RCU commits for 3.3
Quoted 166 lines · Paul E. McKenney
Hello, Ingo,
The major features of this series are RCU infrastructure in support of Frederic Weisbecker's tickless userspace work and a reworked
RCU_FAST_NO_HZthat improves energy efficiency on large lightly loaded SMP systems by allowing the scheduler-clock tick to be turned off more quickly upon entry to idle, even when RCU callbacks are queued on the newly idle CPU. In addition,RCU_FAST_NO_HZmay now be used on systems runningTREE_PREEMPT_RCU, where earlier it was restricted toTREE_RCU.In addition, this series provides additional event tracing, rcutorture changes that improve automated KVM-based testing of RCU, introduces an
srcu_read_lock_raw()needed by uprobes, and ports a couple of patches from -rt to mainline. Finally, this series updates documentation, improves diagnostics, and fixes a number of bugs, including a nasty use of RCU from the idle task spotted and fixed by Frederic Weisbecker.These commits have been posted to LKML and updated based on feedback:
https://lkml.org/lkml/2011/11/2/363 https://lkml.org/lkml/2011/11/15/302 https://lkml.org/lkml/2011/11/28/588 https://lkml.org/lkml/2011/12/3/77 https://lkml.org/lkml/2011/12/12/625They have also been exposed to -next testing.
These changes are based off of 3.2-rc5 and are available at the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.gitrcu/nextCould you please pull them into -tip for additional testing?
Thanx, Paul
------------------>
Frederic Weisbecker (11):
rcu: Detect illegal rcu dereference in extended quiescent state
rcu: Inform the user about extended quiescent state onPROVE_RCUwarning
rcu: Warn whenrcu_read_lock()is used in extended quiescent state
nohz: Separate out irq exit and idle loop dyntick logic
nohz: Allow rcu extended quiescent state handling seperately from tick stop
x86: Enter rcu extended qs after idle notifier call
x86: Call idle notifier afterirq_enter()
rcu: Fix early call torcu_idle_enter()
nohz: Removetick_nohz_idle_enter_norcu()/tick_nohz_idle_exit_norcu()
rcu: Don't check irq nesting from rcu idle entry/exit
rcu: Irq nesting is always 0 onrcu_enter_idle_commonJosh Triplett (1):
driver-core/cpu: Expose hotpluggability to the rest of the kernelKees Cook (1):
docs: Additional LWN links to RCU APIPaul E. McKenney (49):
rcu: ->signaled better named ->fqs_state
rcu: Avoid RCU-preempt expedited grace-period botch
rcu: Makesynchronize_sched_expedited()better at work sharing
lockdep: Update documentation for lock-class leak detection
rcu: Track idleness independent of idle tasks
trace: Allowftrace_dump()to be called from modules
rcu: Add failure tracing to rcutorture
rcu: Document failing tick as cause of RCU CPU stall warning
rcu: Disable preemption inrcu_is_cpu_idle()
rcu: Remove one layer of abstraction fromPROVE_RCUchecking
rcu: Warn whensrcu_read_lock()is used in an extended quiescent state
rcu: Makesrcu_read_lock_held()call common lockdep-enabled function
powerpc: Tell RCU about idle after hcall tracing
rcu: Introduce raw SRCU read-side primitives
rcu: Add documentation for raw SRCU read-side primitives
rcu: Deconfuse dynticks entry-exit tracing
rcu: Add more information to the wrong-idle-task complaint
rcu: Allow dyntick-idle mode for CPUs with callbacks
rcu: Fix idle-task checks
rcu: PermitRCU_FAST_NO_HZto be used byTREE_PREEMPT_RCU
rcu: Add rcutorture system-shutdown capability
rcu: Control rcutorture startup from kernel boot parameters
sched: Addis_idle_task()to handle invalidated uses ofidle_cpu()
rcu: Make RCU use the newis_idle_task()API
sparc: Make SPARC use the newis_idle_task()API
kdb: Make KDB use the newis_idle_task()API
events: Make events use the newis_idle_task()API
tile: Make tile use the newis_idle_task()API
