- 25 Sep, 2019 16 commits
-
-
Quentin Perret authored
The EAS wake-up path computes the system energy for several CPU candidates: the CPU with maximum spare capacity in each performance domain, and the prev_cpu. However, if prev_cpu also happens to be the CPU with maximum spare capacity in its performance domain, the energy calculation is still done twice, unnecessarily. Add a condition to filter out this corner case before doing the energy calculation. Reported-by:
Pavan Kondeti <pkondeti@codeaurora.org> Signed-off-by:
Quentin Perret <qperret@qperret.net> Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: dietmar.eggemann@arm.com Cc: juri.lelli@redhat.com Cc: morten.rasmussen@arm.com Cc: qais.yousef@arm.com Cc: rjw@rjwysocki.net Cc: tkjos@google.com Cc: valentin.schneider@arm.com Cc: vincent.guittot@linaro.org Fixes: eb92692b ("sched/fair: Speed-up energy-aware wake-ups") Link: https://lkml.kernel.org/r/20190920094115.GA11503@qperret.netSigned-off-by:
Ingo Molnar <mingo@kernel.org>
-
Valentin Schneider authored
update_max_interval() is called in both CPUHP_AP_SCHED_STARTING's startup and teardown callbacks, but it turns out it's also called at the end of the startup callback of CPUHP_AP_ACTIVE (which is further down the startup sequence). There's no point in repeating this interval update in the startup sequence since the CPU will remain online until it goes down the teardown path. Remove the redundant call in sched_cpu_activate() (CPUHP_AP_ACTIVE). Signed-off-by:
Valentin Schneider <valentin.schneider@arm.com> Signed-off-by:
-
Valentin Schneider authored
preempt_schedule_irq() is the one that should be called on return from interrupt, clean up the comment to avoid any ambiguity. Signed-off-by:
Thomas Gleixner <tglx@linutronix.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-m68k@lists.linux-m68k.org Cc: linux-riscv@lists.infradead.org Cc: uclinux-h8-devel@lists.sourceforge.jp Link: https://lkml.kernel.org/r/20190923143620.29334-2-valentin.schneider@arm.comSigned-off-by:
-
Qian Cai authored
Commit: de53fd7a ("sched/fair: Fix low cpu usage with high throttling by removing expiration of cpu-local slices") introduced a few compilation warnings: kernel/sched/fair.c: In function '__refill_cfs_bandwidth_runtime': kernel/sched/fair.c:4365:6: warning: variable 'now' set but not used [-Wunused-but-set-variable] kernel/sched/fair.c: In function 'start_cfs_bandwidth': kernel/sched/fair.c:4992:6: warning: variable 'overrun' set but not used [-Wunused-but-set-variable] Also, __refill_cfs_bandwidth_runtime() does no longer update the expiration time, so fix the comments accordingly. Signed-off-by:
Qian Cai <cai@lca.pw> Signed-off-by:
Ben Segall <bsegall@google.com> Reviewed-by:
Dave Chiluk <chiluk+linux@indeed.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: pauld@redhat.com Fixes: de53fd7a ("sched/fair: Fix low cpu usage with high throttling by removing expiration of cpu-local slices") Link: https://lkml.kernel.org/r/1566326455-8038-1-git-send-email-cai@lca.pwSigned-off-by:
-
KeMeng Shi authored
An oops can be triggered in the scheduler when running qemu on arm64: Unable to handle kernel paging request at virtual address ffff000008effe40 Internal error: Oops: 96000007 [#1] SMP Process migration/0 (pid: 12, stack limit = 0x00000000084e3736) pstate: 20000085 (nzCv daIf -PAN -UAO) pc : __ll_sc___cmpxchg_case_acq_4+0x4/0x20 lr : move_queued_task.isra.21+0x124/0x298 ... Call trace: __ll_sc___cmpxchg_case_acq_4+0x4/0x20 __migrate_task+0xc8/0xe0 migration_cpu_stop+0x170/0x180 cpu_stopper_thread+0xec/0x178 smpboot_thread_fn+0x1ac/0x1e8 kthread+0x134/0x138 ret_from_fork+0x10/0x18 __set_cpus_allowed_ptr() will choose an active dest_cpu in affinity mask to migrage the process if process is not currently running on any one of the CPUs specified in affinity mask. __set_cpus_allowed_ptr() will choose an invalid dest_cpu (dest_cpu >= nr_cpu_ids, 1024 in my virtual machine) if CPUS in an affinity mask are deactived by cpu_down after cpumask_intersects check. cpumask_test_cpu() of dest_cpu afterwards is overflown and may pass if corresponding bit is coincidentally set. As a consequence, kernel will access an invalid rq address associate with the invalid CPU in migration_cpu_stop->__migrate_task->move_queued_task and the Oops occurs. The reproduce the crash: 1) A process repeatedly binds itself to cpu0 and cpu1 in turn by calling sched_setaffinity. 2) A shell script repeatedly does "echo 0 > /sys/devices/system/cpu/cpu1/online" and "echo 1 > /sys/devices/system/cpu/cpu1/online" in turn. 3) Oops appears if the invalid CPU is set in memory after tested cpumask. Signed-off-by:
