c0d2166a 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -17,6 +17,7 @@ config OPROFILE
tristate "OProfile system profiling"
depends on PROFILING
depends on HAVE_OPROFILE
+ depends on !PREEMPT_RT_FULL
select RING_BUFFER
select RING_BUFFER_ALLOW_SWAP
help
diff --git a/arch/alpha/include/asm/spinlock_types.h b/arch/alpha/include/asm/spinlock_types.h
index 1d5716bc060b..6883bc952d22 100644
--- a/arch/alpha/include/asm/spinlock_types.h
+++ b/arch/alpha/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef _ALPHA_SPINLOCK_TYPES_H
#define _ALPHA_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int lock;
} arch_spinlock_t;
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index d1346a160760..558b0995e94a 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -45,7 +45,7 @@ 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)
@@ -85,6 +85,7 @@ 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_SYSCALL_TRACEPOINTS
@@ -2164,7 +2165,7 @@ 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.
diff --git a/arch/arm/include/asm/irq.h b/arch/arm/include/asm/irq.h
index b6f319606e30..ad377ef73739 100644
--- a/arch/arm/include/asm/irq.h
+++ b/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);
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index 5976958647fe..a37c0803954b 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef __ASM_SPINLOCK_TYPES_H
#define __ASM_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
#define TICKET_SHIFT 16
typedef struct {
diff --git a/arch/arm/include/asm/switch_to.h b/arch/arm/include/asm/switch_to.h
index d3e937dcee4d..6ab96a2ce1f8 100644
--- a/arch/arm/include/asm/switch_to.h
+++ b/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(struct task_struct *, struct thread_info
#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)
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index 776757d1604a..1f36a4eccc72 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -49,6 +49,7 @@ struct cpu_context_save {
struct thread_info {
unsigned long flags; /* low level flags */
int preempt_count; /* 0 => preemptable, <0 => bug */
+ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */
mm_segment_t addr_limit; /* address limit */
struct task_struct *task; /* main task structure */
__u32 cpu; /* cpu */
@@ -142,7 +143,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#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
@@ -152,6 +154,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
#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)
@@ -167,7 +170,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
* 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 */
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index 608008229c7d..3866da3f7bb7 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -65,6 +65,7 @@ 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));
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index fbc707626b3e..b434c59d2b64 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -220,11 +220,18 @@ __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
@@ -239,8 +246,14 @@ 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:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 99c908226065..5ffd7188af2d 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -53,7 +53,9 @@ 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
@@ -83,8 +85,11 @@ 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)
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index a50dc00d79a2..d0a05a3bdb96 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -16,7 +16,7 @@ struct patch {
unsigned int insn;
};
-static DEFINE_SPINLOCK(patch_lock);
+static DEFINE_RAW_SPINLOCK(patch_lock);
static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
__acquires(&patch_lock)
@@ -33,7 +33,7 @@ static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags)
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 fixmap, unsigned long *flags)
clear_fixmap(fixmap);
if (flags)
- spin_unlock_irqrestore(&patch_lock, *flags);
+ raw_spin_unlock_irqrestore(&patch_lock, *flags);
else
__release(&patch_lock);
}
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index d96714e1858c..cf4e1452d4b4 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -325,6 +325,30 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
}
#ifdef CONFIG_MMU
+/*
+ * CONFIG_SPLIT_PTLOCK_CPUS results in a page->ptl lock. If the lock is not
+ * initialized by pgtable_page_ctor() then a coredump of the vector page will
+ * fail.
+ */
+static int __init vectors_user_mapping_init_page(void)
+{
+ struct page *page;
+ unsigned long addr = 0xffff0000;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ pgd = pgd_offset_k(addr);
+ pud = pud_offset(pgd, addr);
+ pmd = pmd_offset(pud, addr);
+ page = pmd_page(*(pmd));
+
+ pgtable_page_ctor(page);
+
+ return 0;
+}
+late_initcall(vectors_user_mapping_init_page);
+
#ifdef CONFIG_KUSER_HELPERS
/*
* The vectors page is always readable from user space for the
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index b67ae12503f3..7039988510bb 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -615,7 +615,8 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
*/
trace_hardirqs_off();
do {
- if (likely(thread_flags & _TIF_NEED_RESCHED)) {
+ if (likely(thread_flags & (_TIF_NEED_RESCHED |
+ _TIF_NEED_RESCHED_LAZY))) {
schedule();
} else {
if (unlikely(!user_mode(regs)))
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index c9a0a5299827..7e5122af96ca 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -236,8 +236,6 @@ int __cpu_disable(void)
flush_cache_louis();
local_flush_tlb_all();
- clear_tasks_mm_cpumask(cpu);
-
return 0;
}
@@ -255,6 +253,7 @@ void __cpu_die(unsigned int cpu)
}
pr_debug("CPU%u: shutdown\n", cpu);
+ clear_tasks_mm_cpumask(cpu);
/*
* platform_cpu_kill() is generally expected to do the powering off
* and/or cutting of clocks to the dying CPU. Optionally, this may
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index 0bee233fef9a..314cfb232a63 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -93,7 +93,7 @@ extern const struct unwind_idx __start_unwind_idx[];
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_find_idx(unsigned long addr)
/* 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_find_idx(unsigned long addr)
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(unsigned long start, unsigned long size,
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_table *tab)
if (!tab)
return;
- spin_lock_irqsave(&unwind_lock, flags);
+ raw_spin_lock_irqsave(&unwind_lock, flags);
list_del(&tab->list);
- spin_unlock_irqrestore(&unwind_lock, flags);
+ raw_spin_unlock_irqrestore(&unwind_lock, flags);
kfree(tab);
}
diff --git a/arch/arm/mach-exynos/platsmp.c b/arch/arm/mach-exynos/platsmp.c
index 5a03bffe7226..3080ea833d19 100644
--- a/arch/arm/mach-exynos/platsmp.c
+++ b/arch/arm/mach-exynos/platsmp.c
@@ -229,7 +229,7 @@ static void __iomem *scu_base_addr(void)
return (void __iomem *)(S5P_VA_SCU);
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void exynos_secondary_init(unsigned int cpu)
{
@@ -242,8 +242,8 @@ static void exynos_secondary_init(unsigned int cpu)
/*
* 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)
@@ -307,7 +307,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
* 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
@@ -334,7 +334,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
if (timeout == 0) {
printk(KERN_ERR "cpu1 power enable failed");
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return -ETIMEDOUT;
}
}
@@ -380,7 +380,7 @@ static int exynos_boot_secondary(unsigned int cpu, struct task_struct *idle)
* calibrations, then wait for it to finish
*/
fail:
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? ret : 0;
}
diff --git a/arch/arm/mach-hisi/platmcpm.c b/arch/arm/mach-hisi/platmcpm.c
index f66815c3dd07..00524abd963f 100644
--- a/arch/arm/mach-hisi/platmcpm.c
+++ b/arch/arm/mach-hisi/platmcpm.c
@@ -61,7 +61,7 @@
static void __iomem *sysctrl, *fabric;
static int hip04_cpu_table[HIP04_MAX_CLUSTERS][HIP04_MAX_CPUS_PER_CLUSTER];
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static u32 fabric_phys_addr;
/*
* [0]: bootwrapper physical address
@@ -113,7 +113,7 @@ static int hip04_boot_secondary(unsigned int l_cpu, struct task_struct *idle)
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 int l_cpu, struct task_struct *idle)
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)
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_cpu)
}
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)
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_cpu)
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_cpu)
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
diff --git a/arch/arm/mach-omap2/omap-smp.c b/arch/arm/mach-omap2/omap-smp.c
index 69df3620eca5..7cc060865c92 100644
--- a/arch/arm/mach-omap2/omap-smp.c
+++ b/arch/arm/mach-omap2/omap-smp.c
@@ -69,7 +69,7 @@ static const struct omap_smp_config omap5_cfg __initconst = {
.startup_addr = omap5_secondary_startup,
};
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
void __iomem *omap4_get_scu_base(void)
{
@@ -136,8 +136,8 @@ static void omap4_secondary_init(unsigned int cpu)
/*
* 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)
@@ -150,7 +150,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
* 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.
@@ -229,7 +229,7 @@ static int omap4_boot_secondary(unsigned int cpu, struct task_struct *idle)
* 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;
}
diff --git a/arch/arm/mach-prima2/platsmp.c b/arch/arm/mach-prima2/platsmp.c
index 75ef5d4be554..c17c86e5d860 100644
--- a/arch/arm/mach-prima2/platsmp.c
+++ b/arch/arm/mach-prima2/platsmp.c
@@ -22,7 +22,7 @@
static void __iomem *clk_base;
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void sirfsoc_secondary_init(unsigned int cpu)
{
@@ -36,8 +36,8 @@ static void sirfsoc_secondary_init(unsigned int cpu)
/*
* 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(unsigned int cpu, struct task_struct *idle)
/* 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(unsigned int cpu, struct task_struct *idle)
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
diff --git a/arch/arm/mach-qcom/platsmp.c b/arch/arm/mach-qcom/platsmp.c
index 5494c9e0c909..e8ce157d3548 100644
--- a/arch/arm/mach-qcom/platsmp.c
+++ b/arch/arm/mach-qcom/platsmp.c
@@ -46,7 +46,7 @@
extern void secondary_startup_arm(void);
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
#ifdef CONFIG_HOTPLUG_CPU
static void qcom_cpu_die(unsigned int cpu)
@@ -60,8 +60,8 @@ static void qcom_secondary_init(unsigned int cpu)
/*
* 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 int cpu, int (*func)(unsigned int))
* 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 int cpu, int (*func)(unsigned int))
* 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;
}
diff --git a/arch/arm/mach-spear/platsmp.c b/arch/arm/mach-spear/platsmp.c
index 39038a03836a..6da5c93872bf 100644
--- a/arch/arm/mach-spear/platsmp.c
+++ b/arch/arm/mach-spear/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
sync_cache_w(&pen_release);
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void __iomem *scu_base = IOMEM(VA_SCU_BASE);
@@ -47,8 +47,8 @@ static void spear13xx_secondary_init(unsigned int cpu)
/*
* 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(unsigned int cpu, struct task_struct *idle)
* 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(unsigned int cpu, struct task_struct *idle)
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
diff --git a/arch/arm/mach-sti/platsmp.c b/arch/arm/mach-sti/platsmp.c
index 231f19e17436..a3419b7003e6 100644
--- a/arch/arm/mach-sti/platsmp.c
+++ b/arch/arm/mach-sti/platsmp.c
@@ -35,7 +35,7 @@ static void write_pen_release(int val)
sync_cache_w(&pen_release);
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
static void sti_secondary_init(unsigned int cpu)
{
@@ -48,8 +48,8 @@ static void sti_secondary_init(unsigned int cpu)
/*
* 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 int cpu, struct task_struct *idle)
* 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 int cpu, struct task_struct *idle)
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 42f585379e19..93d2eccc8b60 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -434,6 +434,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
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;
@@ -501,6 +504,9 @@ do_translation_fault(unsigned long addr, unsigned int fsr,
static int
do_sect_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
{
+ if (interrupts_enabled(regs))
+ local_irq_enable();
+
do_bad_area(addr, fsr, regs);
return 0;
}
diff --git a/arch/arm/mm/highmem.c b/arch/arm/mm/highmem.c
index d02f8187b1cc..542692dbd40a 100644
--- a/arch/arm/mm/highmem.c
+++ b/arch/arm/mm/highmem.c
@@ -34,6 +34,11 @@ static inline pte_t get_fixmap_pte(unsigned long vaddr)
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
diff --git a/arch/arm/plat-versatile/platsmp.c b/arch/arm/plat-versatile/platsmp.c
index c2366510187a..6b60f582b738 100644
--- a/arch/arm/plat-versatile/platsmp.c
+++ b/arch/arm/plat-versatile/platsmp.c
@@ -32,7 +32,7 @@ static void write_pen_release(int val)
sync_cache_w(&pen_release);
}
-static DEFINE_SPINLOCK(boot_lock);
+static DEFINE_RAW_SPINLOCK(boot_lock);
void versatile_secondary_init(unsigned int cpu)
{
@@ -45,8 +45,8 @@ void versatile_secondary_init(unsigned int cpu)
/*
* 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 int cpu, struct task_struct *idle)
* 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 int cpu, struct task_struct *idle)
* now the secondary core is starting up let it run its
* calibrations, then wait for it to finish
*/
- spin_unlock(&boot_lock);
+ raw_spin_unlock(&boot_lock);
return pen_release != -1 ? -ENOSYS : 0;
}
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1bbb89d37f57..6ccd878c32c2 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -103,6 +103,7 @@ 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_SYSCALL_TRACEPOINTS
@@ -791,7 +792,7 @@ config XEN_DOM0
config XEN
bool "Xen guest support on ARM64"
- depends on ARM64 && OF
+ depends on ARM64 && OF && !PREEMPT_RT_FULL
select SWIOTLB_XEN
select PARAVIRT
help
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 70c517aa4501..2a5f05b5a19a 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -19,19 +19,19 @@ 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_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
@@ -39,7 +39,7 @@ 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
@@ -53,13 +53,13 @@ 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
@@ -67,7 +67,7 @@ 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
@@ -75,7 +75,7 @@ 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
@@ -83,13 +83,13 @@ 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
diff --git a/arch/arm64/crypto/crc32-ce-glue.c b/arch/arm64/crypto/crc32-ce-glue.c
index 34b4e3d46aab..ae055cdad8cf 100644
--- a/arch/arm64/crypto/crc32-ce-glue.c
+++ b/arch/arm64/crypto/crc32-ce-glue.c
@@ -208,7 +208,8 @@ static struct shash_alg crc32_pmull_algs[] = { {
static int __init crc32_pmull_mod_init(void)
{
- if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) && (elf_hwcap & HWCAP_PMULL)) {
+ if (IS_ENABLED(CONFIG_KERNEL_MODE_NEON) &&
+ !IS_ENABLED(CONFIG_PREEMPT_RT_BASE) && (elf_hwcap & HWCAP_PMULL)) {
crc32_pmull_algs[0].update = crc32_pmull_update;
crc32_pmull_algs[1].update = crc32c_pmull_update;
diff --git a/arch/arm64/include/asm/spinlock_types.h b/arch/arm64/include/asm/spinlock_types.h
index 55be59a35e3f..ba0cf1361f65 100644
--- a/arch/arm64/include/asm/spinlock_types.h
+++ b/arch/arm64/include/asm/spinlock_types.h
@@ -16,10 +16,6 @@
#ifndef __ASM_SPINLOCK_TYPES_H
#define __ASM_SPINLOCK_TYPES_H
-#if !defined(__LINUX_SPINLOCK_TYPES_H) && !defined(__ASM_SPINLOCK_H)
-# error "please don't include this file directly"
-#endif
-
#include <linux/types.h>
#define TICKET_SHIFT 16
diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h
index fc786d344e46..b833258b7594 100644
--- a/arch/arm64/include/asm/thread_info.h
+++ b/arch/arm64/include/asm/thread_info.h
@@ -43,6 +43,7 @@ struct thread_info {
u64 ttbr0; /* saved TTBR0_EL1 */
#endif
int preempt_count; /* 0 => preemptable, <0 => bug */
+ int preempt_lazy_count; /* 0 => preemptable, <0 => bug */
};
#define INIT_THREAD_INFO(tsk) \
@@ -82,6 +83,7 @@ void arch_setup_new_exec(void);
#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
@@ -98,6 +100,7 @@ void arch_setup_new_exec(void);
#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)
@@ -109,8 +112,9 @@ void arch_setup_new_exec(void);
#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)
diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c
index b5e43b01b396..ae26a1664436 100644
--- a/arch/arm64/kernel/asm-offsets.c
+++ b/arch/arm64/kernel/asm-offsets.c
@@ -39,6 +39,7 @@ 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));
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index c1ffa95c0ad2..c60ecb5a3916 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -637,11 +637,16 @@ 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
@@ -655,6 +660,7 @@ 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
diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c
index 43442b3a463f..81bf9545a589 100644
--- a/arch/arm64/kernel/signal.c
+++ b/arch/arm64/kernel/signal.c
@@ -756,7 +756,7 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
/* Check valid user FS if needed */
addr_limit_user_check();
- if (thread_flags & _TIF_NEED_RESCHED) {
+ if (thread_flags & _TIF_NEED_RESCHED_MASK) {
schedule();
} else {
local_irq_enable();
diff --git a/arch/blackfin/include/asm/spinlock_types.h b/arch/blackfin/include/asm/spinlock_types.h
index 1a33608c958b..103b34d3dcf6 100644
--- a/arch/blackfin/include/asm/spinlock_types.h
+++ b/arch/blackfin/include/asm/spinlock_types.h
@@ -7,10 +7,6 @@
#ifndef __ASM_SPINLOCK_TYPES_H
#define __ASM_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
#include <asm/rwlock.h>
typedef struct {
diff --git a/arch/hexagon/include/asm/spinlock_types.h b/arch/hexagon/include/asm/spinlock_types.h
index 7a906b5214a4..d8f596fec022 100644
--- a/arch/hexagon/include/asm/spinlock_types.h
+++ b/arch/hexagon/include/asm/spinlock_types.h
@@ -21,10 +21,6 @@
#ifndef _ASM_SPINLOCK_TYPES_H
#define _ASM_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int lock;
} arch_spinlock_t;
diff --git a/arch/ia64/include/asm/spinlock_types.h b/arch/ia64/include/asm/spinlock_types.h
index 6e345fefcdca..681408d6816f 100644
--- a/arch/ia64/include/asm/spinlock_types.h
+++ b/arch/ia64/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef _ASM_IA64_SPINLOCK_TYPES_H
#define _ASM_IA64_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int lock;
} arch_spinlock_t;
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index 555b11180156..6866201a7603 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1824,7 +1824,7 @@ format_mca_init_stack(void *mca_data, unsigned long offset,
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);
diff --git a/arch/m32r/include/asm/spinlock_types.h b/arch/m32r/include/asm/spinlock_types.h
index bb0d17b64198..fc6afa42fe11 100644
--- a/arch/m32r/include/asm/spinlock_types.h
+++ b/arch/m32r/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef _ASM_M32R_SPINLOCK_TYPES_H
#define _ASM_M32R_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile int slock;
} arch_spinlock_t;
diff --git a/arch/metag/include/asm/spinlock_types.h b/arch/metag/include/asm/spinlock_types.h
index cd197f1bed59..adc26e9797c5 100644
--- a/arch/metag/include/asm/spinlock_types.h
+++ b/arch/metag/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef _ASM_METAG_SPINLOCK_TYPES_H
#define _ASM_METAG_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;
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index c82457b0e733..7bb1838508de 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2519,7 +2519,7 @@ config MIPS_ASID_BITS_VARIABLE
#
config HIGHMEM
bool "High Memory Support"
- depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA
+ depends on 32BIT && CPU_SUPPORTS_HIGHMEM && SYS_SUPPORTS_HIGHMEM && !CPU_MIPS32_3_5_EVA && !PREEMPT_RT_FULL
config CPU_SUPPORTS_HIGHMEM
bool
diff --git a/arch/mips/include/asm/switch_to.h b/arch/mips/include/asm/switch_to.h
index e610473d61b8..1428b4febbc9 100644
--- a/arch/mips/include/asm/switch_to.h
+++ b/arch/mips/include/asm/switch_to.h
@@ -42,7 +42,7 @@ extern struct task_struct *ll_task;
* inline to try to keep the overhead down. If we have been forced to run on
* a "CPU" with an FPU because of a previous high level of FP computation,
* but did not actually use the FPU during the most recent time-slice (CU1
- * isn't set), we undo the restriction on cpus_allowed.
+ * isn't set), we undo the restriction on cpus_mask.