rcu: Add rcutorture CPU-hotplug capability
doc: Add load/store guarantees toDocumentation/atomic-ops.txt
rcu: Updatetrace_rcu_dyntick()header comment
rcu: Add tracing forRCU_FAST_NO_HZ
rcu: Go dyntick-idle more quickly if CPU has serviced current grace period
rcu: Avoid needlessly IPIing CPUs at GP end
rcu: EliminateRCU_FAST_NO_HZgrace-period hang
rcu: Reduce latency ofrcu_prepare_for_idle()
rcu: Remove dynticks false positives and RCU failures
rcu: Identify dyntick-idle CPUs on firstforce_quiescent_state()pass
rcu: Document same-context read-side constraints
rcu: Permit dyntick-idle with callbacks pending
rcu: Keep invoking callbacks if CPU otherwise idle
rcu: Adaptive dyntick-idle preparation
rcu: Remove redundantrcu_cpu_stall_suppressdeclaration
rcu: Make rcutorture test for hotpluggability before offlining CPUs
rcu: Add rcutorture tests forsrcu_read_lock_raw()
rcu: Augmentrcu_batch_endtracing for idle and callback state Revert "rcu: Permitrt_mutex_unlock()with irqs disabled"
rcu: ApplyACCESS_ONCE()torcu_boost()return value
cpu: Exportcpu_up()Thomas Gleixner (2):
rcu: Omit self-awaken when setting up expedited grace period
rcu: Remove redundant return fromrcu_report_exp_rnp()Documentation/RCU/checklist.txt | 6 + Documentation/RCU/rcu.txt | 10 +- Documentation/RCU/stallwarn.txt | 16 +- Documentation/RCU/torture.txt | 13 ++ Documentation/RCU/trace.txt | 4 - Documentation/RCU/whatisRCU.txt | 19 ++- Documentation/atomic_ops.txt | 87 +++++++++ Documentation/lockdep-design.txt | 63 +++++++ arch/arm/kernel/process.c | 6 +- arch/avr32/kernel/process.c | 6 +- arch/blackfin/kernel/process.c | 6 +- arch/microblaze/kernel/process.c | 6 +- arch/mips/kernel/process.c | 6 +- arch/openrisc/kernel/idle.c | 6 +- arch/powerpc/kernel/idle.c | 15 ++- arch/powerpc/platforms/iseries/setup.c | 12 +- arch/powerpc/platforms/pseries/lpar.c | 4 + arch/s390/kernel/process.c | 6 +- arch/sh/kernel/idle.c | 6 +- arch/sparc/kernel/process_64.c | 6 +- arch/sparc/kernel/setup_32.c | 2 +- arch/tile/kernel/process.c | 6 +- arch/tile/mm/fault.c | 4 +- arch/um/kernel/process.c | 6 +- arch/unicore32/kernel/process.c | 6 +- arch/x86/kernel/apic/apic.c | 6 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/mcheck/therm_throt.c | 2 +- arch/x86/kernel/cpu/mcheck/threshold.c | 2 +- arch/x86/kernel/irq.c | 6 +- arch/x86/kernel/process_32.c | 6 +- arch/x86/kernel/process_64.c | 10 +- drivers/base/cpu.c | 7 + include/linux/cpu.h | 1 + include/linux/hardirq.h | 21 --- include/linux/rcupdate.h | 115 ++++++++----- include/linux/sched.h | 8 + include/linux/srcu.h | 87 ++++++++-- include/linux/tick.h | 11 +- include/trace/events/rcu.h | 122 +++++++++++-- init/Kconfig | 10 +- kernel/cpu.c | 1 + kernel/debug/kdb/kdb_support.c | 2 +- kernel/events/core.c | 2 +- kernel/lockdep.c | 22 +++ kernel/rcu.h | 7 + kernel/rcupdate.c | 12 ++ kernel/rcutiny.c | 149 +++++++++++++-- kernel/rcutiny_plugin.h | 29 +++- kernel/rcutorture.c | 225 ++++++++++++++++++++++- kernel/rcutree.c | 290 +++++++++++++++++++++---------
Quoted 8 lines
kernel/rcutree.h | 26 ++-- kernel/rcutree_plugin.h | 289 ++++++++++++++++++++++++------ kernel/rcutree_trace.c | 12 +- kernel/rtmutex.c | 8 - kernel/softirq.c | 4 +- kernel/time/tick-sched.c | 97 ++++++---- kernel/trace/trace.c | 1 + 58 files changed, 1512 insertions(+), 407 deletions(-)
Pulled into tip:core/rcu, thanks a lot Paul!
Note that this commit from Frederic:
69e1e811dcc4: sched, nohz: Track nr_busy_cpus in the sched_group_power
conflicted with this commit from Suresh in sched/core:
69e1e811dcc4: sched, nohz: Track nr_busy_cpus in the sched_group_power
I resolved it by making the set_cpu_sd_state_idle() call unconditional within the newly decoupled tick_nohz_stop_sched_tick() function - please double check that it's the right resolution.