*
* We're not calling set_cpus_allowed() here, because we have no need to
* force prompt migration - we're already switching the current CPU to a
@@ -57,7 +57,7 @@ do { \
test_ti_thread_flag(__prev_ti, TIF_FPUBOUND) && \
(!(KSTK_STATUS(prev) & ST0_CU1))) { \
clear_ti_thread_flag(__prev_ti, TIF_FPUBOUND); \
- prev->cpus_allowed = prev->thread.user_cpus_allowed; \
+ prev->cpus_mask = prev->thread.user_cpus_allowed; \
} \
next->thread.emulated_fp = 0; \
} while(0)
diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c
index a7c0f97e4b0d..1a08428eedcf 100644
--- a/arch/mips/kernel/mips-mt-fpaff.c
+++ b/arch/mips/kernel/mips-mt-fpaff.c
@@ -177,7 +177,7 @@ asmlinkage long mipsmt_sys_sched_getaffinity(pid_t pid, unsigned int len,
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:
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 583aed906933..24ad7aaca5eb 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1193,12 +1193,12 @@ 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);
diff --git a/arch/mn10300/include/asm/spinlock_types.h b/arch/mn10300/include/asm/spinlock_types.h
index 32abdc89bbc7..c45230a12d60 100644
--- a/arch/mn10300/include/asm/spinlock_types.h
+++ b/arch/mn10300/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 arch_spinlock {
unsigned int slock;
} arch_spinlock_t;
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index fe418226df7f..b5658e925465 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -111,10 +111,11 @@ 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
@@ -215,6 +216,7 @@ 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_SYSCALL_TRACEPOINTS
@@ -390,7 +392,7 @@ menu "Kernel options"
config HIGHMEM
bool "High memory support"
- depends on PPC32
+ depends on PPC32 && !PREEMPT_RT_FULL
source kernel/Kconfig.hz
source kernel/Kconfig.preempt
diff --git a/arch/powerpc/include/asm/spinlock_types.h b/arch/powerpc/include/asm/spinlock_types.h
index 87adaf13b7e8..7305cb6a53e4 100644
--- a/arch/powerpc/include/asm/spinlock_types.h
+++ b/arch/powerpc/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef _ASM_POWERPC_SPINLOCK_TYPES_H
#define _ASM_POWERPC_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int slock;
} arch_spinlock_t;
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a264c3ad366b..020afb8329a1 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -36,6 +36,8 @@ struct thread_info {
int cpu; /* cpu we're on */
int preempt_count; /* 0 => preemptable,
<0 => BUG */
+ int preempt_lazy_count; /* 0 => preemptable,
+ <0 => BUG */
unsigned long local_flags; /* private flags for thread */
#ifdef CONFIG_LIVEPATCH
unsigned long *livepatch_sp;
@@ -81,8 +83,7 @@ static inline struct thread_info *current_thread_info(void)
#define TIF_SYSCALL_TRACE 0 /* syscall trace active */
#define TIF_SIGPENDING 1 /* signal pending */
#define TIF_NEED_RESCHED 2 /* rescheduling necessary */
-#define TIF_POLLING_NRFLAG 3 /* true if poll_idle() is polling
- TIF_NEED_RESCHED */
+#define TIF_NEED_RESCHED_LAZY 3 /* lazy rescheduling necessary */
#define TIF_32BIT 4 /* 32 bit binary */
#define TIF_RESTORE_TM 5 /* need to restore TM FP/VEC/VSX */
#define TIF_PATCH_PENDING 6 /* pending live patching update */
@@ -101,6 +102,8 @@ static inline struct thread_info *current_thread_info(void)
#if defined(CONFIG_PPC64)
#define TIF_ELF2ABI 18 /* function descriptors must die! */
#endif
+#define TIF_POLLING_NRFLAG 19 /* true if poll_idle() is polling
+ TIF_NEED_RESCHED */
/* as above, but as bit values */
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
@@ -120,14 +123,16 @@ static inline struct thread_info *current_thread_info(void)
#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_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
#define _TIF_USER_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \
_TIF_NOTIFY_RESUME | _TIF_UPROBE | \
- _TIF_RESTORE_TM | _TIF_PATCH_PENDING)
+ _TIF_RESTORE_TM | _TIF_PATCH_PENDING | _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 */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 2e5ea300258a..a2cb40098d7c 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/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);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index e780e1fbf6c2..dc7fe90ff6a9 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -866,7 +866,14 @@ 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 */
@@ -877,11 +884,11 @@ 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
@@ -1204,7 +1211,7 @@ 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 */
@@ -1225,7 +1232,7 @@ 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
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index c194f4c8e66b..117c1f6cab66 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -690,7 +690,7 @@ _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
@@ -752,10 +752,18 @@ 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 cr1,r8,0
ld r0,SOFTE(r1)
cmpdi r0,0
@@ -772,7 +780,7 @@ 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
/*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 0ce8b0e5d7ba..375adb3048fc 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -693,6 +693,7 @@ void irq_ctx_init(void)
}
}
+#ifndef CONFIG_PREEMPT_RT_FULL
void do_softirq_own_stack(void)
{
struct thread_info *curtp, *irqtp;
@@ -710,6 +711,7 @@ 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)
{
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index 3f7a9a2d2435..1795359d27b6 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -41,6 +41,7 @@
* We store the saved ksp_limit in the unused part
* of the STACK_FRAME_OVERHEAD
*/
+#ifndef CONFIG_PREEMPT_RT_FULL
_GLOBAL(call_do_softirq)
mflr r0
stw r0,4(r1)
@@ -57,6 +58,7 @@ _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);
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 3280953a82cf..dd2a80d190c4 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -31,6 +31,7 @@
.text
+#ifndef CONFIG_PREEMPT_RT_FULL
_GLOBAL(call_do_softirq)
mflr r0
std r0,16(r1)
@@ -41,6 +42,7 @@ _GLOBAL(call_do_softirq)
ld r0,16(r1)
mtlr r0
blr
+#endif
_GLOBAL(call_do_irq)
mflr r0
diff --git a/arch/powerpc/kvm/Kconfig b/arch/powerpc/kvm/Kconfig
index 648160334abf..9d24331fc9b4 100644
--- a/arch/powerpc/kvm/Kconfig
+++ b/arch/powerpc/kvm/Kconfig
@@ -177,6 +177,7 @@ config KVM_E500MC
config KVM_MPIC
bool "KVM in-kernel MPIC emulation"
depends on KVM && E500
+ depends on !PREEMPT_RT_FULL
select HAVE_KVM_IRQCHIP
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index 1fbb5da17dd2..ca86366d5424 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -141,7 +141,7 @@ void __spu_update_sched_info(struct spu_context *ctx)
* 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();
diff --git a/arch/powerpc/platforms/ps3/device-init.c b/arch/powerpc/platforms/ps3/device-init.c
index e48462447ff0..2670cee66064 100644
--- a/arch/powerpc/platforms/ps3/device-init.c
+++ b/arch/powerpc/platforms/ps3/device-init.c
@@ -752,7 +752,7 @@ static int ps3_notification_read_write(struct ps3_notification_device *dev,
}
pr_debug("%s:%u: notification %s issued\n", __func__, __LINE__, op);
- res = wait_event_interruptible(dev->done.wait,
+ res = swait_event_interruptible(dev->done.wait,
dev->done.done || kthread_should_stop());
if (kthread_should_stop())
res = -EINTR;
diff --git a/arch/s390/include/asm/spinlock_types.h b/arch/s390/include/asm/spinlock_types.h
index 1861a0c5dd47..74092ebaca3c 100644
--- a/arch/s390/include/asm/spinlock_types.h
+++ b/arch/s390/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef __ASM_SPINLOCK_TYPES_H
#define __ASM_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
int lock;
} __attribute__ ((aligned (4))) arch_spinlock_t;
diff --git a/arch/sh/include/asm/spinlock_types.h b/arch/sh/include/asm/spinlock_types.h
index e82369f286a2..22ca9a98bbb8 100644
--- a/arch/sh/include/asm/spinlock_types.h
+++ b/arch/sh/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef __ASM_SH_SPINLOCK_TYPES_H
#define __ASM_SH_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int lock;
} arch_spinlock_t;
diff --git a/arch/sh/kernel/irq.c b/arch/sh/kernel/irq.c
index 245dbeb20afe..e298c82d2a69 100644
--- a/arch/sh/kernel/irq.c
+++ b/arch/sh/kernel/irq.c
@@ -148,6 +148,7 @@ void irq_ctx_exit(int cpu)
hardirq_ctx[cpu] = NULL;
}
+#ifndef CONFIG_PREEMPT_RT_FULL
void do_softirq_own_stack(void)
{
struct thread_info *curctx;
@@ -175,6 +176,7 @@ void do_softirq_own_stack(void)
"r5", "r6", "r7", "r8", "r9", "r15", "t", "pr"
);
}
+#endif
#else
static inline void handle_one_irq(unsigned int irq)
{
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 4e83f950713e..7f9d71523763 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -206,12 +206,10 @@ config NR_CPUS
source kernel/Kconfig.hz
config RWSEM_GENERIC_SPINLOCK
- bool
- default y if SPARC32
+ def_bool PREEMPT_RT_FULL
config RWSEM_XCHGADD_ALGORITHM
- bool
- default y if SPARC64
+ def_bool !RWSEM_GENERIC_SPINLOCK && !PREEMPT_RT_FULL
config GENERIC_HWEIGHT
bool
diff --git a/arch/sparc/kernel/irq_64.c b/arch/sparc/kernel/irq_64.c
index d66dde833f5e..f87b3f8f4d43 100644
--- a/arch/sparc/kernel/irq_64.c
+++ b/arch/sparc/kernel/irq_64.c
@@ -855,6 +855,7 @@ void __irq_entry handler_irq(int pil, struct pt_regs *regs)
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()];
@@ -869,6 +870,7 @@ void do_softirq_own_stack(void)
__asm__ __volatile__("mov %0, %%sp"
: : "r" (orig_sp));
}
+#endif
#ifdef CONFIG_HOTPLUG_CPU
void fixup_irqs(void)
diff --git a/arch/tile/include/asm/setup.h b/arch/tile/include/asm/setup.h
index 2a0347af0702..670fa2f4cfc3 100644
--- a/arch/tile/include/asm/setup.h
+++ b/arch/tile/include/asm/setup.h
@@ -49,7 +49,7 @@ int hardwall_ipi_valid(int cpu);
/* Hook hardwall code into changes in affinity. */
#define arch_set_cpus_allowed(p, new_mask) do { \
- if (!cpumask_equal(&p->cpus_allowed, new_mask)) \
+ if (!cpumask_equal(p->cpus_ptr, new_mask)) \
hardwall_deactivate_all(p); \
} while (0)
#endif
diff --git a/arch/tile/include/asm/spinlock_types.h b/arch/tile/include/asm/spinlock_types.h
index a71f59b49c50..9311c6ff2abc 100644
--- a/arch/tile/include/asm/spinlock_types.h
+++ b/arch/tile/include/asm/spinlock_types.h
@@ -15,10 +15,6 @@
#ifndef _ASM_TILE_SPINLOCK_TYPES_H
#define _ASM_TILE_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
#ifdef __tilegx__
/* Low 15 bits are "next"; high 15 bits are "current". */
diff --git a/arch/tile/kernel/hardwall.c b/arch/tile/kernel/hardwall.c
index 2fd1694ac1d0..98f4fb696289 100644
--- a/arch/tile/kernel/hardwall.c
+++ b/arch/tile/kernel/hardwall.c
@@ -590,12 +590,12 @@ static int hardwall_activate(struct hardwall_info *info)
* Get our affinity; if we're not bound to this tile uniquely,
* we can't access the network registers.
*/
- if (cpumask_weight(&p->cpus_allowed) != 1)
+ if (p->nr_cpus_allowed != 1)
return -EPERM;
/* Make sure we are bound to a cpu assigned to this resource. */
cpu = smp_processor_id();
- BUG_ON(cpumask_first(&p->cpus_allowed) != cpu);
+ BUG_ON(cpumask_first(p->cpus_ptr) != cpu);
if (!cpumask_test_cpu(cpu, &info->cpumask))
return -EINVAL;
@@ -621,17 +621,17 @@ static int hardwall_activate(struct hardwall_info *info)
* Deactivate a task's hardwall. Must hold lock for hardwall_type.
* This method may be called from exit_thread(), so we don't want to
* rely on too many fields of struct task_struct still being valid.
- * We assume the cpus_allowed, pid, and comm fields are still valid.
+ * We assume the nr_cpus_allowed, pid, and comm fields are still valid.
*/
static void _hardwall_deactivate(struct hardwall_type *hwt,
struct task_struct *task)
{
struct thread_struct *ts = &task->thread;
- if (cpumask_weight(&task->cpus_allowed) != 1) {
+ if (task->nr_cpus_allowed != 1) {
pr_err("pid %d (%s) releasing %s hardwall with an affinity mask containing %d cpus!\n",
task->pid, task->comm, hwt->name,
- cpumask_weight(&task->cpus_allowed));
+ task->nr_cpus_allowed);
BUG();
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7483cd514c32..f40962b7f158 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -169,6 +169,7 @@ config X86
select HAVE_HARDLOCKUP_DETECTOR_PERF if PERF_EVENTS && HAVE_PERF_EVENTS_NMI
select HAVE_PERF_REGS
select HAVE_PERF_USER_STACK_DUMP
+ select HAVE_PREEMPT_LAZY
select HAVE_RCU_TABLE_FREE
select HAVE_REGS_AND_STACK_ACCESS_API
select HAVE_RELIABLE_STACKTRACE if X86_64 && UNWINDER_FRAME_POINTER && STACK_VALIDATION
@@ -255,8 +256,11 @@ 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
@@ -931,7 +935,7 @@ config IOMMU_HELPER
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.
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index c690ddc78c03..7a3138d33e33 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -387,14 +387,14 @@ static int ecb_encrypt(struct skcipher_request *req)
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;
}
@@ -409,14 +409,14 @@ static int ecb_decrypt(struct skcipher_request *req)
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;
}
@@ -431,14 +431,14 @@ static int cbc_encrypt(struct skcipher_request *req)
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;
}
@@ -453,14 +453,14 @@ static int cbc_decrypt(struct skcipher_request *req)
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;
}
@@ -510,18 +510,20 @@ static int ctr_crypt(struct skcipher_request *req)
err = skcipher_walk_virt(&walk, req, true);
- kernel_fpu_begin();
while ((nbytes = walk.nbytes) >= AES_BLOCK_SIZE) {
+ kernel_fpu_begin();
aesni_ctr_enc_tfm(ctx, walk.dst.virt.addr, walk.src.virt.addr,
nbytes & AES_BLOCK_MASK, walk.iv);
+ kernel_fpu_end();
nbytes &= AES_BLOCK_SIZE - 1;
err = skcipher_walk_done(&walk, nbytes);
}
if (walk.nbytes) {
+ kernel_fpu_begin();
ctr_crypt_final(ctx, &walk);
+ kernel_fpu_end();
err = skcipher_walk_done(&walk, 0);
}
- kernel_fpu_end();
return err;
}
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index 60907c139c4e..0902db7d326a 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -206,6 +206,20 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ camellia_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -221,16 +235,19 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_ecb_enc_16way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
}
while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
}
+ camellia_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -251,16 +268,19 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
if (nbytes >= CAMELLIA_AESNI_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_ecb_dec_16way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_AESNI_PARALLEL_BLOCKS;
}
while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
}
+ camellia_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index d96429da88eb..3b8e91841039 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -210,6 +210,21 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void camellia_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ camellia_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void camellia_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = CAMELLIA_BLOCK_SIZE;
@@ -225,10 +240,12 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_enc_blk_2way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
}
+ camellia_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
camellia_enc_blk(ctx->ctx, srcdst, srcdst);
@@ -249,10 +266,12 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
while (nbytes >= CAMELLIA_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
camellia_dec_blk_2way(ctx->ctx, srcdst, srcdst);
srcdst += bsize * CAMELLIA_PARALLEL_BLOCKS;
nbytes -= bsize * CAMELLIA_PARALLEL_BLOCKS;
}
+ camellia_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
camellia_dec_blk(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 575292a33bdf..0a4b0a222b18 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -59,7 +59,7 @@ static inline void cast5_fpu_end(bool fpu_enabled)
static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
bool enc)
{
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct cast5_ctx *ctx = crypto_blkcipher_ctx(desc->tfm);
const unsigned int bsize = CAST5_BLOCK_SIZE;
unsigned int nbytes;
@@ -73,7 +73,7 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
u8 *wsrc = walk->src.virt.addr;
u8 *wdst = walk->dst.virt.addr;
- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+ fpu_enabled = cast5_fpu_begin(false, nbytes);
/* Process multi-block batch */
if (nbytes >= bsize * CAST5_PARALLEL_BLOCKS) {
@@ -102,10 +102,9 @@ static int ecb_crypt(struct blkcipher_desc *desc, struct blkcipher_walk *walk,
} while (nbytes >= bsize);
done:
+ cast5_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, walk, nbytes);
}
-
- cast5_fpu_end(fpu_enabled);
return err;
}
@@ -226,7 +225,7 @@ done:
static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct blkcipher_walk walk;
int err;
@@ -235,12 +234,11 @@ static int cbc_decrypt(struct blkcipher_desc *desc, struct scatterlist *dst,
desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
while ((nbytes = walk.nbytes)) {
- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+ fpu_enabled = cast5_fpu_begin(false, nbytes);
nbytes = __cbc_decrypt(desc, &walk);
+ cast5_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
-
- cast5_fpu_end(fpu_enabled);
return err;
}
@@ -309,7 +307,7 @@ done:
static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
struct scatterlist *src, unsigned int nbytes)
{
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct blkcipher_walk walk;
int err;
@@ -318,13 +316,12 @@ static int ctr_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
desc->flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
while ((nbytes = walk.nbytes) >= CAST5_BLOCK_SIZE) {
- fpu_enabled = cast5_fpu_begin(fpu_enabled, nbytes);
+ fpu_enabled = cast5_fpu_begin(false, nbytes);
nbytes = __ctr_crypt(desc, &walk);
+ cast5_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
- cast5_fpu_end(fpu_enabled);
-
if (walk.nbytes) {
ctr_crypt_final(desc, &walk);
err = blkcipher_walk_done(desc, &walk, 0);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 50e684768c55..8caf9ba8c1da 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -205,19 +205,33 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void cast6_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ cast6_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void cast6_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = CAST6_BLOCK_SIZE;
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
cast6_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+ cast6_fpu_end_rt(ctx);
return;
}
-
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
__cast6_encrypt(ctx->ctx, srcdst, srcdst);
}
@@ -228,10 +242,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * CAST6_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = cast6_fpu_begin(ctx->fpu_enabled, nbytes);
cast6_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+ cast6_fpu_end_rt(ctx);
return;
}
diff --git a/arch/x86/crypto/chacha20_glue.c b/arch/x86/crypto/chacha20_glue.c
index 1e6af1b35f7b..e7809fd2a4fd 100644
--- a/arch/x86/crypto/chacha20_glue.c
+++ b/arch/x86/crypto/chacha20_glue.c
@@ -81,23 +81,24 @@ static int chacha20_simd(struct skcipher_request *req)
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;
}
diff --git a/arch/x86/crypto/glue_helper.c b/arch/x86/crypto/glue_helper.c
index d61e57960fe0..c67560d9718a 100644
--- a/arch/x86/crypto/glue_helper.c
+++ b/arch/x86/crypto/glue_helper.c
@@ -40,7 +40,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
void *ctx = crypto_blkcipher_ctx(desc->tfm);
const unsigned int bsize = 128 / 8;
unsigned int nbytes, i, func_bytes;
- bool fpu_enabled = false;
+ bool fpu_enabled;
int err;
err = blkcipher_walk_virt(desc, walk);
@@ -50,7 +50,7 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
u8 *wdst = walk->dst.virt.addr;
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- desc, fpu_enabled, nbytes);
+ desc, false, nbytes);
for (i = 0; i < gctx->num_funcs; i++) {
func_bytes = bsize * gctx->funcs[i].num_blocks;
@@ -72,10 +72,10 @@ static int __glue_ecb_crypt_128bit(const struct common_glue_ctx *gctx,
}
done:
+ glue_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, walk, nbytes);
}
- glue_fpu_end(fpu_enabled);
return err;
}
@@ -192,7 +192,7 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
struct scatterlist *src, unsigned int nbytes)
{
const unsigned int bsize = 128 / 8;
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct blkcipher_walk walk;
int err;
@@ -201,12 +201,12 @@ int glue_cbc_decrypt_128bit(const struct common_glue_ctx *gctx,
while ((nbytes = walk.nbytes)) {
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- desc, fpu_enabled, nbytes);
+ desc, false, nbytes);
nbytes = __glue_cbc_decrypt_128bit(gctx, desc, &walk);
+ glue_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
- glue_fpu_end(fpu_enabled);
return err;
}
EXPORT_SYMBOL_GPL(glue_cbc_decrypt_128bit);
@@ -275,7 +275,7 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
struct scatterlist *src, unsigned int nbytes)
{
const unsigned int bsize = 128 / 8;
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct blkcipher_walk walk;
int err;
@@ -284,13 +284,12 @@ int glue_ctr_crypt_128bit(const struct common_glue_ctx *gctx,
while ((nbytes = walk.nbytes) >= bsize) {
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- desc, fpu_enabled, nbytes);
+ desc, false, nbytes);
nbytes = __glue_ctr_crypt_128bit(gctx, desc, &walk);
+ glue_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
}
- glue_fpu_end(fpu_enabled);
-
if (walk.nbytes) {
glue_ctr_crypt_final_128bit(
gctx->funcs[gctx->num_funcs - 1].fn_u.ctr, desc, &walk);
@@ -380,7 +379,7 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
void *tweak_ctx, void *crypt_ctx)
{
const unsigned int bsize = 128 / 8;
- bool fpu_enabled = false;
+ bool fpu_enabled;
struct blkcipher_walk walk;
int err;
@@ -393,21 +392,21 @@ int glue_xts_crypt_128bit(const struct common_glue_ctx *gctx,
/* set minimum length to bsize, for tweak_fn */
fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
- desc, fpu_enabled,
+ desc, false,
nbytes < bsize ? bsize : nbytes);
-
/* calculate first value of T */
tweak_fn(tweak_ctx, walk.iv, walk.iv);
+ glue_fpu_end(fpu_enabled);
while (nbytes) {
+ fpu_enabled = glue_fpu_begin(bsize, gctx->fpu_blocks_limit,
+ desc, false, nbytes);
nbytes = __glue_xts_crypt_128bit(gctx, crypt_ctx, desc, &walk);
+ glue_fpu_end(fpu_enabled);
err = blkcipher_walk_done(desc, &walk, nbytes);
nbytes = walk.nbytes;
}
-
- glue_fpu_end(fpu_enabled);
-
return err;
}
EXPORT_SYMBOL_GPL(glue_xts_crypt_128bit);
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 870f6d812a2d..5c806bf39f1d 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -184,6 +184,21 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ serpent_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = SERPENT_BLOCK_SIZE;
@@ -199,10 +214,12 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
}
+ serpent_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
__serpent_encrypt(ctx->ctx, srcdst, srcdst);
@@ -223,10 +240,12 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
}
while (nbytes >= SERPENT_PARALLEL_BLOCKS * bsize) {
+ kernel_fpu_resched();
serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
srcdst += bsize * SERPENT_PARALLEL_BLOCKS;
nbytes -= bsize * SERPENT_PARALLEL_BLOCKS;
}
+ serpent_fpu_end_rt(ctx);
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
__serpent_decrypt(ctx->ctx, srcdst, srcdst);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 6f778d3daa22..46dcbdbd0518 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -218,16 +218,31 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ serpent_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = SERPENT_BLOCK_SIZE;
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
serpent_ecb_enc_8way_avx(ctx->ctx, srcdst, srcdst);
+ serpent_fpu_end_rt(ctx);
return;
}
@@ -241,10 +256,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
serpent_ecb_dec_8way_avx(ctx->ctx, srcdst, srcdst);
+ serpent_fpu_end_rt(ctx);
return;
}
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index ac0e831943f5..d35f607d067f 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -187,16 +187,31 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void serpent_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ serpent_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void serpent_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = SERPENT_BLOCK_SIZE;
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
serpent_enc_blk_xway(ctx->ctx, srcdst, srcdst);
+ serpent_fpu_end_rt(ctx);
return;
}
@@ -210,10 +225,10 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
struct crypt_priv *ctx = priv;
int i;
- ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
-
if (nbytes == bsize * SERPENT_PARALLEL_BLOCKS) {
+ ctx->fpu_enabled = serpent_fpu_begin(ctx->fpu_enabled, nbytes);
serpent_dec_blk_xway(ctx->ctx, srcdst, srcdst);
+ serpent_fpu_end_rt(ctx);
return;
}
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index b7a3904b953c..de00fe24927e 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -218,6 +218,21 @@ struct crypt_priv {
bool fpu_enabled;
};
+#ifdef CONFIG_PREEMPT_RT_FULL
+static void twofish_fpu_end_rt(struct crypt_priv *ctx)
+{
+ bool fpu_enabled = ctx->fpu_enabled;
+
+ if (!fpu_enabled)
+ return;
+ twofish_fpu_end(fpu_enabled);
+ ctx->fpu_enabled = false;
+}
+
+#else
+static void twofish_fpu_end_rt(struct crypt_priv *ctx) { }
+#endif
+
static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
{
const unsigned int bsize = TF_BLOCK_SIZE;
@@ -228,12 +243,16 @@ static void encrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
twofish_ecb_enc_8way(ctx->ctx, srcdst, srcdst);
+ twofish_fpu_end_rt(ctx);
return;
}
- for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+ for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+ kernel_fpu_resched();
twofish_enc_blk_3way(ctx->ctx, srcdst, srcdst);
+ }
+ twofish_fpu_end_rt(ctx);
nbytes %= bsize * 3;
for (i = 0; i < nbytes / bsize; i++, srcdst += bsize)
@@ -250,11 +269,15 @@ static void decrypt_callback(void *priv, u8 *srcdst, unsigned int nbytes)
if (nbytes == bsize * TWOFISH_PARALLEL_BLOCKS) {
twofish_ecb_dec_8way(ctx->ctx, srcdst, srcdst);
+ twofish_fpu_end_rt(ctx);
return;
}
- for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3)
+ for (i = 0; i < nbytes / (bsize * 3); i++, srcdst += bsize * 3) {
+ kernel_fpu_resched();
twofish_dec_blk_3way(ctx->ctx, srcdst, srcdst);
+ }
+ twofish_fpu_end_rt(ctx);
nbytes %= bsize * 3;
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 60e21ccfb6d6..0e27f35febe7 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -133,7 +133,7 @@ static long syscall_trace_enter(struct pt_regs *regs)
#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 pt_regs *regs, u32 cached_flags)
/* 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);
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 60c4c342316c..cd0c7c56e2dd 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -350,8 +350,25 @@ END(ret_from_exception)
ENTRY(resume_kernel)
DISABLE_INTERRUPTS(CLBR_ANY)
.Lneed_resched:
+ # preempt count == 0 + NEED_RS set?
cmpl $0, PER_CPU_VAR(__preempt_count)
+#ifndef CONFIG_PREEMPT_LAZY
jnz restore_all
+#else
+ jz test_int_off
+
+ # atleast preempt count == 0 ?
+ cmpl $_PREEMPT_ENABLED,PER_CPU_VAR(__preempt_count)
+ jne restore_all
+
+ movl PER_CPU_VAR(current_task), %ebp
+ cmpl $0,TASK_TI_preempt_lazy_count(%ebp) # non-zero preempt_lazy_count ?
+ jnz restore_all
+
+ testl $_TIF_NEED_RESCHED_LAZY, TASK_TI_flags(%ebp)
+ jz restore_all
+test_int_off:
+#endif
testl $X86_EFLAGS_IF, PT_EFLAGS(%esp) # interrupts off (exception path) ?
jz restore_all
call preempt_schedule_irq
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f7bfa701219b..e5168e9672e7 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -633,7 +633,23 @@ 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:
@@ -988,6 +1004,7 @@ 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
@@ -998,6 +1015,7 @@ 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
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index a9caac9d4a72..18b31f22ca5d 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -25,6 +25,7 @@ extern void __kernel_fpu_begin(void);
extern void __kernel_fpu_end(void);
extern void kernel_fpu_begin(void);
extern void kernel_fpu_end(void);
+extern void kernel_fpu_resched(void);
extern bool irq_fpu_usable(void);
/*
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 7f2dbd91fc74..22992c837795 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -86,17 +86,46 @@ static __always_inline void __preempt_count_sub(int val)
* 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
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 5f9012ff52ed..39117e57caf2 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -28,6 +28,19 @@ typedef struct {
#define SA_IA32_ABI 0x02000000u
#define SA_X32_ABI 0x01000000u
+/*
+ * Because some traps use the IST stack, we must keep preemption
+ * disabled while calling do_trap(), but do_trap() may call
+ * force_sig_info() which will grab the signal spin_locks for the
+ * task, which in PREEMPT_RT_FULL are mutexes. By defining
+ * ARCH_RT_DELAYS_SIGNAL_SEND the force_sig_info() will set
+ * TIF_NOTIFY_RESUME and set up the signal to be sent on exit of the
+ * trap.
+ */
+#if defined(CONFIG_PREEMPT_RT_FULL)
+#define ARCH_RT_DELAYS_SIGNAL_SEND
+#endif
+
#ifndef CONFIG_COMPAT
typedef sigset_t compat_sigset_t;
#endif
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 371b3a4af000..06613a805b25 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -60,7 +60,7 @@
*/
static __always_inline void boot_init_stack_canary(void)
{
- u64 canary;
+ u64 uninitialized_var(canary);
u64 tsc;
#ifdef CONFIG_X86_64
@@ -71,8 +71,14 @@ static __always_inline void boot_init_stack_canary(void)
* of randomness. The TSC only matters for very early init,
* there it already has some randomness on most systems. Later
* on during the bootup the random pool has true entropy too.
+ * For preempt-rt we need to weaken the randomness a bit, as
+ * we can't call into the random generator from atomic context
+ * due to locking constraints. We just leave canary
+ * uninitialized and use the TSC based randomness on top of it.
*/
+#ifndef CONFIG_PREEMPT_RT_FULL
get_random_bytes(&canary, sizeof(canary));
+#endif
tsc = rdtsc();
canary += tsc + (tsc << 32UL);
canary &= CANARY_MASK;
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 95ff2d7f553f..b1c9129f64fc 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -56,11 +56,14 @@ 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, \
}
#define init_stack (init_thread_union.stack)
@@ -69,6 +72,10 @@ struct thread_info {
#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
/*
@@ -85,6 +92,7 @@ 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 */
@@ -112,6 +120,7 @@ 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)
@@ -153,6 +162,8 @@ 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)
/*
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 7cac79802ad2..2ac6e347bdc5 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -643,9 +643,9 @@ struct bau_control {
cycles_t send_message;
cycles_t period_end;
cycles_t period_time;
- spinlock_t uvhub_lock;
- spinlock_t queue_lock;
- spinlock_t disable_lock;
+ raw_spinlock_t uvhub_lock;
+ raw_spinlock_t queue_lock;
+ raw_spinlock_t disable_lock;
/* tunables */
int max_concurr;
int max_concurr_const;
@@ -847,15 +847,15 @@ static inline int atom_asr(short i, struct atomic_short *v)
* to be lowered below the current 'v'. atomic_add_unless can only stop
* on equal.
*/
-static inline int atomic_inc_unless_ge(spinlock_t *lock, atomic_t *v, int u)
+static inline int atomic_inc_unless_ge(raw_spinlock_t *lock, atomic_t *v, int u)
{
- spin_lock(lock);
+ raw_spin_lock(lock);
if (atomic_read(v) >= u) {
- spin_unlock(lock);
+ raw_spin_unlock(lock);
return 0;
}
atomic_inc(v);
- spin_unlock(lock);
+ raw_spin_unlock(lock);
return 1;
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 3b89b27945ff..9744fbb856af 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1690,7 +1690,8 @@ static bool io_apic_level_ack_pending(struct mp_chip_data *data)
static inline bool ioapic_irqd_mask(struct irq_data *data)
{
/* If we are moving the irq we need to mask it */
- if (unlikely(irqd_is_setaffinity_pending(data))) {
+ if (unlikely(irqd_is_setaffinity_pending(data) &&
+ !irqd_irq_inprogress(data))) {
mask_ioapic_irq(data);
return true;
}
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index 76417a9aab73..62c3e27c8e1c 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -38,6 +38,7 @@ void common(void) {
BLANK();
OFFSET(TASK_TI_flags, task_struct, thread_info.flags);
+ OFFSET(TASK_TI_preempt_lazy_count, task_struct, thread_info.preempt_lazy_count);
OFFSET(TASK_addr_limit, task_struct, thread.addr_limit);
BLANK();
@@ -94,6 +95,7 @@ void common(void) {
BLANK();
DEFINE(PTREGS_SIZE, sizeof(struct pt_regs));
+ DEFINE(_PREEMPT_ENABLED, PREEMPT_ENABLED);
/* TLB state for the entry code */
OFFSET(TLB_STATE_user_pcid_flush_mask, tlb_state, user_pcid_flush_mask);
diff --git a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
index 7f85b76f43bc..9e74b805070f 100644
--- a/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
+++ b/arch/x86/kernel/cpu/mcheck/dev-mcelog.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/kmod.h>
#include <linux/poll.h>
+#include <linux/swork.h>
#include "mce-internal.h"
@@ -86,13 +87,43 @@ static void mce_do_trigger(struct work_struct *work)
static DECLARE_WORK(mce_trigger_work, mce_do_trigger);
-
-void mce_work_trigger(void)
+static void __mce_work_trigger(struct swork_event *event)
{
if (mce_helper[0])
schedule_work(&mce_trigger_work);
}
+#ifdef CONFIG_PREEMPT_RT_FULL
+static bool notify_work_ready __read_mostly;
+static struct swork_event notify_work;
+
+static int mce_notify_work_init(void)
+{
+ int err;
+
+ err = swork_get();
+ if (err)
+ return err;
+
+ INIT_SWORK(&notify_work, __mce_work_trigger);
+ notify_work_ready = true;
+ return 0;
+}
+
+void mce_work_trigger(void)
+{
+ if (notify_work_ready)
+ swork_queue(&notify_work);
+}
+
+#else
+void mce_work_trigger(void)
+{
+ __mce_work_trigger(NULL);
+}
+static inline int mce_notify_work_init(void) { return 0; }
+#endif
+
static ssize_t
show_trigger(struct device *s, struct device_attribute *attr, char *buf)
{
@@ -356,7 +387,7 @@ static __init int dev_mcelog_init_device(void)
return err;
}
-
+ mce_notify_work_init();
mce_register_decode_chain(&dev_mcelog_nb);
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 98e4e4dc4a3b..5cce2ee3b9f6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -42,6 +42,7 @@
#include <linux/debugfs.h>
#include <linux/irq_work.h>
#include <linux/export.h>
+#include <linux/jiffies.h>
#include <linux/jump_label.h>
#include <asm/intel-family.h>
@@ -1365,7 +1366,7 @@ int memory_failure(unsigned long pfn, int vector, int flags)
static unsigned long check_interval = INITIAL_CHECK_INTERVAL;
static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */
-static DEFINE_PER_CPU(struct timer_list, mce_timer);
+static DEFINE_PER_CPU(struct hrtimer, mce_timer);
static unsigned long mce_adjust_timer_default(unsigned long interval)
{
@@ -1374,27 +1375,19 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default;
-static void __start_timer(struct timer_list *t, unsigned long interval)
+static void __start_timer(struct hrtimer *t, unsigned long iv)
{
- unsigned long when = jiffies + interval;
- unsigned long flags;
-
- local_irq_save(flags);
-
- if (!timer_pending(t) || time_before(when, t->expires))
- mod_timer(t, round_jiffies(when));
+ if (!iv)
+ return;
- local_irq_restore(flags);
+ hrtimer_start_range_ns(t, ns_to_ktime(jiffies_to_usecs(iv) * 1000ULL),
+ 0, HRTIMER_MODE_REL_PINNED);
}
-static void mce_timer_fn(unsigned long data)
+static enum hrtimer_restart mce_timer_fn(struct hrtimer *timer)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
- int cpu = smp_processor_id();
unsigned long iv;
- WARN_ON(cpu != data);
-
iv = __this_cpu_read(mce_next_interval);
if (mce_available(this_cpu_ptr(&cpu_info))) {
@@ -1417,7 +1410,11 @@ static void mce_timer_fn(unsigned long data)
done:
__this_cpu_write(mce_next_interval, iv);
- __start_timer(t, iv);
+ if (!iv)
+ return HRTIMER_NORESTART;
+
+ hrtimer_forward_now(timer, ns_to_ktime(jiffies_to_nsecs(iv)));
+ return HRTIMER_RESTART;
}
/*
@@ -1425,7 +1422,7 @@ done:
*/
void mce_timer_kick(unsigned long interval)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
+ struct hrtimer *t = this_cpu_ptr(&mce_timer);
unsigned long iv = __this_cpu_read(mce_next_interval);
__start_timer(t, interval);
@@ -1440,7 +1437,7 @@ static void mce_timer_delete_all(void)
int cpu;
for_each_online_cpu(cpu)
- del_timer_sync(&per_cpu(mce_timer, cpu));
+ hrtimer_cancel(&per_cpu(mce_timer, cpu));
}
/*
@@ -1769,7 +1766,7 @@ static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c)
}
}
-static void mce_start_timer(struct timer_list *t)
+static void mce_start_timer(struct hrtimer *t)
{
unsigned long iv = check_interval * HZ;
@@ -1782,18 +1779,19 @@ static void mce_start_timer(struct timer_list *t)
static void __mcheck_cpu_setup_timer(void)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
- unsigned int cpu = smp_processor_id();
+ struct hrtimer *t = this_cpu_ptr(&mce_timer);
- setup_pinned_timer(t, mce_timer_fn, cpu);
+ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ t->function = mce_timer_fn;
}
static void __mcheck_cpu_init_timer(void)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
- unsigned int cpu = smp_processor_id();
+ struct hrtimer *t = this_cpu_ptr(&mce_timer);
+
+ hrtimer_init(t, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ t->function = mce_timer_fn;
- setup_pinned_timer(t, mce_timer_fn, cpu);
mce_start_timer(t);
}
@@ -2309,7 +2307,7 @@ static int mce_cpu_dead(unsigned int cpu)
static int mce_cpu_online(unsigned int cpu)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
+ struct hrtimer *t = this_cpu_ptr(&mce_timer);
int ret;
mce_device_create(cpu);
@@ -2326,10 +2324,10 @@ static int mce_cpu_online(unsigned int cpu)
static int mce_cpu_pre_down(unsigned int cpu)
{
- struct timer_list *t = this_cpu_ptr(&mce_timer);
+ struct hrtimer *t = this_cpu_ptr(&mce_timer);
mce_disable_cpu();
- del_timer_sync(t);
+ hrtimer_cancel(t);
mce_threshold_remove_device(cpu);
mce_device_remove(cpu);
return 0;
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index f92a6593de1e..7128beaf594c 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -137,6 +137,18 @@ void kernel_fpu_end(void)
}
EXPORT_SYMBOL_GPL(kernel_fpu_end);
+void kernel_fpu_resched(void)
+{
+ WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+
+ if (should_resched(PREEMPT_OFFSET)) {
+ kernel_fpu_end();
+ cond_resched();
+ kernel_fpu_begin();
+ }
+}
+EXPORT_SYMBOL_GPL(kernel_fpu_resched);
+
/*
* Save the FPU state (mark it for reload if necessary):
*
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c1bdbd3d3232..e370e1b8b7ff 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -129,6 +129,7 @@ void irq_ctx_init(int cpu)
cpu, per_cpu(hardirq_stack, cpu), per_cpu(softirq_stack, cpu));
}
+#ifndef CONFIG_PREEMPT_RT_FULL
void do_softirq_own_stack(void)
{
struct irq_stack *irqstk;
@@ -145,6 +146,7 @@ void do_softirq_own_stack(void)
call_on_stack(__do_softirq, isp);
}
+#endif
bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
{
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 5224c6099184..9b2b1f0409c5 100644
--- a/arch/x86/kernel/process_32.c
+++ b/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>
@@ -198,6 +199,35 @@ start_thread(struct pt_regs *regs, unsigned long new_ip, unsigned long new_sp)
}
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.
@@ -273,6 +303,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_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
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 6d0fbff71d7a..92f13ac70ad4 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2120,7 +2120,7 @@ int kvm_create_lapic(struct kvm_vcpu *vcpu)
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;
/*
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 2f3fe25639b3..f1bd2c2c5c04 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6168,6 +6168,13 @@ int kvm_arch_init(void *opaque)
goto out;
}
+#ifdef CONFIG_PREEMPT_RT_FULL
+ if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
+ printk(KERN_ERR "RT requires X86_FEATURE_CONSTANT_TSC\n");
+ return -EOPNOTSUPP;
+ }
+#endif
+
r = kvm_mmu_module_init();
if (r)
goto out_free_percpu;
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 6d18b70ed5a9..f752724c22e8 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -32,10 +32,11 @@ EXPORT_SYMBOL(kunmap);
*/
void *kmap_atomic_prot(struct page *page, pgprot_t prot)
{
+ pte_t pte = mk_pte(page, prot);
unsigned long vaddr;
int idx, type;
- preempt_disable();
+ preempt_disable_nort();
pagefault_disable();
if (!PageHighMem(page))
@@ -45,7 +46,10 @@ void *kmap_atomic_prot(struct page *page, pgprot_t prot)
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);
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index ada98b39b8ad..585f6829653b 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -56,6 +56,7 @@ 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;
@@ -65,7 +66,12 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot)
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;
@@ -113,6 +119,9 @@ 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();
}
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 0b530c53de1f..2df1ee9a55f2 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -740,9 +740,9 @@ static void destination_plugged(struct bau_desc *bau_desc,
quiesce_local_uvhub(hmaster);
- spin_lock(&hmaster->queue_lock);
+ raw_spin_lock(&hmaster->queue_lock);
reset_with_ipi(&bau_desc->distribution, bcp);
- spin_unlock(&hmaster->queue_lock);
+ raw_spin_unlock(&hmaster->queue_lock);
end_uvhub_quiesce(hmaster);
@@ -762,9 +762,9 @@ static void destination_timeout(struct bau_desc *bau_desc,
quiesce_local_uvhub(hmaster);
- spin_lock(&hmaster->queue_lock);
+ raw_spin_lock(&hmaster->queue_lock);
reset_with_ipi(&bau_desc->distribution, bcp);
- spin_unlock(&hmaster->queue_lock);
+ raw_spin_unlock(&hmaster->queue_lock);
end_uvhub_quiesce(hmaster);
@@ -785,7 +785,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
cycles_t tm1;
hmaster = bcp->uvhub_master;
- spin_lock(&hmaster->disable_lock);
+ raw_spin_lock(&hmaster->disable_lock);
if (!bcp->baudisabled) {
stat->s_bau_disabled++;
tm1 = get_cycles();
@@ -798,7 +798,7 @@ static void disable_for_period(struct bau_control *bcp, struct ptc_stats *stat)
}
}
}
- spin_unlock(&hmaster->disable_lock);
+ raw_spin_unlock(&hmaster->disable_lock);
}
static void count_max_concurr(int stat, struct bau_control *bcp,
@@ -861,7 +861,7 @@ static void record_send_stats(cycles_t time1, cycles_t time2,
*/
static void uv1_throttle(struct bau_control *hmaster, struct ptc_stats *stat)
{
- spinlock_t *lock = &hmaster->uvhub_lock;
+ raw_spinlock_t *lock = &hmaster->uvhub_lock;
atomic_t *v;
v = &hmaster->active_descriptor_count;
@@ -995,7 +995,7 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
struct bau_control *hmaster;
hmaster = bcp->uvhub_master;
- spin_lock(&hmaster->disable_lock);
+ raw_spin_lock(&hmaster->disable_lock);
if (bcp->baudisabled && (get_cycles() >= bcp->set_bau_on_time)) {
stat->s_bau_reenabled++;
for_each_present_cpu(tcpu) {
@@ -1007,10 +1007,10 @@ static int check_enable(struct bau_control *bcp, struct ptc_stats *stat)
tbcp->period_giveups = 0;
}
}
- spin_unlock(&hmaster->disable_lock);
+ raw_spin_unlock(&hmaster->disable_lock);
return 0;
}
- spin_unlock(&hmaster->disable_lock);
+ raw_spin_unlock(&hmaster->disable_lock);
return -1;
}
@@ -1941,9 +1941,9 @@ static void __init init_per_cpu_tunables(void)
bcp->cong_reps = congested_reps;
bcp->disabled_period = sec_2_cycles(disabled_period);
bcp->giveup_limit = giveup_limit;
- spin_lock_init(&bcp->queue_lock);
- spin_lock_init(&bcp->uvhub_lock);
- spin_lock_init(&bcp->disable_lock);
+ raw_spin_lock_init(&bcp->queue_lock);
+ raw_spin_lock_init(&bcp->uvhub_lock);
+ raw_spin_lock_init(&bcp->disable_lock);
}
}
diff --git a/arch/x86/platform/uv/uv_time.c b/arch/x86/platform/uv/uv_time.c
index b082d71b08ee..badf377efc21 100644
--- a/arch/x86/platform/uv/uv_time.c
+++ b/arch/x86/platform/uv/uv_time.c
@@ -57,7 +57,7 @@ static DEFINE_PER_CPU(struct clock_event_device, cpu_ced);
/* There is one of these allocated per node */
struct uv_rtc_timer_head {
- spinlock_t lock;
+ raw_spinlock_t lock;
/* next cpu waiting for timer, local node relative: */
int next_cpu;
/* number of cpus on this node: */
@@ -177,7 +177,7 @@ static __init int uv_rtc_allocate_timers(void)
uv_rtc_deallocate_timers();
return -ENOMEM;
}
- spin_lock_init(&head->lock);
+ raw_spin_lock_init(&head->lock);
head->ncpus = uv_blade_nr_possible_cpus(bid);
head->next_cpu = -1;
blade_info[bid] = head;
@@ -231,7 +231,7 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
unsigned long flags;
int next_cpu;
- spin_lock_irqsave(&head->lock, flags);
+ raw_spin_lock_irqsave(&head->lock, flags);
next_cpu = head->next_cpu;
*t = expires;
@@ -243,12 +243,12 @@ static int uv_rtc_set_timer(int cpu, u64 expires)
if (uv_setup_intr(cpu, expires)) {
*t = ULLONG_MAX;
uv_rtc_find_next_timer(head, pnode);
- spin_unlock_irqrestore(&head->lock, flags);
+ raw_spin_unlock_irqrestore(&head->lock, flags);
return -ETIME;
}
}
- spin_unlock_irqrestore(&head->lock, flags);
+ raw_spin_unlock_irqrestore(&head->lock, flags);
return 0;
}
@@ -267,7 +267,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
unsigned long flags;
int rc = 0;
- spin_lock_irqsave(&head->lock, flags);
+ raw_spin_lock_irqsave(&head->lock, flags);
if ((head->next_cpu == bcpu && uv_read_rtc(NULL) >= *t) || force)
rc = 1;
@@ -279,7 +279,7 @@ static int uv_rtc_unset_timer(int cpu, int force)
uv_rtc_find_next_timer(head, pnode);
}
- spin_unlock_irqrestore(&head->lock, flags);
+ raw_spin_unlock_irqrestore(&head->lock, flags);
return rc;
}
@@ -299,13 +299,17 @@ static int uv_rtc_unset_timer(int cpu, int force)
static u64 uv_read_rtc(struct clocksource *cs)
{
unsigned long offset;
+ u64 cycles;
+ preempt_disable();
if (uv_get_min_hub_revision_id() == 1)
offset = 0;
else
offset = (uv_blade_processor_id() * L1_CACHE_BYTES) % PAGE_SIZE;
- return (u64)uv_read_local_mmr(UVH_RTC | offset);
+ cycles = (u64)uv_read_local_mmr(UVH_RTC | offset);
+ preempt_enable();
+ return cycles;
}
/*
diff --git a/arch/xtensa/include/asm/spinlock_types.h b/arch/xtensa/include/asm/spinlock_types.h
index bb1fe6c1816e..8a22f1e7b6c9 100644
--- a/arch/xtensa/include/asm/spinlock_types.h
+++ b/arch/xtensa/include/asm/spinlock_types.h
@@ -2,10 +2,6 @@
#ifndef __ASM_SPINLOCK_TYPES_H
#define __ASM_SPINLOCK_TYPES_H
-#ifndef __LINUX_SPINLOCK_TYPES_H
-# error "please don't include this file directly"
-#endif
-
typedef struct {
volatile unsigned int slock;
} arch_spinlock_t;
diff --git a/block/blk-core.c b/block/blk-core.c
index 68bae6338ad4..81ab56cf7efa 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -116,6 +116,9 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
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;
@@ -280,7 +283,7 @@ EXPORT_SYMBOL(blk_start_queue_async);
void blk_start_queue(struct request_queue *q)
{
lockdep_assert_held(q->queue_lock);
- WARN_ON(!in_interrupt() && !irqs_disabled());
+ WARN_ON_NONRT(!in_interrupt() && !irqs_disabled());
WARN_ON_ONCE(q->mq_ops);
queue_flag_clear(QUEUE_FLAG_STOPPED, q);
@@ -808,12 +811,21 @@ void blk_queue_exit(struct request_queue *q)
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(unsigned long data)
@@ -890,6 +902,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id)
__set_bit(QUEUE_FLAG_BYPASS, &q->queue_flags);
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.
@@ -3308,7 +3321,7 @@ static void queue_unplugged(struct request_queue *q, unsigned int depth,
blk_run_queue_async(q);
else
__blk_run_queue(q);
- spin_unlock(q->queue_lock);
+ spin_unlock_irq(q->queue_lock);
}
static void flush_plug_callbacks(struct blk_plug *plug, bool from_schedule)
@@ -3356,7 +3369,6 @@ EXPORT_SYMBOL(blk_check_plugged);
void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
{
struct request_queue *q;
- unsigned long flags;
struct request *rq;
LIST_HEAD(list);
unsigned int depth;
@@ -3376,11 +3388,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
q = NULL;
depth = 0;
- /*
- * Save and disable interrupts here, to avoid doing it for every
- * queue lock we have to take.