Thanks,
Ingo
Quoted 184 lines · Ingo Molnar
Quoted 166 lines · Paul E. McKenney
Hello, Ingo,
The major features of this series are RCU infrastructure in support of Frederic Weisbecker's tickless userspace work and a reworked
RCU_FAST_NO_HZthat improves energy efficiency on large lightly loaded SMP systems by allowing the scheduler-clock tick to be turned off more quickly upon entry to idle, even when RCU callbacks are queued on the newly idle CPU. In addition,RCU_FAST_NO_HZmay now be used on systems runningTREE_PREEMPT_RCU, where earlier it was restricted toTREE_RCU.In addition, this series provides additional event tracing, rcutorture changes that improve automated KVM-based testing of RCU, introduces an
srcu_read_lock_raw()needed by uprobes, and ports a couple of patches from -rt to mainline. Finally, this series updates documentation, improves diagnostics, and fixes a number of bugs, including a nasty use of RCU from the idle task spotted and fixed by Frederic Weisbecker.These commits have been posted to LKML and updated based on feedback:
https://lkml.org/lkml/2011/11/2/363 https://lkml.org/lkml/2011/11/15/302 https://lkml.org/lkml/2011/11/28/588 https://lkml.org/lkml/2011/12/3/77 https://lkml.org/lkml/2011/12/12/625They have also been exposed to -next testing.
These changes are based off of 3.2-rc5 and are available at the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.gitrcu/nextCould you please pull them into -tip for additional testing?
Thanx, Paul
------------------>
Frederic Weisbecker (11):
rcu: Detect illegal rcu dereference in extended quiescent state
rcu: Inform the user about extended quiescent state onPROVE_RCUwarning
rcu: Warn whenrcu_read_lock()is used in extended quiescent state
nohz: Separate out irq exit and idle loop dyntick logic
nohz: Allow rcu extended quiescent state handling seperately from tick stop
x86: Enter rcu extended qs after idle notifier call
x86: Call idle notifier afterirq_enter()
rcu: Fix early call torcu_idle_enter()
nohz: Removetick_nohz_idle_enter_norcu()/tick_nohz_idle_exit_norcu()
rcu: Don't check irq nesting from rcu idle entry/exit
rcu: Irq nesting is always 0 onrcu_enter_idle_commonJosh Triplett (1):
driver-core/cpu: Expose hotpluggability to the rest of the kernelKees Cook (1):
docs: Additional LWN links to RCU APIPaul E. McKenney (49):
rcu: ->signaled better named ->fqs_state
rcu: Avoid RCU-preempt expedited grace-period botch
rcu: Makesynchronize_sched_expedited()better at work sharing
lockdep: Update documentation for lock-class leak detection
rcu: Track idleness independent of idle tasks
trace: Allowftrace_dump()to be called from modules
rcu: Add failure tracing to rcutorture
rcu: Document failing tick as cause of RCU CPU stall warning
rcu: Disable preemption inrcu_is_cpu_idle()
rcu: Remove one layer of abstraction fromPROVE_RCUchecking
rcu: Warn whensrcu_read_lock()is used in an extended quiescent state
rcu: Makesrcu_read_lock_held()call common lockdep-enabled function
powerpc: Tell RCU about idle after hcall tracing
rcu: Introduce raw SRCU read-side primitives
rcu: Add documentation for raw SRCU read-side primitives
rcu: Deconfuse dynticks entry-exit tracing
rcu: Add more information to the wrong-idle-task complaint
rcu: Allow dyntick-idle mode for CPUs with callbacks
rcu: Fix idle-task checks
rcu: PermitRCU_FAST_NO_HZto be used byTREE_PREEMPT_RCU
rcu: Add rcutorture system-shutdown capability
rcu: Control rcutorture startup from kernel boot parameters
sched: Addis_idle_task()to handle invalidated uses ofidle_cpu()
rcu: Make RCU use the newis_idle_task()API
sparc: Make SPARC use the newis_idle_task()API
kdb: Make KDB use the newis_idle_task()API
events: Make events use the newis_idle_task()API
tile: Make tile use the newis_idle_task()API
rcu: Add rcutorture CPU-hotplug capability
doc: Add load/store guarantees toDocumentation/atomic-ops.txt