- */
- local_irq_save(flags);
while (!list_empty(&list)) {
rq = list_entry_rq(list.next);
list_del_init(&rq->queuelist);
@@ -3393,7 +3400,7 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
queue_unplugged(q, depth, from_schedule);
q = rq->q;
depth = 0;
- spin_lock(q->queue_lock);
+ spin_lock_irq(q->queue_lock);
}
/*
@@ -3420,8 +3427,6 @@ void blk_flush_plug_list(struct blk_plug *plug, bool from_schedule)
*/
if (q)
queue_unplugged(q, depth, from_schedule);
-
- local_irq_restore(flags);
}
void blk_finish_plug(struct blk_plug *plug)
@@ -3631,6 +3636,8 @@ 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);
diff --git a/block/blk-ioc.c b/block/blk-ioc.c
index f23311e4b201..ca9ea624f159 100644
--- a/block/blk-ioc.c
+++ b/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_struct *work)
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;
}
}
diff --git a/block/blk-mq.c b/block/blk-mq.c
index 49979c095f31..0815a6599ab3 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -339,6 +339,9 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
/* tag was already set */
rq->extra_len = 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;
@@ -533,12 +536,24 @@ void blk_mq_end_request(struct request *rq, blk_status_t error)
}
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)
{
@@ -558,19 +573,27 @@ static void __blk_mq_complete_request(struct request *rq)
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();
}
/**
@@ -1238,14 +1261,14 @@ static void __blk_mq_delay_run_hw_queue(struct blk_mq_hw_ctx *hctx, bool async,
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_schedule_delayed_work_on(blk_mq_hctx_next_cpu(hctx),
@@ -2863,10 +2886,9 @@ static bool blk_mq_poll_hybrid_sleep(struct request_queue *q,
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 (test_bit(REQ_ATOM_COMPLETE, &rq->atomic_flags))
break;
diff --git a/block/blk-mq.h b/block/blk-mq.h
index 877237e09083..d944750bade0 100644
--- a/block/blk-mq.h
+++ b/block/blk-mq.h
@@ -98,12 +98,12 @@ static inline struct blk_mq_ctx *__blk_mq_get_ctx(struct request_queue *q,
*/
static inline struct blk_mq_ctx *blk_mq_get_ctx(struct request_queue *q)
{
- return __blk_mq_get_ctx(q, get_cpu());
+ return __blk_mq_get_ctx(q, get_cpu_light());
}
static inline void blk_mq_put_ctx(struct blk_mq_ctx *ctx)
{
- put_cpu();
+ put_cpu_light();
}
struct blk_mq_alloc_data {
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index 01e2b353a2b9..e8c0d4945f5a 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -53,6 +53,7 @@ static void trigger_softirq(void *data)
raise_softirq_irqoff(BLOCK_SOFTIRQ);
local_irq_restore(flags);
+ preempt_check_resched_rt();
}
/*
@@ -91,6 +92,7 @@ static int blk_softirq_cpu_dead(unsigned int cpu)
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();
}
/**
diff --git a/block/bounce.c b/block/bounce.c
index 1d05c422c932..0101ffefddc4 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -66,11 +66,11 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom)
unsigned long flags;
unsigned char *vto;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
vto = kmap_atomic(to->bv_page);
memcpy(vto + to->bv_offset, vfrom, to->bv_len);
kunmap_atomic(vto);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
#else /* CONFIG_HIGHMEM */
diff --git a/crypto/algapi.c b/crypto/algapi.c
index 50eb828db767..7bce92a6599a 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -731,13 +731,13 @@ EXPORT_SYMBOL_GPL(crypto_spawn_tfm2);
int crypto_register_notifier(struct notifier_block *nb)
{
- return blocking_notifier_chain_register(&crypto_chain, nb);
+ return srcu_notifier_chain_register(&crypto_chain, nb);
}
EXPORT_SYMBOL_GPL(crypto_register_notifier);
int crypto_unregister_notifier(struct notifier_block *nb)
{
- return blocking_notifier_chain_unregister(&crypto_chain, nb);
+ return srcu_notifier_chain_unregister(&crypto_chain, nb);
}
EXPORT_SYMBOL_GPL(crypto_unregister_notifier);
diff --git a/crypto/api.c b/crypto/api.c
index 941cd4c6c7ec..2b1cf0c1dcea 100644
--- a/crypto/api.c
+++ b/crypto/api.c
@@ -31,7 +31,7 @@ EXPORT_SYMBOL_GPL(crypto_alg_list);
DECLARE_RWSEM(crypto_alg_sem);
EXPORT_SYMBOL_GPL(crypto_alg_sem);
-BLOCKING_NOTIFIER_HEAD(crypto_chain);
+SRCU_NOTIFIER_HEAD(crypto_chain);
EXPORT_SYMBOL_GPL(crypto_chain);
static struct crypto_alg *crypto_larval_wait(struct crypto_alg *alg);
@@ -236,10 +236,10 @@ int crypto_probing_notify(unsigned long val, void *v)
{
int ok;
- ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+ ok = srcu_notifier_call_chain(&crypto_chain, val, v);
if (ok == NOTIFY_DONE) {
request_module("cryptomgr");
- ok = blocking_notifier_call_chain(&crypto_chain, val, v);
+ ok = srcu_notifier_call_chain(&crypto_chain, val, v);
}
return ok;
diff --git a/crypto/internal.h b/crypto/internal.h
index f07320423191..333d985088fe 100644
--- a/crypto/internal.h
+++ b/crypto/internal.h
@@ -47,7 +47,7 @@ struct crypto_larval {
extern struct list_head crypto_alg_list;
extern struct rw_semaphore crypto_alg_sem;
-extern struct blocking_notifier_head crypto_chain;
+extern struct srcu_notifier_head crypto_chain;
#ifdef CONFIG_PROC_FS
void __init crypto_init_proc(void);
@@ -143,7 +143,7 @@ static inline int crypto_is_moribund(struct crypto_alg *alg)
static inline void crypto_notify(unsigned long val, void *v)
{
- blocking_notifier_call_chain(&crypto_chain, val, v);
+ srcu_notifier_call_chain(&crypto_chain, val, v);
}
#endif /* _CRYPTO_INTERNAL_H */
diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h
index 95eed442703f..50bc5b61d899 100644
--- a/drivers/acpi/acpica/acglobal.h
+++ b/drivers/acpi/acpica/acglobal.h
@@ -116,7 +116,7 @@ ACPI_GLOBAL(u8, acpi_gbl_global_lock_pending);
* interrupt level
*/
ACPI_GLOBAL(acpi_spinlock, acpi_gbl_gpe_lock); /* For GPE data structs and registers */
-ACPI_GLOBAL(acpi_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
+ACPI_GLOBAL(acpi_raw_spinlock, acpi_gbl_hardware_lock); /* For ACPI H/W except GPE registers */
ACPI_GLOBAL(acpi_spinlock, acpi_gbl_reference_count_lock);
/* Mutex for _OSI support */
diff --git a/drivers/acpi/acpica/hwregs.c b/drivers/acpi/acpica/hwregs.c
index acb417b58bbb..ea49e08c263f 100644
--- a/drivers/acpi/acpica/hwregs.c
+++ b/drivers/acpi/acpica/hwregs.c
@@ -428,14 +428,14 @@ acpi_status acpi_hw_clear_acpi_status(void)
ACPI_BITMASK_ALL_FIXED_STATUS,
ACPI_FORMAT_UINT64(acpi_gbl_xpm1a_status.address)));
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
/* Clear the fixed events in PM1 A/B */
status = acpi_hw_register_write(ACPI_REGISTER_PM1_STATUS,
ACPI_BITMASK_ALL_FIXED_STATUS);
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
if (ACPI_FAILURE(status)) {
goto exit;
diff --git a/drivers/acpi/acpica/hwxface.c b/drivers/acpi/acpica/hwxface.c
index 34684ae89981..fb84983e1839 100644
--- a/drivers/acpi/acpica/hwxface.c
+++ b/drivers/acpi/acpica/hwxface.c
@@ -373,7 +373,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
return_ACPI_STATUS(AE_BAD_PARAMETER);
}
- lock_flags = acpi_os_acquire_lock(acpi_gbl_hardware_lock);
+ raw_spin_lock_irqsave(acpi_gbl_hardware_lock, lock_flags);
/*
* At this point, we know that the parent register is one of the
@@ -434,7 +434,7 @@ acpi_status acpi_write_bit_register(u32 register_id, u32 value)
unlock_and_exit:
- acpi_os_release_lock(acpi_gbl_hardware_lock, lock_flags);
+ raw_spin_unlock_irqrestore(acpi_gbl_hardware_lock, lock_flags);
return_ACPI_STATUS(status);
}
diff --git a/drivers/acpi/acpica/utmutex.c b/drivers/acpi/acpica/utmutex.c
index 586354788018..3a3c2a86437f 100644
--- a/drivers/acpi/acpica/utmutex.c
+++ b/drivers/acpi/acpica/utmutex.c
@@ -88,7 +88,7 @@ acpi_status acpi_ut_mutex_initialize(void)
return_ACPI_STATUS (status);
}
- status = acpi_os_create_lock (&acpi_gbl_hardware_lock);
+ status = acpi_os_create_raw_lock (&acpi_gbl_hardware_lock);
if (ACPI_FAILURE (status)) {
return_ACPI_STATUS (status);
}
@@ -145,7 +145,7 @@ void acpi_ut_mutex_terminate(void)
/* Delete the spinlocks */
acpi_os_delete_lock(acpi_gbl_gpe_lock);
- acpi_os_delete_lock(acpi_gbl_hardware_lock);
+ acpi_os_delete_raw_lock(acpi_gbl_hardware_lock);
acpi_os_delete_lock(acpi_gbl_reference_count_lock);
/* Delete the reader/writer lock */
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index cc2f2e35f4c2..0f0bc86e02df 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -679,9 +679,9 @@ unsigned int ata_sff_data_xfer_noirq(struct ata_queued_cmd *qc, unsigned char *b
unsigned long flags;
unsigned int consumed;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
consumed = ata_sff_data_xfer32(qc, buf, buflen, rw);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
return consumed;
}
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index 2d7178f7754e..c1cf87718c2e 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -60,7 +60,6 @@ struct brd_device {
/*
* Look up and return a brd's page for a given sector.
*/
-static DEFINE_MUTEX(brd_mutex);
static struct page *brd_lookup_page(struct brd_device *brd, sector_t sector)
{
pgoff_t idx;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 5b8992beffec..40345483a022 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -116,12 +116,20 @@ ssize_t zcomp_available_show(const char *comp, char *buf)
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 cpu, struct hlist_node *node)
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;
}
diff --git a/drivers/block/zram/zcomp.h b/drivers/block/zram/zcomp.h
index 41c1002a7d7d..d424eafcbf8e 100644
--- a/drivers/block/zram/zcomp.h
+++ b/drivers/block/zram/zcomp.h
@@ -14,6 +14,7 @@ struct zcomp_strm {
/* compression/decompression buffer */
void *buffer;
struct crypto_comp *tfm;
+ spinlock_t zcomp_lock;
};
/* dynamic per-device compression frontend */
diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c
index f149d3e61234..9839656465ea 100644
--- a/drivers/block/zram/zram_drv.c
+++ b/drivers/block/zram/zram_drv.c
@@ -756,6 +756,30 @@ static DEVICE_ATTR_RO(io_stat);
static DEVICE_ATTR_RO(mm_stat);
static DEVICE_ATTR_RO(debug_stat);
+#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_ACCESS, &zram->table[index].value);
+}
+
+static void zram_slot_unlock(struct zram *zram, u32 index)
+{
+ __clear_bit(ZRAM_ACCESS, &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_ACCESS, &zram->table[index].value);
@@ -765,6 +789,7 @@ static void zram_slot_unlock(struct zram *zram, u32 index)
{
bit_spin_unlock(ZRAM_ACCESS, &zram->table[index].value);
}
+#endif
static void zram_meta_free(struct zram *zram, u64 disksize)
{
@@ -794,6 +819,7 @@ static bool zram_meta_alloc(struct zram *zram, u64 disksize)
return false;
}
+ zram_meta_init_table_locks(zram, num_pages);
return true;
}
@@ -845,6 +871,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
unsigned long handle;
unsigned int size;
void *src, *dst;
+ struct zcomp_strm *zstrm;
if (zram_wb_enabled(zram)) {
zram_slot_lock(zram, index);
@@ -879,6 +906,7 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
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);
@@ -886,14 +914,13 @@ static int __zram_bvec_read(struct zram *zram, struct page *page, u32 index,
kunmap_atomic(dst);
ret = 0;
} else {
- struct zcomp_strm *zstrm = zcomp_stream_get(zram->comp);
dst = kmap_atomic(page);
ret = zcomp_decompress(zstrm, src, size, dst);
kunmap_atomic(dst);
- zcomp_stream_put(zram->comp);
}
zs_unmap_object(zram->mem_pool, handle);
+ zcomp_stream_put(zram->comp);
zram_slot_unlock(zram, index);
/* Should NEVER happen. Return bio error if it does. */
diff --git a/drivers/block/zram/zram_drv.h b/drivers/block/zram/zram_drv.h
index 31762db861e3..a417c96b8f3f 100644
--- a/drivers/block/zram/zram_drv.h
+++ b/drivers/block/zram/zram_drv.h
@@ -77,6 +77,9 @@ struct zram_table_entry {
unsigned long element;
};
unsigned long value;
+#ifdef CONFIG_PREEMPT_RT_BASE
+ spinlock_t lock;
+#endif
};
struct zram_stats {
diff --git a/drivers/char/random.c b/drivers/char/random.c
index ea4dbfa30657..c72a7f0b4494 100644
--- a/drivers/char/random.c
+++ b/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>
@@ -856,7 +857,7 @@ static int crng_fast_load(const char *cp, size_t len)
invalidate_batched_entropy();
crng_init = 1;
wake_up_interruptible(&crng_init_wait);
- pr_notice("random: fast init done\n");
+ /* pr_notice("random: fast init done\n"); */
}
return 1;
}
@@ -941,17 +942,21 @@ static void crng_reseed(struct crng_state *crng, struct entropy_store *r)
crng_init = 2;
process_random_ready_list();
wake_up_interruptible(&crng_init_wait);
- pr_notice("random: crng init done\n");
+ /* pr_notice("random: crng init done\n"); */
if (unseeded_warning.missed) {
+#if 0
pr_notice("random: %d get_random_xx warning(s) missed "
"due to ratelimiting\n",
unseeded_warning.missed);
+#endif
unseeded_warning.missed = 0;
}
if (urandom_warning.missed) {
+#if 0
pr_notice("random: %d urandom warning(s) missed "
"due to ratelimiting\n",
urandom_warning.missed);
+#endif
urandom_warning.missed = 0;
}
}
@@ -1122,8 +1127,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
} sample;
long delta, delta2, delta3;
- preempt_disable();
-
sample.jiffies = jiffies;
sample.cycles = random_get_entropy();
sample.num = num;
@@ -1164,7 +1167,6 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num)
*/
credit_entropy_bits(r, min_t(int, fls(delta>>1), 11));
}
- preempt_enable();
}
void add_input_randomness(unsigned int type, unsigned int code,
@@ -1221,28 +1223,27 @@ static __u32 get_reg(struct fast_pool *f, struct pt_regs *regs)
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);
@@ -2200,6 +2201,7 @@ static rwlock_t batched_entropy_reset_lock = __RW_LOCK_UNLOCKED(batched_entropy_
* 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;
@@ -2220,7 +2222,7 @@ 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) {
@@ -2230,12 +2232,13 @@ 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;
@@ -2250,7 +2253,7 @@ 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) {
@@ -2260,7 +2263,7 @@ u32 get_random_u32(void)
ret = batch->entropy_u32[batch->position++];
if (use_lock)
read_unlock_irqrestore(&batched_entropy_reset_lock, flags);
- put_cpu_var(batched_entropy_u32);
+ put_locked_var(batched_entropy_u32_lock, batched_entropy_u32);
return ret;
}
EXPORT_SYMBOL(get_random_u32);
diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c
index 50b59a69dc33..cbdb0a6c5337 100644
--- a/drivers/char/tpm/tpm_tis.c
+++ b/drivers/char/tpm/tpm_tis.c
@@ -52,6 +52,31 @@ static inline struct tpm_tis_tcg_phy *to_tpm_tis_tcg_phy(struct tpm_tis_data *da
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");
@@ -149,7 +174,7 @@ static int tpm_tcg_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len,
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;
}
@@ -176,7 +201,7 @@ static int tpm_tcg_write32(struct tpm_tis_data *data, u32 addr, u32 value)
{
struct tpm_tis_tcg_phy *phy = to_tpm_tis_tcg_phy(data);
- iowrite32(value, phy->iobase + addr);
+ tpm_tis_iowrite32(value, phy->iobase, addr);
return 0;
}
diff --git a/drivers/clocksource/tcb_clksrc.c b/drivers/clocksource/tcb_clksrc.c
index 9de47d4d2d9e..05f4b88bb955 100644
--- a/drivers/clocksource/tcb_clksrc.c
+++ b/drivers/clocksource/tcb_clksrc.c
@@ -25,8 +25,7 @@
* this 32 bit free-running counter. the second channel is not used.
*
* - The third channel may be used to provide a 16-bit clockevent
- * source, used in either periodic or oneshot mode. This runs
- * at 32 KiHZ, and can handle delays of up to two seconds.
+ * source, used in either periodic or oneshot mode.
*
* A boot clocksource and clockevent source are also currently needed,
* unless the relevant platforms (ARM/AT91, AVR32/AT32) are changed so
@@ -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_clkevt(struct clock_event_device *clkevt)
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_event_device *d)
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_event_device *d)
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_event_device *d)
/* 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 *handle)
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 atmel_tc *tc, int clk32k_divisor_idx)
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 atmel_tc *tc, int clk32k_divisor_idx)
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;
diff --git a/drivers/clocksource/timer-atmel-pit.c b/drivers/clocksource/timer-atmel-pit.c
index ec8a4376f74f..d813ea388562 100644
--- a/drivers/clocksource/timer-atmel-pit.c
+++ b/drivers/clocksource/timer-atmel-pit.c
@@ -46,6 +46,7 @@ struct pit_data {
u32 cycle;
u32 cnt;
unsigned int irq;
+ bool irq_requested;
struct clk *mck;
};
@@ -96,15 +97,29 @@ static int pit_clkevt_shutdown(struct clock_event_device *dev)
/* disable irq, leaving the clocksource active */
pit_write(data->base, AT91_PIT_MR, (data->cycle - 1) | AT91_PIT_PITEN);
+ if (data->irq_requested) {
+ free_irq(data->irq, data);
+ data->irq_requested = false;
+ }
return 0;
}
+static irqreturn_t at91sam926x_pit_interrupt(int irq, void *dev_id);
/*
* Clockevent device: interrupts every 1/HZ (== pit_cycles * MCK/16)
*/
static int pit_clkevt_set_periodic(struct clock_event_device *dev)
{
struct pit_data *data = clkevt_to_pit_data(dev);
+ int ret;
+
+ ret = request_irq(data->irq, at91sam926x_pit_interrupt,
+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+ "at91_tick", data);
+ if (ret)
+ panic(pr_fmt("Unable to setup IRQ\n"));
+
+ data->irq_requested = true;
/* update clocksource counter */
data->cnt += data->cycle * PIT_PICNT(pit_read(data->base, AT91_PIT_PIVR));
@@ -230,15 +245,6 @@ static int __init at91sam926x_pit_dt_init(struct device_node *node)
return ret;
}
- /* Set up irq handler */
- ret = request_irq(data->irq, at91sam926x_pit_interrupt,
- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- "at91_tick", data);
- if (ret) {
- pr_err("Unable to setup IRQ\n");
- return ret;
- }
-
/* Set up and register clockevents */
data->clkevt.name = "pit";
data->clkevt.features = CLOCK_EVT_FEAT_PERIODIC;
diff --git a/drivers/clocksource/timer-atmel-st.c b/drivers/clocksource/timer-atmel-st.c
index d2e660f475af..c63b96cfc23e 100644
--- a/drivers/clocksource/timer-atmel-st.c
+++ b/drivers/clocksource/timer-atmel-st.c
@@ -115,18 +115,29 @@ static void clkdev32k_disable_and_flush_irq(void)
last_crtr = read_CRTR();
}
+static int atmel_st_irq;
+
static int clkevt32k_shutdown(struct clock_event_device *evt)
{
clkdev32k_disable_and_flush_irq();
irqmask = 0;
regmap_write(regmap_st, AT91_ST_IER, irqmask);
+ free_irq(atmel_st_irq, regmap_st);
return 0;
}
static int clkevt32k_set_oneshot(struct clock_event_device *dev)
{
+ int ret;
+
clkdev32k_disable_and_flush_irq();
+ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+ "at91_tick", regmap_st);
+ if (ret)
+ panic(pr_fmt("Unable to setup IRQ\n"));
+
/*
* ALM for oneshot irqs, set by next_event()
* before 32 seconds have passed.
@@ -139,8 +150,16 @@ static int clkevt32k_set_oneshot(struct clock_event_device *dev)
static int clkevt32k_set_periodic(struct clock_event_device *dev)
{
+ int ret;
+
clkdev32k_disable_and_flush_irq();
+ ret = request_irq(atmel_st_irq, at91rm9200_timer_interrupt,
+ IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
+ "at91_tick", regmap_st);
+ if (ret)
+ panic(pr_fmt("Unable to setup IRQ\n"));
+
/* PIT for periodic irqs; fixed rate of 1/HZ */
irqmask = AT91_ST_PITS;
regmap_write(regmap_st, AT91_ST_PIMR, timer_latch);
@@ -198,7 +217,7 @@ static int __init atmel_st_timer_init(struct device_node *node)
{
struct clk *sclk;
unsigned int sclk_rate, val;
- int irq, ret;
+ int ret;
regmap_st = syscon_node_to_regmap(node);
if (IS_ERR(regmap_st)) {
@@ -212,21 +231,12 @@ static int __init atmel_st_timer_init(struct device_node *node)
regmap_read(regmap_st, AT91_ST_SR, &val);
/* Get the interrupts property */
- irq = irq_of_parse_and_map(node, 0);
- if (!irq) {
+ atmel_st_irq = irq_of_parse_and_map(node, 0);
+ if (!atmel_st_irq) {
pr_err("Unable to get IRQ from DT\n");
return -EINVAL;
}
- /* Make IRQs happen for the system timer */
- ret = request_irq(irq, at91rm9200_timer_interrupt,
- IRQF_SHARED | IRQF_TIMER | IRQF_IRQPOLL,
- "at91_tick", regmap_st);
- if (ret) {
- pr_err("Unable to setup IRQ\n");
- return ret;
- }
-
sclk = of_clk_get(node, 0);
if (IS_ERR(sclk)) {
pr_err("Unable to get slow clock\n");
diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c
index a782ce87715c..19d265948526 100644
--- a/drivers/connector/cn_proc.c
+++ b/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 = { CN_IDX_PROC, CN_VAL_PROC };
/* 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_msg *msg)
*/
cn_netlink_send(msg, 0, CN_IDX_PROC, GFP_NOWAIT);
- preempt_enable();
+ local_unlock(send_msg_lock);
}
void proc_fork_connector(struct task_struct *task)
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 35f71825b7f3..bb4a6160d0f7 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -125,7 +125,7 @@ config X86_POWERNOW_K7_ACPI
config X86_POWERNOW_K8
tristate "AMD Opteron/Athlon64 PowerNow!"
- depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
+ depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ && !PREEMPT_RT_BASE
help
This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
Support for K10 and newer processors is now in acpi-cpufreq.
diff --git a/drivers/gpu/drm/i915/i915_gem_timeline.c b/drivers/gpu/drm/i915/i915_gem_timeline.c
index c597ce277a04..c1108d3921f8 100644
--- a/drivers/gpu/drm/i915/i915_gem_timeline.c
+++ b/drivers/gpu/drm/i915/i915_gem_timeline.c
@@ -33,11 +33,8 @@ static void __intel_timeline_init(struct intel_timeline *tl,
{
tl->fence_context = context;
tl->common = parent;
-#ifdef CONFIG_DEBUG_SPINLOCK
- __raw_spin_lock_init(&tl->lock.rlock, lockname, lockclass);
-#else
spin_lock_init(&tl->lock);
-#endif
+ lockdep_set_class_and_name(&tl->lock, lockclass, lockname);
init_request_active(&tl->last_request, NULL);
INIT_LIST_HEAD(&tl->requests);
i915_syncmap_init(&tl->sync);
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 20a471ad0ad2..5d34d48a8b7b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -867,6 +867,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
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)
@@ -918,6 +919,7 @@ static bool i915_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
*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);
diff --git a/drivers/gpu/drm/i915/intel_sprite.c b/drivers/gpu/drm/i915/intel_sprite.c
index 41e31a454604..7e0cadf51b31 100644
--- a/drivers/gpu/drm/i915/intel_sprite.c
+++ b/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>
@@ -67,7 +68,7 @@ int intel_usecs_to_scanlines(const struct drm_display_mode *adjusted_mode,
}
#define VBLANK_EVASION_TIME_US 100
-
+static DEFINE_LOCAL_IRQ_LOCK(pipe_update_lock);
/**
* intel_pipe_update_start() - start update of a set of display registers
* @crtc: the crtc of which the registers are going to be updated
@@ -102,7 +103,7 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
VBLANK_EVASION_TIME_US);
max = vblank_start - 1;
- local_irq_disable();
+ local_lock_irq(pipe_update_lock);
if (min <= 0 || max <= 0)
return;
@@ -132,11 +133,11 @@ void intel_pipe_update_start(struct intel_crtc *crtc)
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);
@@ -201,7 +202,7 @@ void intel_pipe_update_end(struct intel_crtc *crtc)
crtc->base.state->event = NULL;
}
- local_irq_enable();
+ local_unlock_irq(pipe_update_lock);
if (intel_vgpu_active(dev_priv))
return;
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index ddfe91efa61e..3157bcf6428f 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -1839,6 +1839,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
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)
@@ -1931,6 +1932,7 @@ int radeon_get_crtc_scanoutpos(struct drm_device *dev, unsigned int pipe,
*etime = ktime_get();
/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+ preempt_enable_rt();
/* Decode into vertical and horizontal scanout position. */
*vpos = position & 0x1fff;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 2cd134dd94d2..cedf225d4182 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -966,6 +966,8 @@ 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))
@@ -1009,7 +1011,7 @@ 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);
}
diff --git a/drivers/ide/alim15x3.c b/drivers/ide/alim15x3.c
index 36f76e28a0bf..394f142f90c7 100644
--- a/drivers/ide/alim15x3.c
+++ b/drivers/ide/alim15x3.c
@@ -234,7 +234,7 @@ static int init_chipset_ali15x3(struct pci_dev *dev)
isa_dev = pci_get_device(PCI_VENDOR_ID_AL, PCI_DEVICE_ID_AL_M1533, NULL);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
if (m5229_revision < 0xC2) {
/*
@@ -325,7 +325,7 @@ out:
}
pci_dev_put(north);
pci_dev_put(isa_dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
return 0;
}
diff --git a/drivers/ide/hpt366.c b/drivers/ide/hpt366.c
index 4b5dc0162e67..590cc7d64622 100644
--- a/drivers/ide/hpt366.c
+++ b/drivers/ide/hpt366.c
@@ -1236,7 +1236,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
dma_old = inb(base + 2);
- local_irq_save(flags);
+ local_irq_save_nort(flags);
dma_new = dma_old;
pci_read_config_byte(dev, hwif->channel ? 0x4b : 0x43, &masterdma);
@@ -1247,7 +1247,7 @@ static int init_dma_hpt366(ide_hwif_t *hwif,
if (dma_new != dma_old)
outb(dma_new, base + 2);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
printk(KERN_INFO " %s: BM-DMA at 0x%04lx-0x%04lx\n",
hwif->name, base, base + 7);
diff --git a/drivers/ide/ide-io-std.c b/drivers/ide/ide-io-std.c
index 19763977568c..4169433faab5 100644
--- a/drivers/ide/ide-io-std.c
+++ b/drivers/ide/ide-io-std.c
@@ -175,7 +175,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
unsigned long uninitialized_var(flags);
if ((io_32bit & 2) && !mmio) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
ata_vlb_sync(io_ports->nsect_addr);
}
@@ -186,7 +186,7 @@ void ide_input_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
insl(data_addr, buf, words);
if ((io_32bit & 2) && !mmio)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
if (((len + 1) & 3) < 2)
return;
@@ -219,7 +219,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
unsigned long uninitialized_var(flags);
if ((io_32bit & 2) && !mmio) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
ata_vlb_sync(io_ports->nsect_addr);
}
@@ -230,7 +230,7 @@ void ide_output_data(ide_drive_t *drive, struct ide_cmd *cmd, void *buf,
outsl(data_addr, buf, words);
if ((io_32bit & 2) && !mmio)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
if (((len + 1) & 3) < 2)
return;
diff --git a/drivers/ide/ide-io.c b/drivers/ide/ide-io.c
index 3a234701d92c..420e4e645856 100644
--- a/drivers/ide/ide-io.c
+++ b/drivers/ide/ide-io.c
@@ -660,7 +660,7 @@ void ide_timer_expiry (unsigned long data)
/* disable_irq_nosync ?? */
disable_irq(hwif->irq);
/* local CPU only, as if we were handling an interrupt */
- local_irq_disable();
+ local_irq_disable_nort();
if (hwif->polling) {
startstop = handler(drive);
} else if (drive_is_ready(drive)) {
diff --git a/drivers/ide/ide-iops.c b/drivers/ide/ide-iops.c
index 210a0887dd29..7bf05b6147e8 100644
--- a/drivers/ide/ide-iops.c
+++ b/drivers/ide/ide-iops.c
@@ -129,12 +129,12 @@ int __ide_wait_stat(ide_drive_t *drive, u8 good, u8 bad,
if ((stat & ATA_BUSY) == 0)
break;
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
*rstat = stat;
return -EBUSY;
}
}
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
/*
* Allow status to settle, then read it again.
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index eaf39e5db08b..be4c941eaa83 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -196,10 +196,10 @@ static void do_identify(ide_drive_t *drive, u8 cmd, u16 *id)
int bswap = 1;
/* local CPU only; some systems need this */
- local_irq_save(flags);
+ local_irq_save_nort(flags);
/* read 512 bytes of id info */
hwif->tp_ops->input_data(drive, NULL, id, SECTOR_SIZE);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
drive->dev_flags |= IDE_DFLAG_ID_READ;
#ifdef DEBUG
diff --git a/drivers/ide/ide-taskfile.c b/drivers/ide/ide-taskfile.c
index 4efe4c6e956c..7eae3aa1def7 100644
--- a/drivers/ide/ide-taskfile.c
+++ b/drivers/ide/ide-taskfile.c
@@ -251,7 +251,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
page_is_high = PageHighMem(page);
if (page_is_high)
- local_irq_save(flags);
+ local_irq_save_nort(flags);
buf = kmap_atomic(page) + offset;
@@ -272,7 +272,7 @@ void ide_pio_bytes(ide_drive_t *drive, struct ide_cmd *cmd,
kunmap_atomic(buf);
if (page_is_high)
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
len -= nr_bytes;
}
@@ -415,7 +415,7 @@ static ide_startstop_t pre_task_out_intr(ide_drive_t *drive,
}
if ((drive->dev_flags & IDE_DFLAG_UNMASK) == 0)
- local_irq_disable();
+ local_irq_disable_nort();
ide_set_handler(drive, &task_pio_intr, WAIT_WORSTCASE);
diff --git a/drivers/infiniband/hw/hfi1/affinity.c b/drivers/infiniband/hw/hfi1/affinity.c
index b5fab55cc275..4b32a4e8d5da 100644
--- a/drivers/infiniband/hw/hfi1/affinity.c
+++ b/drivers/infiniband/hw/hfi1/affinity.c
@@ -575,7 +575,7 @@ 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;
@@ -583,7 +583,7 @@ 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));
@@ -594,7 +594,7 @@ 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));
diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c
index 6781bcdb10b3..d069ad261572 100644
--- a/drivers/infiniband/hw/hfi1/sdma.c
+++ b/drivers/infiniband/hw/hfi1/sdma.c
@@ -856,14 +856,13 @@ struct sdma_engine *sdma_select_user_engine(struct hfi1_devdata *dd,
{
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();
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 40efc9151ec4..12924aad90cc 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -1167,7 +1167,7 @@ static unsigned int qib_poll(struct file *fp, struct poll_table_struct *pt)
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;
@@ -1648,9 +1648,8 @@ static int qib_assign_ctxt(struct file *fp, const struct qib_user_info *uinfo)
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)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 9b3f47ae2016..8327b598d909 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -898,7 +898,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
ipoib_dbg_mcast(priv, "restarting multicast task\n");
- local_irq_save(flags);
+ local_irq_save_nort(flags);
netif_addr_lock(dev);
spin_lock(&priv->lock);
@@ -980,7 +980,7 @@ void ipoib_mcast_restart_task(struct work_struct *work)
spin_unlock(&priv->lock);
netif_addr_unlock(dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
ipoib_mcast_remove_list(&remove_list);
diff --git a/drivers/input/gameport/gameport.c b/drivers/input/gameport/gameport.c
index cedc665364cd..4a4fdef151aa 100644
--- a/drivers/input/gameport/gameport.c
+++ b/drivers/input/gameport/gameport.c
@@ -91,13 +91,13 @@ static int gameport_measure_speed(struct gameport *gameport)
tx = ~0;
for (i = 0; i < 50; i++) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
t1 = ktime_get_ns();
for (t = 0; t < 50; t++)
gameport_read(gameport);
t2 = ktime_get_ns();
t3 = ktime_get_ns();
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
udelay(i * 10);
t = (t2 - t1) - (t3 - t2);
if (t < tx)
@@ -124,12 +124,12 @@ static int old_gameport_measure_speed(struct gameport *gameport)
tx = 1 << 30;
for(i = 0; i < 50; i++) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
GET_TIME(t1);
for (t = 0; t < 50; t++) gameport_read(gameport);
GET_TIME(t2);
GET_TIME(t3);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
udelay(i * 10);
if ((t = DELTA(t2,t1) - DELTA(t3,t2)) < tx) tx = t;
}
@@ -148,11 +148,11 @@ static int old_gameport_measure_speed(struct gameport *gameport)
tx = 1 << 30;
for(i = 0; i < 50; i++) {
- local_irq_save(flags);
+ local_irq_save_nort(flags);
t1 = rdtsc();
for (t = 0; t < 50; t++) gameport_read(gameport);
t2 = rdtsc();
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
udelay(i * 10);
if (t2 - t1 < tx) tx = t2 - t1;
}
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 10190e361a13..b96b8c11a586 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -81,11 +81,12 @@
*/
#define AMD_IOMMU_PGSIZES ((~0xFFFUL) & ~(2ULL << 38))
-static DEFINE_RWLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(amd_iommu_devtable_lock);
+static DEFINE_SPINLOCK(pd_bitmap_lock);
+static DEFINE_SPINLOCK(iommu_table_lock);
/* List of all available dev_data structures */
-static LIST_HEAD(dev_data_list);
-static DEFINE_SPINLOCK(dev_data_list_lock);
+static LLIST_HEAD(dev_data_list);
LIST_HEAD(ioapic_map);
LIST_HEAD(hpet_map);
@@ -204,40 +205,33 @@ static struct dma_ops_domain* to_dma_ops_domain(struct protection_domain *domain
static struct iommu_dev_data *alloc_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
- unsigned long flags;
dev_data = kzalloc(sizeof(*dev_data), GFP_KERNEL);
if (!dev_data)
return NULL;
dev_data->devid = devid;
-
- spin_lock_irqsave(&dev_data_list_lock, flags);
- list_add_tail(&dev_data->dev_data_list, &dev_data_list);
- spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
ratelimit_default_init(&dev_data->rs);
+ llist_add(&dev_data->dev_data_list, &dev_data_list);
return dev_data;
}
static struct iommu_dev_data *search_dev_data(u16 devid)
{
struct iommu_dev_data *dev_data;
- unsigned long flags;
+ struct llist_node *node;
+
+ if (llist_empty(&dev_data_list))
+ return NULL;
- spin_lock_irqsave(&dev_data_list_lock, flags);
- list_for_each_entry(dev_data, &dev_data_list, dev_data_list) {
+ node = dev_data_list.first;
+ llist_for_each_entry(dev_data, node, dev_data_list) {
if (dev_data->devid == devid)
- goto out_unlock;
+ return dev_data;
}
- dev_data = NULL;
-
-out_unlock:
- spin_unlock_irqrestore(&dev_data_list_lock, flags);
-
- return dev_data;
+ return NULL;
}
static int __last_alias(struct pci_dev *pdev, u16 alias, void *data)
@@ -1056,9 +1050,9 @@ static int iommu_queue_command_sync(struct amd_iommu *iommu,
unsigned long flags;
int ret;
- spin_lock_irqsave(&iommu->lock, flags);
+ raw_spin_lock_irqsave(&iommu->lock, flags);
ret = __iommu_queue_command_sync(iommu, cmd, sync);
- spin_unlock_irqrestore(&iommu->lock, flags);
+ raw_spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
}
@@ -1084,7 +1078,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
build_completion_wait(&cmd, (u64)&iommu->cmd_sem);
- spin_lock_irqsave(&iommu->lock, flags);
+ raw_spin_lock_irqsave(&iommu->lock, flags);
iommu->cmd_sem = 0;
@@ -1095,7 +1089,7 @@ static int iommu_completion_wait(struct amd_iommu *iommu)
ret = wait_on_sem(&iommu->cmd_sem);
out_unlock:
- spin_unlock_irqrestore(&iommu->lock, flags);
+ raw_spin_unlock_irqrestore(&iommu->lock, flags);
return ret;
}
@@ -1604,29 +1598,26 @@ static void del_domain_from_list(struct protection_domain *domain)
static u16 domain_id_alloc(void)
{
- unsigned long flags;
int id;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock(&pd_bitmap_lock);
id = find_first_zero_bit(amd_iommu_pd_alloc_bitmap, MAX_DOMAIN_ID);
BUG_ON(id == 0);
if (id > 0 && id < MAX_DOMAIN_ID)
__set_bit(id, amd_iommu_pd_alloc_bitmap);
else
id = 0;
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock(&pd_bitmap_lock);
return id;
}
static void domain_id_free(int id)
{
- unsigned long flags;
-
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock(&pd_bitmap_lock);
if (id > 0 && id < MAX_DOMAIN_ID)
__clear_bit(id, amd_iommu_pd_alloc_bitmap);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock(&pd_bitmap_lock);
}
#define DEFINE_FREE_PT_FN(LVL, FN) \
@@ -1946,10 +1937,10 @@ static int __attach_device(struct iommu_dev_data *dev_data,
int ret;
/*
- * Must be called with IRQs disabled. Warn here to detect early
- * when its not.
+ * Must be called with IRQs disabled on a non RT kernel. Warn here to
+ * detect early when its not.
*/
- WARN_ON(!irqs_disabled());
+ WARN_ON_NONRT(!irqs_disabled());
/* lock domain */
spin_lock(&domain->lock);
@@ -2095,9 +2086,9 @@ static int attach_device(struct device *dev,
}
skip_ats_check:
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
ret = __attach_device(dev_data, domain);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
/*
* We might boot into a crash-kernel here. The crashed kernel
@@ -2117,10 +2108,10 @@ static void __detach_device(struct iommu_dev_data *dev_data)
struct protection_domain *domain;
/*
- * Must be called with IRQs disabled. Warn here to detect early
- * when its not.
+ * Must be called with IRQs disabled on a non RT kernel. Warn here to
+ * detect early when its not.
*/
- WARN_ON(!irqs_disabled());
+ WARN_ON_NONRT(!irqs_disabled());
if (WARN_ON(!dev_data->domain))
return;
@@ -2147,9 +2138,9 @@ static void detach_device(struct device *dev)
domain = dev_data->domain;
/* lock device table */
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
__detach_device(dev_data);
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
if (!dev_is_pci(dev))
return;
@@ -2813,7 +2804,7 @@ static void cleanup_domain(struct protection_domain *domain)
struct iommu_dev_data *entry;
unsigned long flags;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&amd_iommu_devtable_lock, flags);
while (!list_empty(&domain->dev_list)) {
entry = list_first_entry(&domain->dev_list,
@@ -2821,7 +2812,7 @@ static void cleanup_domain(struct protection_domain *domain)
__detach_device(entry);
}
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
}
static void protection_domain_free(struct protection_domain *domain)
@@ -3588,14 +3579,62 @@ static void set_dte_irq_entry(u16 devid, struct irq_remap_table *table)
amd_iommu_dev_table[devid].data[2] = dte;
}
-static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
+static struct irq_remap_table *get_irq_table(u16 devid)
+{
+ struct irq_remap_table *table;
+
+ if (WARN_ONCE(!amd_iommu_rlookup_table[devid],
+ "%s: no iommu for devid %x\n", __func__, devid))
+ return NULL;
+
+ table = irq_lookup_table[devid];
+ if (WARN_ONCE(!table, "%s: no table for devid %x\n", __func__, devid))
+ return NULL;
+
+ return table;
+}
+
+static struct irq_remap_table *__alloc_irq_table(void)
+{
+ struct irq_remap_table *table;
+
+ table = kzalloc(sizeof(*table), GFP_KERNEL);
+ if (!table)
+ return NULL;
+
+ table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_KERNEL);
+ if (!table->table) {
+ kfree(table);
+ return NULL;
+ }
+ raw_spin_lock_init(&table->lock);
+
+ if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
+ memset(table->table, 0,
+ MAX_IRQS_PER_TABLE * sizeof(u32));
+ else
+ memset(table->table, 0,
+ (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
+ return table;
+}
+
+static void set_remap_table_entry(struct amd_iommu *iommu, u16 devid,
+ struct irq_remap_table *table)
+{
+ irq_lookup_table[devid] = table;
+ set_dte_irq_entry(devid, table);
+ iommu_flush_dte(iommu, devid);
+}
+
+static struct irq_remap_table *alloc_irq_table(u16 devid)
{
struct irq_remap_table *table = NULL;
+ struct irq_remap_table *new_table = NULL;
struct amd_iommu *iommu;
unsigned long flags;
u16 alias;
- write_lock_irqsave(&amd_iommu_devtable_lock, flags);
+ spin_lock_irqsave(&iommu_table_lock, flags);
iommu = amd_iommu_rlookup_table[devid];
if (!iommu)
@@ -3608,60 +3647,45 @@ static struct irq_remap_table *get_irq_table(u16 devid, bool ioapic)
alias = amd_iommu_alias_table[devid];
table = irq_lookup_table[alias];
if (table) {
- irq_lookup_table[devid] = table;
- set_dte_irq_entry(devid, table);
- iommu_flush_dte(iommu, devid);
- goto out;
+ set_remap_table_entry(iommu, devid, table);
+ goto out_wait;
}
+ spin_unlock_irqrestore(&iommu_table_lock, flags);
/* Nothing there yet, allocate new irq remapping table */
- table = kzalloc(sizeof(*table), GFP_ATOMIC);
- if (!table)
- goto out_unlock;
-
- /* Initialize table spin-lock */
- spin_lock_init(&table->lock);
+ new_table = __alloc_irq_table();
+ if (!new_table)
+ return NULL;
- if (ioapic)
- /* Keep the first 32 indexes free for IOAPIC interrupts */
- table->min_index = 32;
+ spin_lock_irqsave(&iommu_table_lock, flags);
- table->table = kmem_cache_alloc(amd_iommu_irq_cache, GFP_ATOMIC);
- if (!table->table) {
- kfree(table);
- table = NULL;
+ table = irq_lookup_table[devid];
+ if (table)
goto out_unlock;
- }
-
- if (!AMD_IOMMU_GUEST_IR_GA(amd_iommu_guest_ir))
- memset(table->table, 0,
- MAX_IRQS_PER_TABLE * sizeof(u32));
- else
- memset(table->table, 0,
- (MAX_IRQS_PER_TABLE * (sizeof(u64) * 2)));
- if (ioapic) {
- int i;
-
- for (i = 0; i < 32; ++i)
- iommu->irte_ops->set_allocated(table, i);
+ table = irq_lookup_table[alias];
+ if (table) {
+ set_remap_table_entry(iommu, devid, table);
+ goto out_wait;
}
- irq_lookup_table[devid] = table;
- set_dte_irq_entry(devid, table);
- iommu_flush_dte(iommu, devid);
- if (devid != alias) {
- irq_lookup_table[alias] = table;
- set_dte_irq_entry(alias, table);
- iommu_flush_dte(iommu, alias);
- }
+ table = new_table;
+ new_table = NULL;
-out:
+ set_remap_table_entry(iommu, devid, table);
+ if (devid != alias)
+ set_remap_table_entry(iommu, alias, table);
+
+out_wait:
iommu_completion_wait(iommu);
out_unlock:
- write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
+ spin_unlock_irqrestore(&iommu_table_lock, flags);
+ if (new_table) {
+ kmem_cache_free(amd_iommu_irq_cache, new_table->table);
+ kfree(new_table);
+ }
return table;
}
@@ -3675,11 +3699,11 @@ static int alloc_irq_index(u16 devid, int count)
if (!iommu)
return -ENODEV;
- table = get_irq_table(devid, false);
+ table = alloc_irq_table(devid);
if (!table)
return -ENODEV;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
/* Scan table for free entries */
for (c = 0, index = table->min_index;
@@ -3702,7 +3726,7 @@ static int alloc_irq_index(u16 devid, int count)
index = -ENOSPC;
out:
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
return index;
}
@@ -3719,11 +3743,11 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
if (iommu == NULL)
return -EINVAL;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return -ENOMEM;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
entry = (struct irte_ga *)table->table;
entry = &entry[index];
@@ -3734,7 +3758,7 @@ static int modify_irte_ga(u16 devid, int index, struct irte_ga *irte,
if (data)
data->ref = entry;
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3752,13 +3776,13 @@ static int modify_irte(u16 devid, int index, union irte *irte)
if (iommu == NULL)
return -EINVAL;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return -ENOMEM;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
table->table[index] = irte->val;
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3776,13 +3800,13 @@ static void free_irte(u16 devid, int index)
if (iommu == NULL)
return;
- table = get_irq_table(devid, false);
+ table = get_irq_table(devid);
if (!table)
return;
- spin_lock_irqsave(&table->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
iommu->irte_ops->clear_allocated(table, index);
- spin_unlock_irqrestore(&table->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
@@ -3863,10 +3887,8 @@ static void irte_ga_set_affinity(void *entry, u16 devid, u16 index,
u8 vector, u32 dest_apicid)
{
struct irte_ga *irte = (struct irte_ga *) entry;
- struct iommu_dev_data *dev_data = search_dev_data(devid);
- if (!dev_data || !dev_data->use_vapic ||
- !irte->lo.fields_remap.guest_mode) {
+ if (!irte->lo.fields_remap.guest_mode) {
irte->hi.fields.vector = vector;
irte->lo.fields_remap.destination = dest_apicid;
modify_irte_ga(devid, index, irte, NULL);
@@ -4072,7 +4094,7 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
struct amd_ir_data *data = NULL;
struct irq_cfg *cfg;
int i, ret, devid;
- int index = -1;
+ int index;
if (!info)
return -EINVAL;
@@ -4096,10 +4118,26 @@ static int irq_remapping_alloc(struct irq_domain *domain, unsigned int virq,
return ret;
if (info->type == X86_IRQ_ALLOC_TYPE_IOAPIC) {
- if (get_irq_table(devid, true))
+ struct irq_remap_table *table;
+ struct amd_iommu *iommu;
+
+ table = alloc_irq_table(devid);
+ if (table) {
+ if (!table->min_index) {
+ /*
+ * Keep the first 32 indexes free for IOAPIC
+ * interrupts.
+ */
+ table->min_index = 32;
+ iommu = amd_iommu_rlookup_table[devid];
+ for (i = 0; i < 32; ++i)
+ iommu->irte_ops->set_allocated(table, i);
+ }
+ WARN_ON(table->min_index != 32);
index = info->ioapic_pin;
- else
- ret = -ENOMEM;
+ } else {
+ index = -ENOMEM;
+ }
} else {
index = alloc_irq_index(devid, nr_irqs);
}
@@ -4343,7 +4381,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
{
unsigned long flags;
struct amd_iommu *iommu;
- struct irq_remap_table *irt;
+ struct irq_remap_table *table;
struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
int devid = ir_data->irq_2_irte.devid;
struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -4357,11 +4395,11 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
if (!iommu)
return -ENODEV;
- irt = get_irq_table(devid, false);
- if (!irt)
+ table = get_irq_table(devid);
+ if (!table)
return -ENODEV;
- spin_lock_irqsave(&irt->lock, flags);
+ raw_spin_lock_irqsave(&table->lock, flags);
if (ref->lo.fields_vapic.guest_mode) {
if (cpu >= 0)
@@ -4370,7 +4408,7 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
barrier();
}
- spin_unlock_irqrestore(&irt->lock, flags);
+ raw_spin_unlock_irqrestore(&table->lock, flags);
iommu_flush_irt(iommu, devid);
iommu_completion_wait(iommu);
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index 6fe2d0346073..e3cd81b32a33 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -1474,7 +1474,7 @@ static int __init init_iommu_one(struct amd_iommu *iommu, struct ivhd_header *h)
{
int ret;
- spin_lock_init(&iommu->lock);
+ raw_spin_lock_init(&iommu->lock);
/* Add IOMMU to internal data structures */
list_add_tail(&iommu->list, &amd_iommu_list);
diff --git a/drivers/iommu/amd_iommu_types.h b/drivers/iommu/amd_iommu_types.h
index f6b24c7d8b70..16b1404da58c 100644
--- a/drivers/iommu/amd_iommu_types.h
+++ b/drivers/iommu/amd_iommu_types.h
@@ -406,7 +406,7 @@ extern bool amd_iommu_iotlb_sup;
#define IRQ_TABLE_ALIGNMENT 128
struct irq_remap_table {
- spinlock_t lock;
+ raw_spinlock_t lock;
unsigned min_index;
u32 *table;
};
@@ -488,7 +488,7 @@ struct amd_iommu {
int index;
/* locks the accesses to the hardware */
- spinlock_t lock;
+ raw_spinlock_t lock;
/* Pointer to PCI device of this IOMMU */
struct pci_dev *dev;
@@ -625,7 +625,7 @@ struct devid_map {
*/
struct iommu_dev_data {
struct list_head list; /* For domain->dev_list */
- struct list_head dev_data_list; /* For global dev_data_list */
+ struct llist_node dev_data_list; /* For global dev_data_list */
struct protection_domain *domain; /* Domain the device is bound to */
u16 devid; /* PCI Device ID */
u16 alias; /* Alias Device ID */
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index 33edfa794ae9..b30900025c62 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -570,7 +570,7 @@ void queue_iova(struct iova_domain *iovad,
unsigned long pfn, unsigned long pages,
unsigned long data)
{
- struct iova_fq *fq = get_cpu_ptr(iovad->fq);
+ struct iova_fq *fq = raw_cpu_ptr(iovad->fq);
unsigned long flags;
unsigned idx;
@@ -600,8 +600,6 @@ void queue_iova(struct iova_domain *iovad,
if (atomic_cmpxchg(&iovad->fq_timer_on, 0, 1) == 0)
mod_timer(&iovad->fq_timer,
jiffies + msecs_to_jiffies(IOVA_FQ_TIMEOUT));
-
- put_cpu_ptr(iovad->fq);
}
EXPORT_SYMBOL_GPL(queue_iova);
diff --git a/drivers/leds/trigger/Kconfig b/drivers/leds/trigger/Kconfig
index 3f9ddb9fafa7..09da5b6b44a1 100644
--- a/drivers/leds/trigger/Kconfig
+++ b/drivers/leds/trigger/Kconfig
@@ -69,7 +69,7 @@ config LEDS_TRIGGER_BACKLIGHT
config LEDS_TRIGGER_CPU
bool "LED CPU Trigger"
- depends on LEDS_TRIGGERS
+ depends on LEDS_TRIGGERS && !PREEMPT_RT_BASE
help
This allows LEDs to be controlled by active CPUs. This shows
the active CPUs across an array of LEDs so you can see which
diff --git a/drivers/md/bcache/Kconfig b/drivers/md/bcache/Kconfig
index 4d200883c505..98b64ed5cb81 100644
--- a/drivers/md/bcache/Kconfig
+++ b/drivers/md/bcache/Kconfig
@@ -1,6 +1,7 @@
config BCACHE
tristate "Block device as cache"
+ depends on !PREEMPT_RT_FULL
---help---
Allows a block device to be used as cache for other devices; uses
a btree for indexing and the layout is optimized for SSDs.
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index eadfcfd106ff..8824aeda85cf 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -671,7 +671,7 @@ static void dm_old_request_fn(struct request_queue *q)
/* Establish tio->ti before queuing work (map_tio_request) */
tio->ti = ti;
kthread_queue_work(&md->kworker, &tio->work);
- BUG_ON(!irqs_disabled());
+ BUG_ON_NONRT(!irqs_disabled());
}
}
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 07ca2fd10189..6d8112678ff9 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -410,7 +410,7 @@ void raid5_release_stripe(struct stripe_head *sh)
md_wakeup_thread(conf->mddev->thread);
return;
slow_path:
- local_irq_save(flags);
+ local_irq_save_nort(flags);
/* we are ok here if STRIPE_ON_RELEASE_LIST is set or not */
if (atomic_dec_and_lock(&sh->count, &conf->device_lock)) {
INIT_LIST_HEAD(&list);
@@ -419,7 +419,7 @@ slow_path:
spin_unlock(&conf->device_lock);
release_inactive_stripe_list(conf, &list, hash);
}
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
static inline void remove_hash(struct stripe_head *sh)
@@ -2067,8 +2067,9 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
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++;
@@ -2127,7 +2128,8 @@ static void raid_run_ops(struct stripe_head *sh, unsigned long ops_request)
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)
@@ -6775,6 +6777,7 @@ static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
__func__, cpu);
return -ENOMEM;
}
+ spin_lock_init(&per_cpu_ptr(conf->percpu, cpu)->lock);
return 0;
}
@@ -6785,7 +6788,6 @@ static int raid5_alloc_percpu(struct r5conf *conf)
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,
diff --git a/drivers/md/raid5.h b/drivers/md/raid5.h
index 2e6123825095..37a6021418a2 100644
--- a/drivers/md/raid5.h
+++ b/drivers/md/raid5.h
@@ -624,6 +624,7 @@ struct r5conf {
int recovery_disabled;
/* per cpu variables */
struct raid5_percpu {
+ spinlock_t lock; /* Protection for -RT */
struct page *spare_page; /* Used when checking P/Q in raid6 */
struct flex_array *scribble; /* space for constructing buffer
* lists and performing address
diff --git a/drivers/mfd/atmel-smc.c b/drivers/mfd/atmel-smc.c
index 7d77948567d7..0adbd2e796fe 100644
--- a/drivers/mfd/atmel-smc.c
+++ b/drivers/mfd/atmel-smc.c
@@ -12,6 +12,7 @@
*/
#include <linux/mfd/syscon/atmel-smc.h>
+#include <linux/string.h>
/**
* atmel_smc_cs_conf_init - initialize a SMC CS conf
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 8136dc7e863d..86e83b9629d7 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -54,6 +54,7 @@ config AD525X_DPOT_SPI
config ATMEL_TCLIB
bool "Atmel AT32/AT91 Timer/Counter Library"
depends on (AVR32 || ARCH_AT91)
+ default y if PREEMPT_RT_FULL
help
Select this if you want a library to allocate the Timer/Counter
blocks found on many Atmel processors. This facilitates using
@@ -69,8 +70,7 @@ 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
@@ -84,6 +84,15 @@ 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 if !PREEMPT_RT_FULL
+ help
+ Select this to use 32 KiHz base clock rate as TC block clock
+ source for clock events.
+
+
config DUMMY_IRQ
tristate "Dummy IRQ handler"
default n
diff --git a/drivers/mmc/host/mmci.c b/drivers/mmc/host/mmci.c
index f1f54a818489..ce102378df02 100644
--- a/drivers/mmc/host/mmci.c
+++ b/drivers/mmc/host/mmci.c
@@ -1200,15 +1200,12 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
struct sg_mapping_iter *sg_miter = &host->sg_miter;
struct variant_data *variant = host->variant;
void __iomem *base = host->base;
- unsigned long flags;
u32 status;
status = readl(base + MMCISTATUS);
dev_dbg(mmc_dev(host->mmc), "irq1 (pio) %08x\n", status);
- local_irq_save(flags);
-
do {
unsigned int remain, len;
char *buffer;
@@ -1248,8 +1245,6 @@ static irqreturn_t mmci_pio_irq(int irq, void *dev_id)
sg_miter_stop(sg_miter);
- local_irq_restore(flags);
-
/*
* If we have less than the fifo 'half-full' threshold to transfer,
* trigger a PIO interrupt as soon as any data is available.
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c
index 402d9090ad29..9bc02563b853 100644
--- a/drivers/net/ethernet/3com/3c59x.c
+++ b/drivers/net/ethernet/3com/3c59x.c
@@ -842,9 +842,9 @@ static void poll_vortex(struct net_device *dev)
{
struct vortex_private *vp = netdev_priv(dev);
unsigned long flags;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
(vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
#endif
@@ -1908,12 +1908,12 @@ static void vortex_tx_timeout(struct net_device *dev)
* Block interrupts because vortex_interrupt does a bare spin_lock()
*/
unsigned long flags;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
if (vp->full_bus_master_tx)
boomerang_interrupt(dev->irq, dev);
else
vortex_interrupt(dev->irq, dev);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
}
diff --git a/drivers/net/ethernet/marvell/mvpp2.c b/drivers/net/ethernet/marvell/mvpp2.c
index 529be74f609d..b1d7378b131c 100644
--- a/drivers/net/ethernet/marvell/mvpp2.c
+++ b/drivers/net/ethernet/marvell/mvpp2.c
@@ -830,9 +830,8 @@ struct mvpp2_pcpu_stats {
/* Per-CPU port control */
struct mvpp2_port_pcpu {
struct hrtimer tx_done_timer;
+ struct net_device *dev;
bool timer_scheduled;
- /* Tasklet for egress finalization */
- struct tasklet_struct tx_done_tasklet;
};
struct mvpp2_queue_vector {
@@ -5954,46 +5953,34 @@ static void mvpp2_link_event(struct net_device *dev)
}
}
-static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu)
-{
- ktime_t interval;
-
- if (!port_pcpu->timer_scheduled) {
- port_pcpu->timer_scheduled = true;
- interval = MVPP2_TXDONE_HRTIMER_PERIOD_NS;
- hrtimer_start(&port_pcpu->tx_done_timer, interval,
- HRTIMER_MODE_REL_PINNED);
- }
-}
-
-static void mvpp2_tx_proc_cb(unsigned long data)
+static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
{
- struct net_device *dev = (struct net_device *)data;
- struct mvpp2_port *port = netdev_priv(dev);
- struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
+ struct net_device *dev;
+ struct mvpp2_port *port;
+ struct mvpp2_port_pcpu *port_pcpu;
unsigned int tx_todo, cause;
+ port_pcpu = container_of(timer, struct mvpp2_port_pcpu, tx_done_timer);
+ dev = port_pcpu->dev;
+
if (!netif_running(dev))
- return;
+ return HRTIMER_NORESTART;
+
port_pcpu->timer_scheduled = false;
+ port = netdev_priv(dev);
/* Process all the Tx queues */
cause = (1 << port->ntxqs) - 1;
tx_todo = mvpp2_tx_done(port, cause, smp_processor_id());
/* Set the timer in case not all the packets were processed */
- if (tx_todo)
- mvpp2_timer_set(port_pcpu);
-}
-
-static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer)
-{
- struct mvpp2_port_pcpu *port_pcpu = container_of(timer,
- struct mvpp2_port_pcpu,
- tx_done_timer);
-
- tasklet_schedule(&port_pcpu->tx_done_tasklet);
+ if (tx_todo && !port_pcpu->timer_scheduled) {
+ port_pcpu->timer_scheduled = true;
+ hrtimer_forward_now(&port_pcpu->tx_done_timer,
+ MVPP2_TXDONE_HRTIMER_PERIOD_NS);
+ return HRTIMER_RESTART;
+ }
return HRTIMER_NORESTART;
}
@@ -6482,7 +6469,12 @@ out:
txq_pcpu->count > 0) {
struct mvpp2_port_pcpu *port_pcpu = this_cpu_ptr(port->pcpu);
- mvpp2_timer_set(port_pcpu);
+ if (!port_pcpu->timer_scheduled) {
+ port_pcpu->timer_scheduled = true;
+ hrtimer_start(&port_pcpu->tx_done_timer,
+ MVPP2_TXDONE_HRTIMER_PERIOD_NS,
+ HRTIMER_MODE_REL_PINNED_SOFT);
+ }
}
return NETDEV_TX_OK;
@@ -6871,7 +6863,6 @@ static int mvpp2_stop(struct net_device *dev)
hrtimer_cancel(&port_pcpu->tx_done_timer);
port_pcpu->timer_scheduled = false;
- tasklet_kill(&port_pcpu->tx_done_tasklet);
}
}
mvpp2_cleanup_rxqs(port);
@@ -7644,13 +7635,10 @@ static int mvpp2_port_probe(struct platform_device *pdev,
port_pcpu = per_cpu_ptr(port->pcpu, cpu);
hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL_PINNED);
+ HRTIMER_MODE_REL_PINNED_SOFT);
port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb;
port_pcpu->timer_scheduled = false;
-
- tasklet_init(&port_pcpu->tx_done_tasklet,
- mvpp2_tx_proc_cb,
- (unsigned long)dev);
+ port_pcpu->dev = dev;
}
}
diff --git a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
index 56f6e3b71f48..a50350d01a80 100644
--- a/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
+++ b/drivers/net/wireless/intersil/orinoco/orinoco_usb.c
@@ -697,7 +697,7 @@ static void ezusb_req_ctx_wait(struct ezusb_priv *upriv,
while (!ctx->done.done && msecs--)
udelay(1000);
} else {
- wait_event_interruptible(ctx->done.wait,
+ swait_event_interruptible(ctx->done.wait,
ctx->done.done);
}
break;
diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c
index d686ba10fecc..4afcdee4f8e2 100644
--- a/drivers/net/wireless/mac80211_hwsim.c
+++ b/drivers/net/wireless/mac80211_hwsim.c
@@ -537,7 +537,7 @@ struct mac80211_hwsim_data {
unsigned int rx_filter;
bool started, idle, scanning;
struct mutex mutex;
- struct tasklet_hrtimer beacon_timer;
+ struct hrtimer beacon_timer;
enum ps_mode {
PS_DISABLED, PS_ENABLED, PS_AUTO_POLL, PS_MANUAL_POLL
} ps;
@@ -1423,7 +1423,7 @@ static void mac80211_hwsim_stop(struct ieee80211_hw *hw)
{
struct mac80211_hwsim_data *data = hw->priv;
data->started = false;
- tasklet_hrtimer_cancel(&data->beacon_timer);
+ hrtimer_cancel(&data->beacon_timer);
wiphy_debug(hw->wiphy, "%s\n", __func__);
}
@@ -1546,14 +1546,12 @@ static enum hrtimer_restart
mac80211_hwsim_beacon(struct hrtimer *timer)
{
struct mac80211_hwsim_data *data =
- container_of(timer, struct mac80211_hwsim_data,
- beacon_timer.timer);
+ container_of(timer, struct mac80211_hwsim_data, beacon_timer);
struct ieee80211_hw *hw = data->hw;
u64 bcn_int = data->beacon_int;
- ktime_t next_bcn;
if (!data->started)
- goto out;
+ return HRTIMER_NORESTART;
ieee80211_iterate_active_interfaces_atomic(
hw, IEEE80211_IFACE_ITER_NORMAL,
@@ -1565,11 +1563,9 @@ mac80211_hwsim_beacon(struct hrtimer *timer)
data->bcn_delta = 0;
}
- next_bcn = ktime_add(hrtimer_get_expires(timer),
- ns_to_ktime(bcn_int * 1000));
- tasklet_hrtimer_start(&data->beacon_timer, next_bcn, HRTIMER_MODE_ABS);
-out:
- return HRTIMER_NORESTART;
+ hrtimer_forward(&data->beacon_timer, hrtimer_get_expires(timer),
+ ns_to_ktime(bcn_int * NSEC_PER_USEC));
+ return HRTIMER_RESTART;
}
static const char * const hwsim_chanwidths[] = {
@@ -1643,15 +1639,15 @@ static int mac80211_hwsim_config(struct ieee80211_hw *hw, u32 changed)
mutex_unlock(&data->mutex);
if (!data->started || !data->beacon_int)
- tasklet_hrtimer_cancel(&data->beacon_timer);
- else if (!hrtimer_is_queued(&data->beacon_timer.timer)) {
+ hrtimer_cancel(&data->beacon_timer);
+ else if (!hrtimer_is_queued(&data->beacon_timer)) {
u64 tsf = mac80211_hwsim_get_tsf(hw, NULL);
u32 bcn_int = data->beacon_int;
u64 until_tbtt = bcn_int - do_div(tsf, bcn_int);
- tasklet_hrtimer_start(&data->beacon_timer,
- ns_to_ktime(until_tbtt * 1000),
- HRTIMER_MODE_REL);
+ hrtimer_start(&data->beacon_timer,
+ ns_to_ktime(until_tbtt * 1000),
+ HRTIMER_MODE_REL_SOFT);
}
return 0;
@@ -1714,7 +1710,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
info->enable_beacon, info->beacon_int);
vp->bcn_en = info->enable_beacon;
if (data->started &&
- !hrtimer_is_queued(&data->beacon_timer.timer) &&
+ !hrtimer_is_queued(&data->beacon_timer) &&
info->enable_beacon) {
u64 tsf, until_tbtt;
u32 bcn_int;
@@ -1722,9 +1718,9 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
tsf = mac80211_hwsim_get_tsf(hw, vif);
bcn_int = data->beacon_int;
until_tbtt = bcn_int - do_div(tsf, bcn_int);
- tasklet_hrtimer_start(&data->beacon_timer,
- ns_to_ktime(until_tbtt * 1000),
- HRTIMER_MODE_REL);
+ hrtimer_start(&data->beacon_timer,
+ ns_to_ktime(until_tbtt * 1000),
+ HRTIMER_MODE_REL_SOFT);
} else if (!info->enable_beacon) {
unsigned int count = 0;
ieee80211_iterate_active_interfaces_atomic(
@@ -1733,7 +1729,7 @@ static void mac80211_hwsim_bss_info_changed(struct ieee80211_hw *hw,
wiphy_debug(hw->wiphy, " beaconing vifs remaining: %u",
count);
if (count == 0) {
- tasklet_hrtimer_cancel(&data->beacon_timer);
+ hrtimer_cancel(&data->beacon_timer);
data->beacon_int = 0;
}
}
@@ -2725,9 +2721,9 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
data->debugfs,
data, &hwsim_simulate_radar);
- tasklet_hrtimer_init(&data->beacon_timer,
- mac80211_hwsim_beacon,
- CLOCK_MONOTONIC, HRTIMER_MODE_ABS);
+ hrtimer_init(&data->beacon_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_ABS_SOFT);
+ data->beacon_timer.function = mac80211_hwsim_beacon;
spin_lock_bh(&hwsim_radio_lock);
list_add_tail(&data->list, &hwsim_radios);
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index af81b2dec42e..1910c6c72fcd 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -306,10 +306,11 @@ 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;
@@ -331,7 +332,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev)
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);
@@ -414,7 +415,7 @@ static int mrpc_queue_cmd(struct switchtec_user *stuser)
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);
@@ -451,7 +452,8 @@ static void mrpc_complete_cmd(struct switchtec_dev *stdev)
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;
@@ -721,10 +723,11 @@ static ssize_t switchtec_dev_read(struct file *filp, char __user *data,
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;
}
@@ -772,7 +775,7 @@ static unsigned int switchtec_dev_poll(struct file *filp, poll_table *wait)
struct switchtec_dev *stdev = stuser->stdev;
int 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))
@@ -780,7 +783,7 @@ static unsigned int switchtec_dev_poll(struct file *filp, poll_table *wait)
mutex_unlock(&stdev->mrpc_mutex);
- if (try_wait_for_completion(&stuser->comp))
+ if (READ_ONCE(stuser->cmd_done))
ret |= POLLIN | POLLRDNORM;
if (stuser->event_cnt != atomic_read(&stdev->event_cnt))
@@ -1255,7 +1258,8 @@ static void stdev_kill(struct switchtec_dev *stdev)
/* Wake up and kill any users waiting on an MRPC request */
list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) {
- complete_all(&stuser->comp);
+ stuser->cmd_done = true;
+ wake_up_interruptible(&stuser->cmd_comp);
list_del_init(&stuser->list);
stuser_put(stuser);
}
diff --git a/drivers/scsi/fcoe/fcoe.c b/drivers/scsi/fcoe/fcoe.c
index 85f9a3eba387..08ea05ddcd82 100644
--- a/drivers/scsi/fcoe/fcoe.c
+++ b/drivers/scsi/fcoe/fcoe.c
@@ -1464,11 +1464,11 @@ 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;
}
@@ -1655,11 +1655,11 @@ static inline int fcoe_filter_frames(struct fc_lport *lport,
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;
}
@@ -1702,7 +1702,7 @@ static void fcoe_recv_frame(struct sk_buff *skb)
*/
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 "
@@ -1734,13 +1734,13 @@ static void fcoe_recv_frame(struct sk_buff *skb)
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);
}
diff --git a/drivers/scsi/fcoe/fcoe_ctlr.c b/drivers/scsi/fcoe/fcoe_ctlr.c
index fff6f1851dc1..0ac24fd699a1 100644
--- a/drivers/scsi/fcoe/fcoe_ctlr.c
+++ b/drivers/scsi/fcoe/fcoe_ctlr.c
@@ -835,7 +835,7 @@ static unsigned long fcoe_ctlr_age_fcfs(struct fcoe_ctlr *fip)
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(struct fcoe_ctlr *fip)
sel_time = fcf->time;
}
}
- put_cpu();
+ put_cpu_light();
list_for_each_entry_safe(fcf, next, &del_list, list) {
/* Removes fcf from current list */
diff --git a/drivers/scsi/libfc/fc_exch.c b/drivers/scsi/libfc/fc_exch.c
index 42bcf7f3a0f9..2ce045d6860c 100644
--- a/drivers/scsi/libfc/fc_exch.c
+++ b/drivers/scsi/libfc/fc_exch.c
@@ -833,10 +833,10 @@ static struct fc_exch *fc_exch_em_alloc(struct fc_lport *lport,
}
memset(ep, 0, sizeof(*ep));
- cpu = get_cpu();
+ cpu = get_cpu_light();
pool = per_cpu_ptr(mp->pool, cpu);
spin_lock_bh(&pool->lock);
- put_cpu();
+ put_cpu_light();
/* peek cache of free slot */
if (pool->left != FC_XID_UNKNOWN) {
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 70be4425ae0b..a23ef685deac 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -190,7 +190,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
/* TODO: audit callers to ensure they are ready for qc_issue to
* unconditionally re-enable interrupts
*/
- local_irq_save(flags);
+ local_irq_save_nort(flags);
spin_unlock(ap->lock);
/* If the device fell off, no sense in issuing commands */
@@ -252,7 +252,7 @@ static unsigned int sas_ata_qc_issue(struct ata_queued_cmd *qc)
out:
spin_lock(ap->lock);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
return ret;
}
diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
index 9a2c86eacf44..28266455b54c 100644
--- a/drivers/scsi/qla2xxx/qla_inline.h
+++ b/drivers/scsi/qla2xxx/qla_inline.h
@@ -59,12 +59,12 @@ qla2x00_poll(struct rsp_que *rsp)
{
unsigned long flags;
struct qla_hw_data *ha = rsp->hw;
- local_irq_save(flags);
+ local_irq_save_nort(flags);
if (IS_P3P_TYPE(ha))
qla82xx_poll(0, rsp);
else
ha->isp_ops->intr_handler(0, rsp);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
}
static inline uint8_t *
diff --git a/drivers/staging/greybus/audio_manager.c b/drivers/staging/greybus/audio_manager.c
index aa6508b44fab..045696ce85c7 100644
--- a/drivers/staging/greybus/audio_manager.c
+++ b/drivers/staging/greybus/audio_manager.c
@@ -10,7 +10,7 @@
#include <linux/sysfs.h>
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/rwlock.h>
+#include <linux/spinlock.h>
#include <linux/idr.h>
#include "audio_manager.h"
diff --git a/drivers/target/target_core_tmr.c b/drivers/target/target_core_tmr.c
index 9c7bc1ca341a..3d35dad1de2c 100644
--- a/drivers/target/target_core_tmr.c
+++ b/drivers/target/target_core_tmr.c
@@ -114,8 +114,6 @@ static bool __target_check_io_state(struct se_cmd *se_cmd,
{
struct se_session *sess = se_cmd->se_sess;
- assert_spin_locked(&sess->sess_cmd_lock);
- WARN_ON_ONCE(!irqs_disabled());
/*
* If command already reached CMD_T_COMPLETE state within
* target_complete_cmd() or CMD_T_FABRIC_STOP due to shutdown,
diff --git a/drivers/target/target_core_transport.c b/drivers/target/target_core_transport.c
index e6d51135d105..b00829995131 100644
--- a/drivers/target/target_core_transport.c
+++ b/drivers/target/target_core_transport.c
@@ -2966,9 +2966,6 @@ __transport_wait_for_tasks(struct se_cmd *cmd, bool fabric_stop,
__acquires(&cmd->t_state_lock)
{
- assert_spin_locked(&cmd->t_state_lock);
- WARN_ON_ONCE(!irqs_disabled());
-
if (fabric_stop)
cmd->transport_state |= CMD_T_FABRIC_STOP;
@@ -3238,9 +3235,6 @@ static int __transport_check_aborted_status(struct se_cmd *cmd, int send_status)
{
int ret;
- assert_spin_locked(&cmd->t_state_lock);
- WARN_ON_ONCE(!irqs_disabled());
-
if (!(cmd->transport_state & CMD_T_ABORTED))
return 0;
/*
diff --git a/drivers/thermal/x86_pkg_temp_thermal.c b/drivers/thermal/x86_pkg_temp_thermal.c
index d93eee2f101b..0287333b1f3c 100644
--- a/drivers/thermal/x86_pkg_temp_thermal.c
+++ b/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(int cpu, struct delayed_work *work)
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_val)
}
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);
@@ -515,10 +554,15 @@ static int __init pkg_temp_thermal_init(void)
if (!x86_match_cpu(pkg_temp_thermal_ids))
return -ENODEV;
+ if (!pkg_thermal_notify_work_init())
+ return -ENODEV;
+
max_packages = topology_max_packages();
packages = kzalloc(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);
@@ -536,6 +580,7 @@ static int __init pkg_temp_thermal_init(void)
return 0;
err:
+ pkg_thermal_notify_work_cleanup();
kfree(packages);
return ret;
}
@@ -549,6 +594,7 @@ static void __exit pkg_temp_thermal_exit(void)