rcu: Updatetrace_rcu_dyntick()header comment
rcu: Add tracing forRCU_FAST_NO_HZ
rcu: Go dyntick-idle more quickly if CPU has serviced current grace period
rcu: Avoid needlessly IPIing CPUs at GP end
rcu: EliminateRCU_FAST_NO_HZgrace-period hang
rcu: Reduce latency ofrcu_prepare_for_idle()
rcu: Remove dynticks false positives and RCU failures
rcu: Identify dyntick-idle CPUs on firstforce_quiescent_state()pass
rcu: Document same-context read-side constraints
rcu: Permit dyntick-idle with callbacks pending
rcu: Keep invoking callbacks if CPU otherwise idle
rcu: Adaptive dyntick-idle preparation
rcu: Remove redundantrcu_cpu_stall_suppressdeclaration
rcu: Make rcutorture test for hotpluggability before offlining CPUs
rcu: Add rcutorture tests forsrcu_read_lock_raw()
rcu: Augmentrcu_batch_endtracing for idle and callback state Revert "rcu: Permitrt_mutex_unlock()with irqs disabled"
rcu: ApplyACCESS_ONCE()torcu_boost()return value
cpu: Exportcpu_up()Thomas Gleixner (2):
rcu: Omit self-awaken when setting up expedited grace period
rcu: Remove redundant return fromrcu_report_exp_rnp()Documentation/RCU/checklist.txt | 6 + Documentation/RCU/rcu.txt | 10 +- Documentation/RCU/stallwarn.txt | 16 +- Documentation/RCU/torture.txt | 13 ++ Documentation/RCU/trace.txt | 4 - Documentation/RCU/whatisRCU.txt | 19 ++- Documentation/atomic_ops.txt | 87 +++++++++ Documentation/lockdep-design.txt | 63 +++++++ arch/arm/kernel/process.c | 6 +- arch/avr32/kernel/process.c | 6 +- arch/blackfin/kernel/process.c | 6 +- arch/microblaze/kernel/process.c | 6 +- arch/mips/kernel/process.c | 6 +- arch/openrisc/kernel/idle.c | 6 +- arch/powerpc/kernel/idle.c | 15 ++- arch/powerpc/platforms/iseries/setup.c | 12 +- arch/powerpc/platforms/pseries/lpar.c | 4 + arch/s390/kernel/process.c | 6 +- arch/sh/kernel/idle.c | 6 +- arch/sparc/kernel/process_64.c | 6 +- arch/sparc/kernel/setup_32.c | 2 +- arch/tile/kernel/process.c | 6 +- arch/tile/mm/fault.c | 4 +- arch/um/kernel/process.c | 6 +- arch/unicore32/kernel/process.c | 6 +- arch/x86/kernel/apic/apic.c | 6 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/mcheck/therm_throt.c | 2 +- arch/x86/kernel/cpu/mcheck/threshold.c | 2 +- arch/x86/kernel/irq.c | 6 +- arch/x86/kernel/process_32.c | 6 +- arch/x86/kernel/process_64.c | 10 +- drivers/base/cpu.c | 7 + include/linux/cpu.h | 1 + include/linux/hardirq.h | 21 --- include/linux/rcupdate.h | 115 ++++++++----- include/linux/sched.h | 8 + include/linux/srcu.h | 87 ++++++++-- include/linux/tick.h | 11 +- include/trace/events/rcu.h | 122 +++++++++++-- init/Kconfig | 10 +- kernel/cpu.c | 1 + kernel/debug/kdb/kdb_support.c | 2 +- kernel/events/core.c | 2 +- kernel/lockdep.c | 22 +++ kernel/rcu.h | 7 + kernel/rcupdate.c | 12 ++ kernel/rcutiny.c | 149 +++++++++++++-- kernel/rcutiny_plugin.h | 29 +++- kernel/rcutorture.c | 225 ++++++++++++++++++++++- kernel/rcutree.c | 290 +++++++++++++++++++++---------Quoted 8 lines
kernel/rcutree.h | 26 ++-- kernel/rcutree_plugin.h | 289 ++++++++++++++++++++++++------ kernel/rcutree_trace.c | 12 +- kernel/rtmutex.c | 8 - kernel/softirq.c | 4 +- kernel/time/tick-sched.c | 97 ++++++---- kernel/trace/trace.c | 1 + 58 files changed, 1512 insertions(+), 407 deletions(-)Pulled into tip:core/rcu, thanks a lot Paul!
Note that this commit from Frederic:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_power
Quoted 8 lines
conflicted with this commit from Suresh in sched/core:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_powerI resolved it by making the
set_cpu_sd_state_idle()call unconditional within the newly decoupledtick_nohz_stop_sched_tick()function - please double check that it's the right resolution.
After a quick look, I believe this should rather be under tick_nohz_idle_enter(), (This is the equivalent of the old tick_nohz_stop_sched_tick(1)) This wants to be set only once we enter idle, not everytime we have an idle interrupt.
Quoted 194 lines · Frederic Weisbecker
Quoted 184 lines · Ingo Molnar
Quoted 166 lines · Paul E. McKenney
Hello, Ingo,
The major features of this series are RCU infrastructure in support of Frederic Weisbecker's tickless userspace work and a reworked
RCU_FAST_NO_HZthat improves energy efficiency on large lightly loaded SMP systems by allowing the scheduler-clock tick to be turned off more quickly upon entry to idle, even when RCU callbacks are queued on the newly idle CPU. In addition,RCU_FAST_NO_HZmay now be used on systems runningTREE_PREEMPT_RCU, where earlier it was restricted toTREE_RCU.In addition, this series provides additional event tracing, rcutorture changes that improve automated KVM-based testing of RCU, introduces an
srcu_read_lock_raw()needed by uprobes, and ports a couple of patches from -rt to mainline. Finally, this series updates documentation, improves diagnostics, and fixes a number of bugs, including a nasty use of RCU from the idle task spotted and fixed by Frederic Weisbecker.These commits have been posted to LKML and updated based on feedback:
https://lkml.org/lkml/2011/11/2/363 https://lkml.org/lkml/2011/11/15/302 https://lkml.org/lkml/2011/11/28/588 https://lkml.org/lkml/2011/12/3/77 https://lkml.org/lkml/2011/12/12/625They have also been exposed to -next testing.
These changes are based off of 3.2-rc5 and are available at the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu.gitrcu/nextCould you please pull them into -tip for additional testing?
Thanx, Paul
------------------>
Frederic Weisbecker (11):
rcu: Detect illegal rcu dereference in extended quiescent state
rcu: Inform the user about extended quiescent state onPROVE_RCUwarning
rcu: Warn whenrcu_read_lock()is used in extended quiescent state
nohz: Separate out irq exit and idle loop dyntick logic
nohz: Allow rcu extended quiescent state handling seperately from tick stop
x86: Enter rcu extended qs after idle notifier call
x86: Call idle notifier afterirq_enter()
rcu: Fix early call torcu_idle_enter()
nohz: Removetick_nohz_idle_enter_norcu()/tick_nohz_idle_exit_norcu()
rcu: Don't check irq nesting from rcu idle entry/exit
rcu: Irq nesting is always 0 onrcu_enter_idle_commonJosh Triplett (1):
driver-core/cpu: Expose hotpluggability to the rest of the kernelKees Cook (1):
docs: Additional LWN links to RCU APIPaul E. McKenney (49):
rcu: ->signaled better named ->fqs_state
rcu: Avoid RCU-preempt expedited grace-period botch
rcu: Makesynchronize_sched_expedited()better at work sharing
lockdep: Update documentation for lock-class leak detection
rcu: Track idleness independent of idle tasks
trace: Allowftrace_dump()to be called from modules
rcu: Add failure tracing to rcutorture
rcu: Document failing tick as cause of RCU CPU stall warning
rcu: Disable preemption inrcu_is_cpu_idle()
rcu: Remove one layer of abstraction fromPROVE_RCUchecking
rcu: Warn whensrcu_read_lock()is used in an extended quiescent state
rcu: Makesrcu_read_lock_held()call common lockdep-enabled function
powerpc: Tell RCU about idle after hcall tracing
rcu: Introduce raw SRCU read-side primitives
rcu: Add documentation for raw SRCU read-side primitives
rcu: Deconfuse dynticks entry-exit tracing
rcu: Add more information to the wrong-idle-task complaint
rcu: Allow dyntick-idle mode for CPUs with callbacks
rcu: Fix idle-task checks
rcu: PermitRCU_FAST_NO_HZto be used byTREE_PREEMPT_RCU
rcu: Add rcutorture system-shutdown capability
rcu: Control rcutorture startup from kernel boot parameters
sched: Addis_idle_task()to handle invalidated uses ofidle_cpu()
rcu: Make RCU use the newis_idle_task()API
sparc: Make SPARC use the newis_idle_task()API
kdb: Make KDB use the newis_idle_task()API
events: Make events use the newis_idle_task()API
tile: Make tile use the newis_idle_task()API
rcu: Add rcutorture CPU-hotplug capability
doc: Add load/store guarantees toDocumentation/atomic-ops.txt
rcu: Updatetrace_rcu_dyntick()header comment
rcu: Add tracing forRCU_FAST_NO_HZ
rcu: Go dyntick-idle more quickly if CPU has serviced current grace period
rcu: Avoid needlessly IPIing CPUs at GP end
rcu: EliminateRCU_FAST_NO_HZgrace-period hang
rcu: Reduce latency ofrcu_prepare_for_idle()
rcu: Remove dynticks false positives and RCU failures