cpuhp_remove_state(pkg_thermal_hp_state);
debugfs_remove_recursive(debugfs);
kfree(packages);
+ pkg_thermal_notify_work_cleanup();
}
module_exit(pkg_temp_thermal_exit)
diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c
index d29b512a7d9f..bc8cbb995b29 100644
--- a/drivers/tty/serial/8250/8250_core.c
+++ b/drivers/tty/serial/8250/8250_core.c
@@ -58,7 +58,16 @@ 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>
/*
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index be456ea27ab2..05d4a17236cb 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -35,6 +35,7 @@
#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>
@@ -3225,9 +3226,9 @@ void serial8250_console_write(struct uart_8250_port *up, const char *s,
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);
diff --git a/drivers/tty/serial/amba-pl011.c b/drivers/tty/serial/amba-pl011.c
index c9f701aca677..81d6b15fb80a 100644
--- a/drivers/tty/serial/amba-pl011.c
+++ b/drivers/tty/serial/amba-pl011.c
@@ -2236,13 +2236,19 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
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
@@ -2268,8 +2274,7 @@ pl011_console_write(struct console *co, const char *s, unsigned int count)
pl011_write(old_cr, uap, REG_CR);
if (locked)
- spin_unlock(&uap->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&uap->port.lock, flags);
clk_disable(uap->clk);
}
diff --git a/drivers/tty/serial/omap-serial.c b/drivers/tty/serial/omap-serial.c
index 26a22b100df1..69117e355bcd 100644
--- a/drivers/tty/serial/omap-serial.c
+++ b/drivers/tty/serial/omap-serial.c
@@ -1311,13 +1311,10 @@ serial_omap_console_write(struct console *co, const char *s,
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
@@ -1346,8 +1343,7 @@ serial_omap_console_write(struct console *co, const char *s,
pm_runtime_mark_last_busy(up->dev);
pm_runtime_put_autosuspend(up->dev);
if (locked)
- spin_unlock(&up->port.lock);
- local_irq_restore(flags);
+ spin_unlock_irqrestore(&up->port.lock, flags);
}
static int __init
diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index d0b2e0ed9bab..91f4f2bd55b0 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1775,9 +1775,9 @@ static void __usb_hcd_giveback_urb(struct urb *urb)
* and no one may trigger the above deadlock situation when
* running complete() in tasklet.
*/
- local_irq_save(flags);
+ local_irq_save_nort(flags);
urb->complete(urb);
- local_irq_restore(flags);
+ local_irq_restore_nort(flags);
usb_anchor_resume_wakeups(anchor);
atomic_dec(&urb->use_count);
diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
index 52e6897fa35a..d9f2040c10f2 100644
--- a/drivers/usb/gadget/function/f_fs.c
+++ b/drivers/usb/gadget/function/f_fs.c
@@ -1613,7 +1613,7 @@ static void ffs_data_put(struct ffs_data *ffs)
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);
diff --git a/drivers/usb/gadget/function/f_ncm.c b/drivers/usb/gadget/function/f_ncm.c
index 45b334ceaf2e..5f24e6d3b6eb 100644
--- a/drivers/usb/gadget/function/f_ncm.c
+++ b/drivers/usb/gadget/function/f_ncm.c
@@ -77,9 +77,7 @@ struct f_ncm {
struct sk_buff *skb_tx_ndp;
u16 ndp_dgram_count;
bool timer_force_tx;
- struct tasklet_struct tx_tasklet;
struct hrtimer task_timer;
-
bool timer_stopping;
};
@@ -1108,7 +1106,7 @@ static struct sk_buff *ncm_wrap_ntb(struct gether *port,
/* Delay the timer. */
hrtimer_start(&ncm->task_timer, TX_TIMEOUT_NSECS,
- HRTIMER_MODE_REL);
+ HRTIMER_MODE_REL_SOFT);
/* Add the datagram position entries */
ntb_ndp = skb_put_zero(ncm->skb_tx_ndp, dgram_idx_len);
@@ -1152,17 +1150,15 @@ err:
}
/*
- * This transmits the NTB if there are frames waiting.
+ * The transmit should only be run if no skb data has been sent
+ * for a certain duration.
*/
-static void ncm_tx_tasklet(unsigned long data)
+static enum hrtimer_restart ncm_tx_timeout(struct hrtimer *data)
{
- struct f_ncm *ncm = (void *)data;
-
- if (ncm->timer_stopping)
- return;
+ struct f_ncm *ncm = container_of(data, struct f_ncm, task_timer);
/* Only send if data is available. */
- if (ncm->skb_tx_data) {
+ if (!ncm->timer_stopping && ncm->skb_tx_data) {
ncm->timer_force_tx = true;
/* XXX This allowance of a NULL skb argument to ndo_start_xmit
@@ -1175,16 +1171,6 @@ static void ncm_tx_tasklet(unsigned long data)
ncm->timer_force_tx = false;
}
-}
-
-/*
- * The transmit should only be run if no skb data has been sent
- * for a certain duration.
- */
-static enum hrtimer_restart ncm_tx_timeout(struct hrtimer *data)
-{
- struct f_ncm *ncm = container_of(data, struct f_ncm, task_timer);
- tasklet_schedule(&ncm->tx_tasklet);
return HRTIMER_NORESTART;
}
@@ -1517,8 +1503,7 @@ static int ncm_bind(struct usb_configuration *c, struct usb_function *f)
ncm->port.open = ncm_open;
ncm->port.close = ncm_close;
- tasklet_init(&ncm->tx_tasklet, ncm_tx_tasklet, (unsigned long) ncm);
- hrtimer_init(&ncm->task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&ncm->task_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
ncm->task_timer.function = ncm_tx_timeout;
DBG(cdev, "CDC Network: %s speed IN/%s OUT/%s NOTIFY/%s\n",
@@ -1627,7 +1612,6 @@ static void ncm_unbind(struct usb_configuration *c, struct usb_function *f)
DBG(c->cdev, "ncm unbind\n");
hrtimer_cancel(&ncm->task_timer);
- tasklet_kill(&ncm->tx_tasklet);
ncm_string_defs[0].id = 0;
usb_free_all_descriptors(f);
diff --git a/drivers/usb/gadget/legacy/inode.c b/drivers/usb/gadget/legacy/inode.c
index 5c28bee327e1..ed49dba4704d 100644
--- a/drivers/usb/gadget/legacy/inode.c
+++ b/drivers/usb/gadget/legacy/inode.c
@@ -347,7 +347,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
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)) {
@@ -356,7 +356,7 @@ ep_io (struct ep_data *epdata, void *buf, unsigned len)
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 {
diff --git a/fs/aio.c b/fs/aio.c
index 3a749c3a92e3..24c6ceadaae6 100644
--- a/fs/aio.c
+++ b/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>
@@ -117,6 +118,7 @@ struct kioctx {
struct rcu_head free_rcu;
struct work_struct free_work; /* see free_ioctx() */
+ struct swork_event free_swork; /* see free_ioctx() */
/*
* signals when all in-flight requests are done
@@ -259,6 +261,7 @@ 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.");
@@ -633,9 +636,9 @@ static void free_ioctx_reqs(struct percpu_ref *ref)
* 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);
@@ -653,6 +656,14 @@ static void free_ioctx_users(struct percpu_ref *ref)
percpu_ref_put(&ctx->reqs);
}
+static void free_ioctx_users(struct percpu_ref *ref)
+{
+ struct kioctx *ctx = container_of(ref, struct kioctx, users);
+
+ INIT_SWORK(&ctx->free_swork, free_ioctx_users_work);
+ swork_queue(&ctx->free_swork);
+}
+
static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm)
{
unsigned i, new_nr;
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 4737615f0eaa..bf71f1aaecbe 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -20,6 +20,7 @@
#include <linux/sched.h>
#include <linux/mount.h>
#include <linux/namei.h>
+#include <linux/delay.h>
#include <linux/uaccess.h>
#include <linux/mutex.h>
#include <linux/spinlock.h>
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 57725d4a8c59..62220508bace 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -148,7 +148,7 @@ 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);
diff --git a/fs/buffer.c b/fs/buffer.c
index b96f3b98a6ef..4ca5f222537a 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -302,8 +302,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
* 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;
@@ -316,8 +315,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
}
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
@@ -329,9 +327,7 @@ static void end_buffer_async_read(struct buffer_head *bh, int uptodate)
return;
still_busy:
- bit_spin_unlock(BH_Uptodate_Lock, &first->b_state);
- local_irq_restore(flags);
- return;
+ bh_uptodate_unlock_irqrestore(first, flags);
}
/*
@@ -358,8 +354,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
}
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);
@@ -371,15 +366,12 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
}
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);
@@ -3417,6 +3409,7 @@ struct buffer_head *alloc_buffer_head(gfp_t gfp_flags)
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();
diff --git a/fs/cifs/readdir.c b/fs/cifs/readdir.c
index a27fc8791551..791aecb7c1ac 100644
--- a/fs/cifs/readdir.c
+++ b/fs/cifs/readdir.c
@@ -80,7 +80,7 @@ cifs_prime_dcache(struct dentry *parent, struct qstr *name,
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);
diff --git a/fs/dcache.c b/fs/dcache.c
index 5f31a93150d1..c1c1f3ce00ca 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -19,6 +19,7 @@
#include <linux/mm.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
+#include <linux/delay.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/hash.h>
@@ -796,6 +797,8 @@ static inline bool fast_dput(struct dentry *dentry)
*/
void dput(struct dentry *dentry)
{
+ struct dentry *parent;
+
if (unlikely(!dentry))
return;
@@ -832,9 +835,18 @@ repeat:
return;
kill_it:
- dentry = dentry_kill(dentry);
- if (dentry) {
- cond_resched();
+ parent = dentry_kill(dentry);
+ if (parent) {
+ int r;
+
+ if (parent == dentry) {
+ /* the task with the highest priority won't schedule */
+ r = cond_resched();
+ if (!r)
+ cpu_chill();
+ } else {
+ dentry = parent;
+ }
goto repeat;
}
}
@@ -2394,7 +2406,7 @@ again:
if (dentry->d_lockref.count == 1) {
if (!spin_trylock(&inode->i_lock)) {
spin_unlock(&dentry->d_lock);
- cpu_relax();
+ cpu_chill();
goto again;
}
dentry->d_flags &= ~DCACHE_CANT_MOUNT;
@@ -2439,9 +2451,10 @@ 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();
}
@@ -2449,26 +2462,30 @@ static inline unsigned start_dir_add(struct inode *dir)
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);
@@ -2482,7 +2499,7 @@ struct dentry *d_alloc_parallel(struct dentry *parent,
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)) {
@@ -2510,7 +2527,7 @@ 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;
@@ -2583,7 +2600,7 @@ void __d_lookup_done(struct dentry *dentry)
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);
@@ -3618,6 +3635,8 @@ __setup("dhash_entries=", set_dhash_entries);
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.
*/
@@ -3634,10 +3653,14 @@ static void __init dcache_init_early(void)
&d_hash_mask,
0,
0);
+
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
+ INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
}
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
@@ -3660,6 +3683,10 @@ static void __init dcache_init(void)
&d_hash_mask,
0,
0);
+
+ for (loop = 0; loop < (1U << d_hash_shift); loop++)
+ INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
+
}
/* SLAB cache for __getname() consumers */
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 2fabd19cdeea..b768c32631eb 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -587,12 +587,12 @@ static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
*/
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();
}
static void ep_remove_wait_queue(struct eppoll_entry *pwq)
diff --git a/fs/exec.c b/fs/exec.c
index 0da4d748b4e6..609aee4dbfa9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1024,12 +1024,14 @@ static int exec_mmap(struct mm_struct *mm)
}
}
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);
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index db7590178dfc..d76364124443 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -95,8 +95,7 @@ static void ext4_finish_bio(struct bio *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 *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)
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 7a980b4462d9..6dfe526c832f 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1187,7 +1187,7 @@ static int fuse_direntplus_link(struct file *file,
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) {
/*
diff --git a/fs/inode.c b/fs/inode.c
index cfc36d11bcb3..b77ce179798a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -154,7 +154,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
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;
diff --git a/fs/libfs.c b/fs/libfs.c
index 3aabe553fc45..b5d63bf1ad8e 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -90,7 +90,7 @@ static struct dentry *next_positive(struct dentry *parent,
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 *cursor, struct list_head *after)
else
list_add_tail(&cursor->d_child, &parent->d_subdirs);
smp_store_release(seq, n + 2);
+ preempt_enable_rt();
spin_unlock(&parent->d_lock);
}
diff --git a/fs/locks.c b/fs/locks.c
index 1bd71c4d663a..fef5f1e29a4f 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -945,7 +945,7 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request)
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 *inode, struct file_lock *request,
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 *inode, struct file_lock *request,
}
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, unsigned int mode, unsigned int type)
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;
@@ -1619,7 +1619,7 @@ 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) {
@@ -1629,7 +1629,7 @@ 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);
}
@@ -1704,7 +1704,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr
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);
@@ -1775,7 +1775,7 @@ 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);
@@ -1798,7 +1798,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
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 &&
@@ -1811,7 +1811,7 @@ static int generic_delete_lease(struct file *filp, void *owner)
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;
}
@@ -2535,13 +2535,13 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx)
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);
}
diff --git a/fs/namei.c b/fs/namei.c
index 0b46b858cd42..f5c6c2ec44ce 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1627,7 +1627,7 @@ static struct dentry *lookup_slow(const struct qstr *name,
{
struct dentry *dentry = ERR_PTR(-ENOENT), *old;
struct inode *inode = dir->d_inode;
- DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
+ DECLARE_SWAIT_QUEUE_HEAD_ONSTACK(wq);
inode_lock_shared(inode);
/* Don't go there if it's already dead */
@@ -3100,7 +3100,7 @@ static int lookup_open(struct nameidata *nd, struct path *path,
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;
diff --git a/fs/namespace.c b/fs/namespace.c
index 1eb3bfd8be5a..78aae83453dd 100644
--- a/fs/namespace.c
+++ b/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 (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD)
- cpu_relax();
+ while (ACCESS_ONCE(mnt->mnt.mnt_flags) & MNT_WRITE_HOLD) {
+ preempt_enable();
+ cpu_chill();
+ preempt_disable();
+ }
/*
* After the slowpath clears MNT_WRITE_HOLD, mnt_is_readonly will
* be set to match its requirements. So we must not load that until
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 606dd3871f66..fa41eb75b4d8 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -150,11 +150,11 @@ 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);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index bf2c43635062..f43f5da4a8c3 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -452,7 +452,7 @@ 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);
@@ -1443,7 +1443,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
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 };
@@ -1763,7 +1763,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
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) {
@@ -1773,7 +1777,11 @@ int nfs_rmdir(struct inode *dir, struct dentry *dentry)
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);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 134d9f560240..ff64167f9811 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2014,7 +2014,11 @@ 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);
}
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index a73144b3cb8c..0c403d280b96 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -112,7 +112,7 @@ struct nfs4_state_owner {
unsigned long so_flags;
struct list_head so_states;
struct nfs_seqid_counter so_seqid;
- seqcount_t so_reclaim_seqcount;
+ seqlock_t so_reclaim_seqlock;
struct mutex so_delegreturn_mutex;
};
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 43fbf4495090..751063bd6211 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2689,7 +2689,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
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);
if (ret != 0)
@@ -2727,7 +2727,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
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);
}
out:
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 45873ed92057..c487a1ca7106 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -494,7 +494,7 @@ nfs4_alloc_state_owner(struct nfs_server *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;
}
@@ -1519,8 +1519,12 @@ static int nfs4_reclaim_open_state(struct nfs4_state_owner *sp, const struct nfs
* 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))
@@ -1589,14 +1593,20 @@ 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;
}
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 630b4a3c1a93..0dc1d3e6a62f 100644
--- a/fs/nfs/unlink.c
+++ b/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_task *task, void *calldata)
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(void *calldata)
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 *dentry, struct nfs_unlinkdata *data)
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 *dentry, struct nfs_unlinkdata *data)
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, const struct qstr *name)
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);
diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c
index cc91856b5e2d..a982d7c3ad91 100644
--- a/fs/ntfs/aops.c
+++ b/fs/ntfs/aops.c
@@ -93,13 +93,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
ofs = 0;
if (file_ofs < init_size)
ofs = init_size - file_ofs;
- local_irq_save(flags);
+ local_irq_save_nort(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);
+ local_irq_restore_nort(flags);
}
} else {
clear_buffer_uptodate(bh);
@@ -108,8 +108,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
"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 +123,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
}
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 +144,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
recs = PAGE_SIZE / rec_size;
/* Should have been verified before we got here... */
BUG_ON(!recs);
- local_irq_save(flags);
+ local_irq_save_nort(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);
+ local_irq_restore_nort(flags);
flush_dcache_page(page);
if (likely(page_uptodate && !PageError(page)))
SetPageUptodate(page);
@@ -160,9 +158,7 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate)
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);
}
/**
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 4ac811e1a26c..9dcb40690cde 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -386,9 +386,9 @@ static inline void task_context_switch_counts(struct seq_file *m,
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));
}
int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c5c42f3e33d1..f5dcd63f37aa 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1886,7 +1886,7 @@ bool proc_fill_cache(struct file *file, struct dir_context *ctx,
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;
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index 82ac5f682b73..c35714621a38 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -679,7 +679,7 @@ static bool proc_sys_fill_cache(struct file *file,
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;
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 040612ec9598..b3d9d435926c 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -471,7 +471,10 @@ static int do_timerfd_settime(int ufd, int flags,
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);
}
/*
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index b0cccf8a81a8..eaa4383defec 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -120,8 +120,7 @@ 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) {
@@ -143,8 +142,7 @@ 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);
diff --git a/include/acpi/platform/aclinux.h b/include/acpi/platform/aclinux.h
index 1b473efd9eb6..89ee5e1dac48 100644
--- a/include/acpi/platform/aclinux.h
+++ b/include/acpi/platform/aclinux.h
@@ -134,6 +134,7 @@
#define acpi_cache_t struct kmem_cache
#define acpi_spinlock spinlock_t *
+#define acpi_raw_spinlock raw_spinlock_t *
#define acpi_cpu_flags unsigned long
/* Use native linux version of acpi_os_allocate_zeroed */
@@ -152,6 +153,20 @@
#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_get_thread_id
#define ACPI_USE_ALTERNATE_PROTOTYPE_acpi_os_create_lock
+#define acpi_os_create_raw_lock(__handle) \
+({ \
+ raw_spinlock_t *lock = ACPI_ALLOCATE(sizeof(*lock)); \
+ \
+ if (lock) { \
+ *(__handle) = lock; \
+ raw_spin_lock_init(*(__handle)); \
+ } \
+ lock ? AE_OK : AE_NO_MEMORY; \
+ })
+
+#define acpi_os_delete_raw_lock(__handle) kfree(__handle)
+
+
/*
* OSL interfaces used by debugger/disassembler
*/
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index ae1a33aa8955..c6d04eca8345 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -234,6 +234,20 @@ void __warn(const char *file, int line, void *caller, unsigned taint,
# define WARN_ON_SMP(x) ({0;})
#endif
+#ifdef CONFIG_PREEMPT_RT_BASE
+# define BUG_ON_RT(c) BUG_ON(c)
+# define BUG_ON_NONRT(c) do { } while (0)
+# define WARN_ON_RT(condition) WARN_ON(condition)
+# define WARN_ON_NONRT(condition) do { } while (0)
+# define WARN_ON_ONCE_NONRT(condition) do { } while (0)
+#else
+# define BUG_ON_RT(c) do { } while (0)
+# define BUG_ON_NONRT(c) BUG_ON(c)
+# define WARN_ON_RT(condition) do { } while (0)
+# define WARN_ON_NONRT(condition) WARN_ON(condition)
+# define WARN_ON_ONCE_NONRT(condition) WARN_ON_ONCE(condition)
+#endif
+
#endif /* __ASSEMBLY__ */
#endif
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 994cbb0f7ffc..0d4b7e3489a9 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -226,7 +226,7 @@ static inline u16 blk_mq_unique_tag_to_tag(u32 unique_tag)
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);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 4d4af0e94059..cbf9d5730dd3 100644
--- a/include/linux/blkdev.h
+++ b/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>
struct module;
struct scsi_ioctl_command;
@@ -134,6 +135,9 @@ typedef __u32 __bitwise req_flags_t;
*/
struct request {
struct list_head queuelist;
+#ifdef CONFIG_PREEMPT_RT_FULL
+ struct work_struct work;
+#endif
union {
struct __call_single_data csd;
u64 fifo_time;
@@ -596,6 +600,7 @@ struct request_queue {
#endif
struct rcu_head rcu_head;
wait_queue_head_t mq_freeze_wq;
+ struct swork_event mq_pcpu_wake;
struct percpu_ref q_usage_counter;
struct list_head all_q_node;
diff --git a/include/linux/bottom_half.h b/include/linux/bottom_half.h
index a19519f4241d..40dd5ef9c154 100644
--- a/include/linux/bottom_half.h
+++ b/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 */
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index afa37f807f12..48505fade7e1 100644
--- a/include/linux/buffer_head.h
+++ b/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.