rcu: Identify dyntick-idle CPUs on firstforce_quiescent_state()pass
rcu: Document same-context read-side constraints
rcu: Permit dyntick-idle with callbacks pending
rcu: Keep invoking callbacks if CPU otherwise idle
rcu: Adaptive dyntick-idle preparation
rcu: Remove redundantrcu_cpu_stall_suppressdeclaration
rcu: Make rcutorture test for hotpluggability before offlining CPUs
rcu: Add rcutorture tests forsrcu_read_lock_raw()
rcu: Augmentrcu_batch_endtracing for idle and callback state Revert "rcu: Permitrt_mutex_unlock()with irqs disabled"
rcu: ApplyACCESS_ONCE()torcu_boost()return value
cpu: Exportcpu_up()Thomas Gleixner (2):
rcu: Omit self-awaken when setting up expedited grace period
rcu: Remove redundant return fromrcu_report_exp_rnp()Documentation/RCU/checklist.txt | 6 + Documentation/RCU/rcu.txt | 10 +- Documentation/RCU/stallwarn.txt | 16 +- Documentation/RCU/torture.txt | 13 ++ Documentation/RCU/trace.txt | 4 - Documentation/RCU/whatisRCU.txt | 19 ++- Documentation/atomic_ops.txt | 87 +++++++++ Documentation/lockdep-design.txt | 63 +++++++ arch/arm/kernel/process.c | 6 +- arch/avr32/kernel/process.c | 6 +- arch/blackfin/kernel/process.c | 6 +- arch/microblaze/kernel/process.c | 6 +- arch/mips/kernel/process.c | 6 +- arch/openrisc/kernel/idle.c | 6 +- arch/powerpc/kernel/idle.c | 15 ++- arch/powerpc/platforms/iseries/setup.c | 12 +- arch/powerpc/platforms/pseries/lpar.c | 4 + arch/s390/kernel/process.c | 6 +- arch/sh/kernel/idle.c | 6 +- arch/sparc/kernel/process_64.c | 6 +- arch/sparc/kernel/setup_32.c | 2 +- arch/tile/kernel/process.c | 6 +- arch/tile/mm/fault.c | 4 +- arch/um/kernel/process.c | 6 +- arch/unicore32/kernel/process.c | 6 +- arch/x86/kernel/apic/apic.c | 6 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/mcheck/therm_throt.c | 2 +- arch/x86/kernel/cpu/mcheck/threshold.c | 2 +- arch/x86/kernel/irq.c | 6 +- arch/x86/kernel/process_32.c | 6 +- arch/x86/kernel/process_64.c | 10 +- drivers/base/cpu.c | 7 + include/linux/cpu.h | 1 + include/linux/hardirq.h | 21 --- include/linux/rcupdate.h | 115 ++++++++----- include/linux/sched.h | 8 + include/linux/srcu.h | 87 ++++++++-- include/linux/tick.h | 11 +- include/trace/events/rcu.h | 122 +++++++++++-- init/Kconfig | 10 +- kernel/cpu.c | 1 + kernel/debug/kdb/kdb_support.c | 2 +- kernel/events/core.c | 2 +- kernel/lockdep.c | 22 +++ kernel/rcu.h | 7 + kernel/rcupdate.c | 12 ++ kernel/rcutiny.c | 149 +++++++++++++-- kernel/rcutiny_plugin.h | 29 +++- kernel/rcutorture.c | 225 ++++++++++++++++++++++- kernel/rcutree.c | 290 +++++++++++++++++++++---------Quoted 8 lines
kernel/rcutree.h | 26 ++-- kernel/rcutree_plugin.h | 289 ++++++++++++++++++++++++------ kernel/rcutree_trace.c | 12 +- kernel/rtmutex.c | 8 - kernel/softirq.c | 4 +- kernel/time/tick-sched.c | 97 ++++++---- kernel/trace/trace.c | 1 + 58 files changed, 1512 insertions(+), 407 deletions(-)Pulled into tip:core/rcu, thanks a lot Paul!
Note that this commit from Frederic:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_powerQuoted 8 lines
conflicted with this commit from Suresh in sched/core:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_powerI resolved it by making the
set_cpu_sd_state_idle()call unconditional within the newly decoupledtick_nohz_stop_sched_tick()function - please double check that it's the right resolution.
Quoted 4 lines
After a quick look, I believe this should rather be under
tick_nohz_idle_enter(), (This is the equivalent of the oldtick_nohz_stop_sched_tick(1)) This wants to be set only once we enter idle, not everytime we have an idle interrupt.
I don't know how you plan to fix the conflict, by redoing the merge or by applying a patch on tip/master.
In any case, here is a patch you can use. Feel free to apply it as is or to just refer to its diff to redo the merge:
(Outrageously only compile tested)
---
From: Frederic Weisbecker <[email protected]>
Date: Wed, 14 Dec 2011 18:36:00 +0100
Subject: [PATCH] sched: Only update the CPU idleness in the domain
hierarchy from idle loop entry
We don't need to inform the sched domain hierarchy about the CPU idleness everytime we call tick_nohz_stop_sched_tick() as this includes both idle loop entry and idle interrupt exit.
Doing it once from the idle loop entry is enough, call set_cpu_sd_state_idle() only from tick_nohz_idle_enter() instead to fix this.
--- kernel/time/tick-sched.c | 16 ++++++++-------- 1 files changed, 8 insertions(+), 8 deletions(-)
kernel/time/tick-sched.c +8 -8
@@ -289,14 +289,6 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) now =tick_nohz_start_idle (cpu, ts);/* -* Update the idle state in the scheduler domain hierarchy -* when tick_nohz_stop_sched_tick() is called from the idle loop. -* State will be updated to busy during the first busy tick after -* exiting idle. -*/ -set_cpu_sd_state_idle (); - -/* * If this cpu is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the cpu which runs the tick timer next. If we don't drop
@@ -483,6 +475,14 @@ void tick_nohz_idle_enter(void)* update of the idle time accounting in tick_nohz_start_idle(). */ ts->inidle =1 ; + +/* +* Update the idle state in the scheduler domain hierarchy +* when tick_nohz_idle_enter() is called from the idle loop. +* State will be updated to busy during the first busy tick after +* exiting idle. +*/ +set_cpu_sd_state_idle ();tick_nohz_stop_sched_tick (ts);local_irq_enable ();
Signature · 1 line
1.7.5.4
Quoted 3 lines · Frederic Weisbecker
Quoted 2 lines · Frederic Weisbecker
Quoted 1 line · Ingo Molnar
* Paul E. McKenney <[email protected]> wrote:
[ . . . ]
Quoted 20 lines
Quoted 15 lines
Quoted 6 lines
Pulled into tip:core/rcu, thanks a lot Paul!
Note that this commit from Frederic:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_powerQuoted 8 lines
conflicted with this commit from Suresh in sched/core:
69e1e811dcc4: sched, nohz: Tracknr_busy_cpusin thesched_group_powerI resolved it by making the
set_cpu_sd_state_idle()call unconditional within the newly decoupledtick_nohz_stop_sched_tick()function - please double check that it's the right resolution.Quoted 4 lines
After a quick look, I believe this should rather be under
tick_nohz_idle_enter(), (This is the equivalent of the oldtick_nohz_stop_sched_tick(1)) This wants to be set only once we enter idle, not everytime we have an idle interrupt.
Quoted 7 lines
I don't know how you plan to fix the conflict, by redoing the merge or by applying a patch on tip/master.
In any case, here is a patch you can use. Feel free to apply it as is or to just refer to its diff to redo the merge:
(Outrageously only compile tested)
I have started up a short rcutorture test of this patch on top of tip/master, will let you know how it goes.
Thanx, Paul
Quoted 60 lines
---
From: Frederic Weisbecker <[email protected]>
Date: Wed, 14 Dec 2011 18:36:00 +0100
Subject: [PATCH] sched: Only update the CPU idleness in the domain
hierarchy from idle loop entryWe don't need to inform the sched domain hierarchy about the CPU idleness everytime we call
tick_nohz_stop_sched_tick()as this includes both idle loop entry and idle interrupt exit.Doing it once from the idle loop entry is enough, call
set_cpu_sd_state_idle()only fromtick_nohz_idle_enter()instead to fix this.Signed-off-by Frederic Weisbecker <[email protected]>Cc Paul E. McKenney <[email protected]>Cc Suresh Siddha <[email protected]>Cc Peter Zijlstra <[email protected]>--- kernel/time/tick-sched.c | 16 ++++++++-------- 1 files changed, 8 insertions(+), 8 deletions(-)kernel/time/tick-sched.c +8
-8@@ -289,14 +289,6 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) now =tick_nohz_start_idle (cpu, ts);/* -* Update the idle state in the scheduler domain hierarchy -* when tick_nohz_stop_sched_tick() is called from the idle loop. -* State will be updated to busy during the first busy tick after -* exiting idle. -*/ -set_cpu_sd_state_idle (); - -/* * If this cpu is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the cpu which runs the tick timer next. If we don't drop @@ -483,6 +475,14 @@ void tick_nohz_idle_enter(void)* update of the idle time accounting in tick_nohz_start_idle(). */ ts->inidle =1 ; + +/* +* Update the idle state in the scheduler domain hierarchy +* when tick_nohz_idle_enter() is called from the idle loop. +* State will be updated to busy during the first busy tick after +* exiting idle. +*/ +set_cpu_sd_state_idle ();tick_nohz_stop_sched_tick (ts);local_irq_enable ();Signature · 1 line
1.7.5.4
Suresh Siddha
Acked-byQuoted 18 lines · Frederic Weisbecker
I don't know how you plan to fix the conflict, by redoing the merge or by applying a patch on tip/master.