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4e8f77504a57..8155c26315b7 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -19,6 +19,7 @@
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
#include <linux/bpf-cgroup.h>
+#include <linux/swork.h>
#ifdef CONFIG_CGROUPS
@@ -152,6 +153,7 @@ struct cgroup_subsys_state {
/* percpu_ref killing and RCU release */
struct rcu_head rcu_head;
struct work_struct destroy_work;
+ struct swork_event destroy_swork;
/*
* PI: the parent css. Placed here for cache proximity to following
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 7828451e161a..f5838b10cf84 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,7 +9,7 @@
* See kernel/sched/completion.c for details.
*/
-#include <linux/wait.h>
+#include <linux/swait.h>
#ifdef CONFIG_LOCKDEP_COMPLETIONS
#include <linux/lockdep.h>
#endif
@@ -28,7 +28,7 @@
*/
struct completion {
unsigned int done;
- wait_queue_head_t wait;
+ struct swait_queue_head wait;
#ifdef CONFIG_LOCKDEP_COMPLETIONS
struct lockdep_map_cross map;
#endif
@@ -67,11 +67,11 @@ static inline void complete_release_commit(struct completion *x) {}
#ifdef CONFIG_LOCKDEP_COMPLETIONS
#define COMPLETION_INITIALIZER(work) \
- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
+ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) }
#else
#define COMPLETION_INITIALIZER(work) \
- { 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+ { 0, __SWAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
#endif
#define COMPLETION_INITIALIZER_ONSTACK(work) \
@@ -117,7 +117,7 @@ static inline void complete_release_commit(struct completion *x) {}
static inline void __init_completion(struct completion *x)
{
x->done = 0;
- init_waitqueue_head(&x->wait);
+ init_swait_queue_head(&x->wait);
}
/**
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 9546bf2fe310..74fcf89801f0 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -118,6 +118,8 @@ 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 */
@@ -128,6 +130,9 @@ 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 */
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 006f4ccda5f5..d413993f7f17 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -107,7 +107,7 @@ 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 void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op
extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
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 *);
diff --git a/include/linux/delay.h b/include/linux/delay.h
index b78bab4395d8..7c4bc414a504 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -64,4 +64,10 @@ static inline void ssleep(unsigned int seconds)
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) */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc613f20e5a6..b806e2116f5c 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -655,7 +655,7 @@ struct inode {
struct block_device *i_bdev;
struct cdev *i_cdev;
char *i_link;
- unsigned i_dir_seq;
+ unsigned __i_dir_seq;
};
__u32 i_generation;
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 776f90f3a1cd..5f0bd7a3e6a7 100644
--- a/include/linux/highmem.h
+++ b/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 *page)
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 page *page)
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 *addr)
#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
}
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 012c37fdb688..3bd606859b0a 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -22,19 +22,42 @@
#include <linux/percpu.h>
#include <linux/timer.h>
#include <linux/timerqueue.h>
+#include <linux/wait.h>
struct hrtimer_clock_base;
struct hrtimer_cpu_base;
/*
* Mode arguments of xxx_hrtimer functions:
+ *
+ * HRTIMER_MODE_ABS - Time value is absolute
+ * HRTIMER_MODE_REL - Time value is relative to now
+ * HRTIMER_MODE_PINNED - Timer is bound to CPU (is only considered
+ * when starting the timer)
+ * HRTIMER_MODE_SOFT - Timer callback function will be executed in
+ * soft irq context
*/
enum hrtimer_mode {
- HRTIMER_MODE_ABS = 0x0, /* Time value is absolute */
- HRTIMER_MODE_REL = 0x1, /* Time value is relative to now */
- HRTIMER_MODE_PINNED = 0x02, /* Timer is bound to CPU */
- HRTIMER_MODE_ABS_PINNED = 0x02,
- HRTIMER_MODE_REL_PINNED = 0x03,
+ HRTIMER_MODE_ABS = 0x00,
+ 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,
+
+ HRTIMER_MODE_ABS_SOFT = HRTIMER_MODE_ABS | HRTIMER_MODE_SOFT,
+ HRTIMER_MODE_REL_SOFT = HRTIMER_MODE_REL | HRTIMER_MODE_SOFT,
+
+ 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,
};
/*
@@ -87,6 +110,7 @@ enum hrtimer_restart {
* @base: pointer to the timer base (per cpu and per clock)
* @state: state information (See bit values above)
* @is_rel: Set if the timer was armed relative
+ * @is_soft: Set if hrtimer will be expired in soft interrupt context.
*
* The hrtimer structure must be initialized by hrtimer_init()
*/
@@ -97,6 +121,7 @@ struct hrtimer {
struct hrtimer_clock_base *base;
u8 state;
u8 is_rel;
+ u8 is_soft;
};
/**
@@ -112,9 +137,9 @@ struct hrtimer_sleeper {
};
#ifdef CONFIG_64BIT
-# define HRTIMER_CLOCK_BASE_ALIGN 64
+# define __hrtimer_clock_base_align ____cacheline_aligned
#else
-# define HRTIMER_CLOCK_BASE_ALIGN 32
+# define __hrtimer_clock_base_align
#endif
/**
@@ -123,48 +148,57 @@ struct hrtimer_sleeper {
* @index: clock type index for per_cpu support when moving a
* timer to a base on another cpu.
* @clockid: clock id for per_cpu support
+ * @seq: seqcount around __run_hrtimer
+ * @running: pointer to the currently running hrtimer
* @active: red black tree root node for the active timers
* @get_time: function to retrieve the current time of the clock
* @offset: offset of this clock to the monotonic base
*/
struct hrtimer_clock_base {
struct hrtimer_cpu_base *cpu_base;
- int index;
+ unsigned int index;
clockid_t clockid;
+ seqcount_t seq;
+ struct hrtimer *running;
struct timerqueue_head active;
ktime_t (*get_time)(void);
ktime_t offset;
-} __attribute__((__aligned__(HRTIMER_CLOCK_BASE_ALIGN)));
+} __hrtimer_clock_base_align;
enum hrtimer_base_type {
HRTIMER_BASE_MONOTONIC,
HRTIMER_BASE_REALTIME,
HRTIMER_BASE_BOOTTIME,
HRTIMER_BASE_TAI,
+ HRTIMER_BASE_MONOTONIC_SOFT,
+ HRTIMER_BASE_REALTIME_SOFT,
+ HRTIMER_BASE_BOOTTIME_SOFT,
+ HRTIMER_BASE_TAI_SOFT,
HRTIMER_MAX_CLOCK_BASES,
};
-/*
+/**
* struct hrtimer_cpu_base - the per cpu clock bases
* @lock: lock protecting the base and associated clock bases
* and timers
- * @seq: seqcount around __run_hrtimer
- * @running: pointer to the currently running hrtimer
* @cpu: cpu number
* @active_bases: Bitfield to mark bases with active timers
* @clock_was_set_seq: Sequence counter of clock was set events
- * @migration_enabled: The migration of hrtimers to other cpus is enabled
- * @nohz_active: The nohz functionality is enabled
- * @expires_next: absolute time of the next event which was scheduled
- * via clock_set_next_event()
- * @next_timer: Pointer to the first expiring timer
- * @in_hrtirq: hrtimer_interrupt() is currently executing
* @hres_active: State of high resolution mode
+ * @in_hrtirq: hrtimer_interrupt() is currently executing
* @hang_detected: The last hrtimer interrupt detected a hang
+ * @softirq_activated: displays, if the softirq is raised - update of softirq
+ * related settings is not required then.
* @nr_events: Total number of hrtimer interrupt events
* @nr_retries: Total number of hrtimer interrupt retries
* @nr_hangs: Total number of hrtimer interrupt hangs
* @max_hang_time: Maximum time spent in hrtimer_interrupt
+ * @expires_next: absolute time of the next event, is required for remote
+ * hrtimer enqueue; it is the total first expiry time (hard
+ * and soft hrtimer are taken into account)
+ * @next_timer: Pointer to the first expiring timer
+ * @softirq_expires_next: Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer: Pointer to the first expiring softirq based timer
* @clock_base: array of clock bases for this cpu
*
* Note: next_timer is just an optimization for __remove_hrtimer().
@@ -173,31 +207,31 @@ enum hrtimer_base_type {
*/
struct hrtimer_cpu_base {
raw_spinlock_t lock;
- seqcount_t seq;
- struct hrtimer *running;
unsigned int cpu;
unsigned int active_bases;
unsigned int clock_was_set_seq;
- bool migration_enabled;
- bool nohz_active;
+ unsigned int hres_active : 1,
+ in_hrtirq : 1,
+ hang_detected : 1,
+ softirq_activated : 1;
#ifdef CONFIG_HIGH_RES_TIMERS
- unsigned int in_hrtirq : 1,
- hres_active : 1,
- hang_detected : 1;
- ktime_t expires_next;
- struct hrtimer *next_timer;
unsigned int nr_events;
- unsigned int nr_retries;
- unsigned int nr_hangs;
+ unsigned short nr_retries;
+ unsigned short nr_hangs;
unsigned int max_hang_time;
#endif
+ 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;
static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
{
- BUILD_BUG_ON(sizeof(struct hrtimer_clock_base) > HRTIMER_CLOCK_BASE_ALIGN);
-
timer->node.expires = time;
timer->_softexpires = time;
}
@@ -266,16 +300,17 @@ static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
return timer->base->get_time();
}
+static inline int hrtimer_is_hres_active(struct hrtimer *timer)
+{
+ return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ?
+ timer->base->cpu_base->hres_active : 0;
+}
+
#ifdef CONFIG_HIGH_RES_TIMERS
struct clock_event_device;
extern void hrtimer_interrupt(struct clock_event_device *dev);
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
- return timer->base->cpu_base->hres_active;
-}
-
/*
* The resolution of the clocks. The resolution value is returned in
* the clock_getres() system call to give application programmers an
@@ -298,11 +333,6 @@ extern unsigned int hrtimer_resolution;
#define hrtimer_resolution (unsigned int)LOW_RES_NSEC
-static inline int hrtimer_is_hres_active(struct hrtimer *timer)
-{
- return 0;
-}
-
static inline void clock_was_set_delayed(void) { }
#endif
@@ -344,10 +374,17 @@ DECLARE_PER_CPU(struct tick_device, tick_cpu_device);
/* 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
@@ -357,6 +394,15 @@ static inline void hrtimer_init_on_stack(struct hrtimer *timer,
{
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
@@ -365,11 +411,12 @@ extern void hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim,
u64 range_ns, const enum hrtimer_mode mode);
/**
- * hrtimer_start - (re)start an hrtimer on the current CPU
+ * hrtimer_start - (re)start an hrtimer
* @timer: the timer to be added
* @tim: expiry time
- * @mode: expiry mode: absolute (HRTIMER_MODE_ABS) or
- * relative (HRTIMER_MODE_REL)
+ * @mode: timer mode: absolute (HRTIMER_MODE_ABS) or
+ * relative (HRTIMER_MODE_REL), and pinned (HRTIMER_MODE_PINNED);
+ * softirq based mode is considered for debug purpose only!
*/
static inline void hrtimer_start(struct hrtimer *timer, ktime_t tim,
const enum hrtimer_mode mode)
@@ -396,6 +443,13 @@ static inline void hrtimer_restart(struct hrtimer *timer)
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);
@@ -420,9 +474,9 @@ static inline int hrtimer_is_queued(struct hrtimer *timer)
* 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->cpu_base->running == timer;
+ return timer->base->running == timer;
}
/* Forward a hrtimer so it expires after now: */
@@ -458,15 +512,12 @@ extern long hrtimer_nanosleep(const struct timespec64 *rqtp,
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,
u64 delta,
const enum hrtimer_mode mode,
- int clock);
+ clockid_t clock_id);
extern int schedule_hrtimeout(ktime_t *expires, const enum hrtimer_mode mode);
/* Soft interrupt function to run the hrtimer queues: */
diff --git a/include/linux/idr.h b/include/linux/idr.h
index 7c3a365f7e12..a922d984d9b6 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -167,10 +167,7 @@ static inline bool idr_is_empty(const struct idr *idr)
* 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_find - return pointer for given id
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 8062e6cc607c..ee3ff961b84c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -163,6 +163,12 @@ extern struct cred init_cred;
# define INIT_PERF_EVENTS(tsk)
#endif
+#if defined(CONFIG_POSIX_TIMERS) && defined(CONFIG_PREEMPT_RT_BASE)
+# define INIT_TIMER_LIST .posix_timer_list = NULL,
+#else
+# define INIT_TIMER_LIST
+#endif
+
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
# define INIT_VTIME(tsk) \
.vtime.seqcount = SEQCNT_ZERO(tsk.vtime.seqcount), \
@@ -234,7 +240,8 @@ extern struct cred init_cred;
.static_prio = MAX_PRIO-20, \
.normal_prio = MAX_PRIO-20, \
.policy = SCHED_NORMAL, \
- .cpus_allowed = CPU_MASK_ALL, \
+ .cpus_ptr = &tsk.cpus_mask, \
+ .cpus_mask = CPU_MASK_ALL, \
.nr_cpus_allowed= NR_CPUS, \
.mm = NULL, \
.active_mm = &init_mm, \
@@ -276,6 +283,7 @@ extern struct cred init_cred;
INIT_CPU_TIMERS(tsk) \
.pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.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), \
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 69c238210325..0f25fa19b2d8 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -15,6 +15,7 @@
#include <linux/hrtimer.h>
#include <linux/kref.h>
#include <linux/workqueue.h>
+#include <linux/swork.h>
#include <linux/atomic.h>
#include <asm/ptrace.h>
@@ -63,6 +64,7 @@
* 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
@@ -76,6 +78,7 @@
#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)
@@ -207,7 +210,7 @@ extern void devm_free_irq(struct device *dev, unsigned int irq, void *dev_id);
#ifdef CONFIG_LOCKDEP
# define local_irq_enable_in_hardirq() do { } while (0)
#else
-# define local_irq_enable_in_hardirq() local_irq_enable()
+# define local_irq_enable_in_hardirq() local_irq_enable_nort()
#endif
extern void disable_irq_nosync(unsigned int irq);
@@ -227,6 +230,7 @@ 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.
@@ -238,7 +242,11 @@ 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);
};
@@ -429,9 +437,13 @@ extern int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
bool state);
#ifdef CONFIG_IRQ_FORCED_THREADING
+# ifndef CONFIG_PREEMPT_RT_BASE
extern bool force_irqthreads;
+# else
+# define force_irqthreads (true)
+# endif
#else
-#define force_irqthreads (0)
+#define force_irqthreads (false)
#endif
#ifndef __ARCH_SET_SOFTIRQ_PENDING
@@ -488,9 +500,10 @@ 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
@@ -499,13 +512,25 @@ static inline void do_softirq_own_stack(void)
__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);
@@ -527,8 +552,9 @@ static inline struct task_struct *this_cpu_ksoftirqd(void)
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.
@@ -553,27 +579,36 @@ struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }
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
@@ -607,41 +642,17 @@ static inline void tasklet_disable(struct tasklet_struct *t)
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);
-struct tasklet_hrtimer {
- struct hrtimer timer;
- struct tasklet_struct tasklet;
- enum hrtimer_restart (*function)(struct hrtimer *);
-};
-
-extern void
-tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
- enum hrtimer_restart (*function)(struct hrtimer *),
- clockid_t which_clock, enum hrtimer_mode mode);
-
-static inline
-void tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
- const enum hrtimer_mode mode)
-{
- hrtimer_start(&ttimer->timer, time, mode);
-}
-
-static inline
-void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
-{
- hrtimer_cancel(&ttimer->timer);
- tasklet_kill(&ttimer->tasklet);
-}
+#ifdef CONFIG_PREEMPT_RT_FULL
+extern void softirq_early_init(void);
+#else
+static inline void softirq_early_init(void) { }
+#endif
/*
* Autoprobing for irqs:
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 0d53626405bf..ddd23c6e2e55 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -74,6 +74,7 @@ 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 {
@@ -101,13 +102,14 @@ 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)
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 9270d73ea682..1e66fac6f1d2 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -17,6 +17,7 @@
#define IRQ_WORK_BUSY 2UL
#define IRQ_WORK_FLAGS 3UL
#define IRQ_WORK_LAZY 4UL /* Doesn't want IPI, wait for tick */
+#define IRQ_WORK_HARD_IRQ 8UL /* Run hard IRQ context, even on RT */
struct irq_work {
unsigned long flags;
@@ -52,4 +53,10 @@ static inline bool irq_work_needs_cpu(void) { return false; }
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 */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index b6084898d330..d334476cdca6 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -70,6 +70,7 @@ struct irq_desc {
unsigned int irqs_unhandled;
atomic_t threads_handled;
int threads_handled_last;
+ u64 random_ip;
raw_spinlock_t lock;
struct cpumask *percpu_enabled;
const struct cpumask *percpu_affinity;
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 46cb57d5eb13..2e023bfe45af 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -34,16 +34,6 @@ do { \
current->hardirq_context--; \
crossrelease_hist_end(XHLOCK_HARD); \
} while (0)
-# define lockdep_softirq_enter() \
-do { \
- current->softirq_context++; \
- crossrelease_hist_start(XHLOCK_SOFT); \
-} while (0)
-# define lockdep_softirq_exit() \
-do { \
- current->softirq_context--; \
- crossrelease_hist_end(XHLOCK_SOFT); \
-} while (0)
# define INIT_TRACE_IRQFLAGS .softirqs_enabled = 1,
#else
# define trace_hardirqs_on() do { } while (0)
@@ -56,9 +46,23 @@ do { \
# define trace_softirqs_enabled(p) 0
# define trace_hardirq_enter() do { } while (0)
# define trace_hardirq_exit() do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+#endif
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && !defined(CONFIG_PREEMPT_RT_FULL)
+# define lockdep_softirq_enter() \
+do { \
+ current->softirq_context++; \
+ crossrelease_hist_start(XHLOCK_SOFT); \
+} while (0)
+# define lockdep_softirq_exit() \
+do { \
+ current->softirq_context--; \
+ crossrelease_hist_end(XHLOCK_SOFT); \
+} while (0)
+#else
# define lockdep_softirq_enter() do { } while (0)
# define lockdep_softirq_exit() do { } while (0)
-# define INIT_TRACE_IRQFLAGS
#endif
#if defined(CONFIG_IRQSOFF_TRACER) || \
@@ -165,4 +169,23 @@ do { \
#define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags)
+/*
+ * local_irq* variants depending on RT/!RT
+ */
+#ifdef CONFIG_PREEMPT_RT_FULL
+# define local_irq_disable_nort() do { } while (0)
+# define local_irq_enable_nort() do { } while (0)
+# define local_irq_save_nort(flags) local_save_flags(flags)
+# define local_irq_restore_nort(flags) (void)(flags)
+# define local_irq_disable_rt() local_irq_disable()
+# define local_irq_enable_rt() local_irq_enable()
+#else
+# define local_irq_disable_nort() local_irq_disable()
+# define local_irq_enable_nort() local_irq_enable()
+# define local_irq_save_nort(flags) local_irq_save(flags)
+# define local_irq_restore_nort(flags) local_irq_restore(flags)
+# define local_irq_disable_rt() do { } while (0)
+# define local_irq_enable_rt() do { } while (0)
+#endif
+
#endif
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 29290bfb94a8..32379bfab9f0 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -347,32 +347,56 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
static inline void jbd_lock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(BH_State, &bh->b_state);
+#else
+ spin_lock(&bh->b_state_lock);
+#endif
}
static inline int jbd_trylock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
return bit_spin_trylock(BH_State, &bh->b_state);
+#else
+ return spin_trylock(&bh->b_state_lock);
+#endif
}
static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
return bit_spin_is_locked(BH_State, &bh->b_state);
+#else
+ return spin_is_locked(&bh->b_state_lock);
+#endif
}
static inline void jbd_unlock_bh_state(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_unlock(BH_State, &bh->b_state);
+#else
+ spin_unlock(&bh->b_state_lock);
+#endif
}
static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_lock(BH_JournalHead, &bh->b_state);
+#else
+ spin_lock(&bh->b_journal_head_lock);
+#endif
}
static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
{
+#ifndef CONFIG_PREEMPT_RT_BASE
bit_spin_unlock(BH_JournalHead, &bh->b_state);
+#else
+ spin_unlock(&bh->b_journal_head_lock);
+#endif
}
#define J_ASSERT(assert) BUG_ON(!(assert))
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 68bd88223417..e033b25b0b72 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -167,6 +167,7 @@ extern __printf(2, 0) int vkdb_printf(enum kdb_msgsrc src, const char *fmt,
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 *, kdb_func_t, char *, char *,
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; }
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 4b484ab9e163..74feebf9d82c 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -225,6 +225,9 @@ 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,
@@ -232,6 +235,7 @@ 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
@@ -531,6 +535,7 @@ extern enum system_states {
SYSTEM_HALT,
SYSTEM_POWER_OFF,
SYSTEM_RESTART,
+ SYSTEM_SUSPEND,
} system_state;
#define TAINT_PROPRIETARY_MODULE 0
diff --git a/include/linux/list_bl.h b/include/linux/list_bl.h
index 3fc2cc57ba1b..0b5de7d9ffcf 100644
--- a/include/linux/list_bl.h
+++ b/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)
+#el