In any case, here is a patch you can use. Feel free to apply it as is or to just refer to its diff to redo the merge:
(Outrageously only compile tested)
---
From: Frederic Weisbecker <[email protected]>
Date: Wed, 14 Dec 2011 18:36:00 +0100
Subject: [PATCH] sched: Only update the CPU idleness in the domain
hierarchy from idle loop entryWe don't need to inform the sched domain hierarchy about the CPU idleness everytime we call
tick_nohz_stop_sched_tick()as this includes both idle loop entry and idle interrupt exit.
Quoted 8 lines
Doing it once from the idle loop entry is enough, call
set_cpu_sd_state_idle()only fromtick_nohz_idle_enter()instead to fix this.Signed-off-by Frederic Weisbecker <[email protected]>Cc Paul E. McKenney <[email protected]>Cc Suresh Siddha <[email protected]>Cc Peter Zijlstra <[email protected]>
Quoted 42 lines
--- kernel/time/tick-sched.c | 16 ++++++++-------- 1 files changed, 8 insertions(+), 8 deletions(-)kernel/time/tick-sched.c +8
-9@@ -289,14 +289,6 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) now =tick_nohz_start_idle (cpu, ts);/* -* Update the idle state in the scheduler domain hierarchy -* when tick_nohz_stop_sched_tick() is called from the idle loop. -* State will be updated to busy during the first busy tick after -* exiting idle. -*/ -set_cpu_sd_state_idle (); - -/* * If this cpu is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the cpu which runs the tick timer next. If we don't drop @@ -483,6 +475,14 @@ void tick_nohz_idle_enter(void)* update of the idle time accounting in tick_nohz_start_idle(). */ ts->inidle =1 ; + +/* +* Update the idle state in the scheduler domain hierarchy +* when tick_nohz_idle_enter() is called from the idle loop. +* State will be updated to busy during the first busy tick after +* exiting idle. +*/ +set_cpu_sd_state_idle ();tick_nohz_stop_sched_tick (ts);local_irq_enable (); --1.7.5.4
Paul E. McKenney
Tested-byQuoted 23 lines · Suresh Siddha
Quoted 22 lines · Frederic Weisbecker
I don't know how you plan to fix the conflict, by redoing the merge or by applying a patch on tip/master.
In any case, here is a patch you can use. Feel free to apply it as is or to just refer to its diff to redo the merge:
(Outrageously only compile tested)
---
From: Frederic Weisbecker <[email protected]>
Date: Wed, 14 Dec 2011 18:36:00 +0100
Subject: [PATCH] sched: Only update the CPU idleness in the domain
hierarchy from idle loop entryWe don't need to inform the sched domain hierarchy about the CPU idleness everytime we call
tick_nohz_stop_sched_tick()as this includes both idle loop entry and idle interrupt exit.Doing it once from the idle loop entry is enough, call
set_cpu_sd_state_idle()only fromtick_nohz_idle_enter()instead to fix this.
Quoted 6 lines
Quoted 4 lines
Signed-off-by Frederic Weisbecker <[email protected]>Cc Paul E. McKenney <[email protected]>Cc Suresh Siddha <[email protected]>Cc Peter Zijlstra <[email protected]>Acked-by Suresh Siddha <[email protected]>
Quoted 44 lines
Quoted 42 lines
--- kernel/time/tick-sched.c | 16 ++++++++-------- 1 files changed, 8 insertions(+), 8 deletions(-)kernel/time/tick-sched.c +8
-9@@ -289,14 +289,6 @@ static void tick_nohz_stop_sched_tick(struct tick_sched *ts) now =tick_nohz_start_idle (cpu, ts);/* -* Update the idle state in the scheduler domain hierarchy -* when tick_nohz_stop_sched_tick() is called from the idle loop. -* State will be updated to busy during the first busy tick after -* exiting idle. -*/ -set_cpu_sd_state_idle (); - -/* * If this cpu is offline and it is the one which updates * jiffies, then give up the assignment and let it be taken by * the cpu which runs the tick timer next. If we don't drop @@ -483,6 +475,14 @@ void tick_nohz_idle_enter(void)* update of the idle time accounting in tick_nohz_start_idle(). */ ts->inidle =1 ; + +/* +* Update the idle state in the scheduler domain hierarchy +* when tick_nohz_idle_enter() is called from the idle loop. +* State will be updated to busy during the first busy tick after +* exiting idle. +*/ +set_cpu_sd_state_idle ();tick_nohz_stop_sched_tick (ts);local_irq_enable (); --1.7.5.4
Quoted 2 lines · Frederic Weisbecker
I don't know how you plan to fix the conflict, by redoing the merge or by applying a patch on tip/master.
I've re-done the merge - thanks guys!
Ingo