KeMeng Shi <shikemeng@huawei.com> Signed-off-by:
-
Mathieu Desnoyers authored
Remove the IPI fallback code from membarrier to deal with very infrequent cpumask memory allocation failure. Use GFP_KERNEL rather than GFP_NOWAIT, and relax the blocking guarantees for the expedited membarrier system call commands, allowing it to block if waiting for memory to be made available. In addition, now -ENOMEM can be returned to user-space if the cpumask memory allocation fails. Signed-off-by:
Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by:
-
Mathieu Desnoyers authored
If there is only a single mm_user for the mm, the private expedited membarrier command can skip the IPIs, because only a single thread is using the mm. Signed-off-by:
-
Mathieu Desnoyers authored
membarrier commands cover very different code paths if they are in a single-threaded vs multi-threaded process. Therefore, exercise both scenarios in the kernel selftests to increase coverage of this selftest. Signed-off-by:
-
Mathieu Desnoyers authored
The membarrier_state field is located within the mm_struct, which is not guaranteed to exist when used from runqueue-lock-free iteration on runqueues by the membarrier system call. Copy the membarrier_state from the mm_struct into the scheduler runqueue when the scheduler switches between mm. When registering membarrier for mm, after setting the registration bit in the mm membarrier state, issue a synchronize_rcu() to ensure the scheduler observes the change. In order to take care of the case where a runqueue keeps executing the target mm without swapping to other mm, iterate over each runqueue and issue an IPI to copy the membarrier_state from the mm_struct into each runqueue which have the same mm which state has just been modified. Move the mm membarrier_state field closer to pgd in mm_struct to use a cache line already touched by the scheduler switch_mm. The membarrier_execve() (now membarrier_exec_mmap) hook now needs to clear the runqueue's membarrier state in addition to clear the mm membarrier state, so move its implementation into the scheduler membarrier code so it can access the runqueue structure. Add memory barrier in membarrier_exec_mmap() prior to clearing the membarrier state, ensuring memory accesses executed prior to exec are not reordered with the stores clearing the membarrier state. As suggested by Linus, move all membarrier.c RCU read-side locks outside of the for each cpu loops. Suggested-by:
Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by:
-
Mathieu Desnoyers authored
When the prev and next task's mm change, switch_mm() provides the core serializing guarantees before returning to usermode. The only case where an explicit core serialization is needed is when the scheduler keeps the same mm for prev and next. Suggested-by:
Oleg Nesterov <oleg@redhat.com> Signed-off-by:
-
Mathieu Desnoyers authored
Checking that the number of threads is 1 is redundant with checking mm_users == 1. No change in functionality intended. Suggested-by:
-
Mathieu Desnoyers authored
Fix a logic flaw in the way membarrier_register_private_expedited() handles ready state checks for private expedited sync core and private expedited registrations. If a private expedited membarrier registration is first performed, and then a private expedited sync_core registration is performed, the ready state check will skip the second registration when it really should not. Signed-off-by:
-
Eric W. Biederman authored
The current task on the runqueue is currently read with rcu_dereference(). To obtain ordinary RCU semantics for an rcu_dereference() of rq->curr it needs to be paired with rcu_assign_pointer() of rq->curr. Which provides the memory barrier necessary to order assignments to the task_struct and the assignment to rq->curr. Unfortunately the assignment of rq->curr in __schedule is a hot path, and it has already been show that additional barriers in that code will reduce the performance of the scheduler. So I will attempt to describe below why you can effectively have ordinary RCU semantics without any additional barriers. The assignment of rq->curr in init_idle is a slow path called once per cpu and that can use rcu_assign_pointer() without any concerns. As I write this there are effectively two users of rcu_dereference() on rq->curr. There is the membarrier code in kernel/sched/membarrier.c that only looks at "->mm" after the rcu_dereference(). Then there is task_numa_compare() in kernel/sched/fair.c. My best reading of the code shows that task_numa_compare only access: "->flags", "->cpus_ptr", "->numa_group", "->numa_faults[]", "->total_numa_faults", and "->se.cfs_rq". The code in __schedule() essentially does: rq_lock(...); smp_mb__after_spinlock(); next = pick_next_task(...); rq->curr = next; context_switch(prev, next); At the start of the function the rq_lock/smp_mb__after_spinlock pair provides a full memory barrier. Further there is a full memory barrier in context_switch(). This means that any task that has already run and modified itself (the common case) has already seen two memory barriers before __schedule() runs and begins executing. A task that modifies itself then sees a third full memory barrier pair with the rq_lock(); For a brand new task that is enqueued with wake_up_new_task() there are the memory barriers present from the taking and release the pi_lock and the rq_lock as the processes is enqueued as well as the full memory barrier at the start of __schedule() assuming __schedule() happens on the same cpu. This means that by the time we reach the assignment of rq->curr except for values on the task struct modified in pick_next_task the code has the same guarantees as if it used rcu_assign_pointer(). Reading through all of the implementations of pick_next_task it appears pick_next_task is limited to modifying the task_struct fields "->se", "->rt", "->dl". These fields are the sched_entity structures of the varies schedulers. Further "->se.cfs_rq" is only changed in cgroup attach/move operations initialized by userspace. Unless I have missed something this means that in practice that the users of "rcu_dereference(rq->curr)" get normal RCU semantics of rcu_dereference() for the fields the care about, despite the assignment of rq->curr in __schedule() ot using rcu_assign_pointer. Signed-off-by:
Eric W. Biederman <ebiederm@xmission.com> Signed-off-by:
-
Eric W. Biederman authored
Remove work arounds that were written before there was a grace period after tasks left the runqueue in finish_task_switch(). In particular now that there tasks exiting the runqueue exprience a RCU grace period none of the work performed by task_rcu_dereference() excpet the rcu_dereference() is necessary so replace task_rcu_dereference() with rcu_dereference(). Remove the code in rcuwait_wait_event() that checks to ensure the current task has not exited. It is no longer necessary as it is guaranteed that any running task will experience a RCU grace period after it leaves the run queueue. Remove the comment in rcuwait_wake_up() as it is no longer relevant. Ref: 8f95c90c ("sched/wait, RCU: Introduce rcuwait machinery") Ref: 150593bf ("sched/api: Introduce task_rcu_dereference() and try_get_task_struct()") Signed-off-by:
-
Eric W. Biederman authored
In the ordinary case today the RCU grace period for a task_struct is triggered when another process wait's for it's zombine and causes the kernel to call release_task(). As the waiting task has to receive a signal and then act upon it before this happens, typically this will occur after the original task as been removed from the runqueue. Unfortunaty in some cases such as self reaping tasks it can be shown that release_task() will be called starting the grace period for task_struct long before the task leaves the runqueue. Therefore use put_task_struct_rcu_user() in finish_task_switch() to guarantee that the there is a RCU lifetime after the task leaves the runqueue. Besides the change in the start of the RCU grace period for the task_struct this change may cause perf_event_delayed_put and trace_sched_process_free. The function perf_event_delayed_put boils down to just a WARN_ON for cases that I assume never show happen. So I don't see any problem with delaying it. The function trace_sched_process_free is a trace point and thus visible to user space. Occassionally userspace has the strangest dependencies so this has a miniscule chance of causing a regression. This change only changes the timing of when the tracepoint is called. The change in timing arguably gives userspace a more accurate picture of what is going on. So I don't expect there to be a regression. In the case where a task self reaps we are pretty much guaranteed that the RCU grace period is delayed. So we should get quite a bit of coverage in of this worst case for the change in a normal threaded workload. So I expect any issues to turn up quickly or not at all. I have lightly tested this change and everything appears to work fine. Inspired-by:
-
Eric W. Biederman authored
Add a count of the number of RCU users (currently 1) of the task struct so that we can later add the scheduler case and get rid of the very subtle task_rcu_dereference(), and just use rcu_dereference(). As suggested by Oleg have the count overlap rcu_head so that no additional space in task_struct is required. Inspired-by:
-
- 18 Sep, 2019 1 commit
-
-
Qian Cai authored
Clang reports this warning: kernel/locking/osq_lock.c:25:19: warning: unused function 'node_cpu' [-Wunused-function] due to osq_lock() calling vcpu_is_preempted(node_cpu(node->prev))), but vcpu_is_preempted() is compiled away. Fix it by converting the dummy vcpu_is_preempted() from a macro to a proper static inline function. Signed-off-by:
Mel Gorman <mgorman@suse.de> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: bsegall@google.com Cc: dietmar.eggemann@arm.com Cc: juri.lelli@redhat.com Cc: rostedt@goodmis.org Cc: vincent.guittot@linaro.org Link: https://lkml.kernel.org/r/1568730894-10483-1-git-send-email-cai@lca.pwSigned-off-by:
-
- 17 Sep, 2019 13 commits
-
-
Qian Cai authored
cfs_rq_clock_task() was first introduced and used in: f1b17280 ("sched: Maintain runnable averages across throttled periods") Over time its use has been graduately removed by the following commits: d31b1a66 ("sched/fair: Factorize PELT update") 23127296 ("sched/fair: Update scale invariance of PELT") Today, there is no single user left, so it can be safely removed. Found via the -Wunused-function build warning. Signed-off-by:
-
git://git.infradead.org/linux-platform-drivers-x86Linus Torvalds authored
Pull x86 platform-drivers updates from Andy Shevchenko: - ASUS WMI driver got a couple of updates, i.e. support of FAN is fixed for recent products and the charge threshold support has been added - Two uknown key events for Dell laptops are being ignored now to avoid spamming users with harmless messages - HP ZBook 17 G5 and ASUS Zenbook UX430UNR got accelerometer support. - Intel CherryTrail platforms had a regression with wake up. Now it's fixed - Intel PMC driver got fixed in order to work nicely in Xen environment - Intel Speed Select driver provides bucket vs core count relationship. Besides that the tools has been updated for better output - The PrivacyGuard is enabled on Lenovo ThinkPad laptops - Three tablets - Trekstor Primebook C11B 2-in-1, Irbis TW90 and Chuwi Surbook Mini - got touchscreen support * tag 'platform-drivers-x86-v5.4-1' of git://git.infradead.org/linux-platform-drivers-x86: (53 commits) MAINTAINERS: Switch PDx86 subsystem status to Odd Fixes platform/x86: asus-wmi: Refactor charge threshold to use the battery hooking API platform/x86: asus-wmi: Rename CHARGE_THRESHOLD to RSOC platform/x86: asus-wmi: Reorder ASUS_WMI_CHARGE_THRESHOLD tools/power/x86/intel-speed-select: Display core count for bucket platform/x86: ISST: Allow additional TRL MSRs tools/power/x86/intel-speed-select: Fix memory leak tools/power/x86/intel-speed-select: Output success/failed for command output tools/power/x86/intel-speed-select: Output human readable CPU list tools/power/x86/intel-speed-select: Change turbo ratio output to maximum turbo frequency tools/power/x86/intel-speed-select: Switch output to MHz tools/power/x86/intel-speed-select: Simplify output for turbo-freq and base-freq tools/power/x86/intel-speed-select: Fix cpu-count output tools/power/x86/intel-speed-select: Fix help option typo tools/power/x86/intel-speed-select: Fix package typo tools/power/x86/intel-speed-select: Fix a read overflow in isst_set_tdp_level_msr() platform/x86: intel_int0002_vgpio: Use device_init_wakeup platform/x86: intel_int0002_vgpio: Fix wakeups not working on Cherry Trail platform/x86: compal-laptop: Initialize "value" in ec_read_u8() platform/x86: touchscreen_dmi: Add info for the Trekstor Primebook C11B 2-in-1 ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 vmware updates from Ingo Molnar: "This updates the VMWARE guest driver with support for VMCALL/VMMCALL based hypercalls" * 'x86-vmware-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: input/vmmouse: Update the backdoor call with support for new instructions drm/vmwgfx: Update the backdoor call with support for new instructions x86/vmware: Add a header file for hypercall definitions x86/vmware: Update platform detection code for VMCALL/VMMCALL hypercalls
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 hyperv updates from Ingo Molnar: "Misc updates related to page size abstractions within the HyperV code, in preparation for future features" * 'x86-hyperv-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: drivers: hv: vmbus: Replace page definition with Hyper-V specific one x86/hyperv: Add functions to allocate/deallocate page for Hyper-V x86/hyperv: Create and use Hyper-V page definitions
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 platform update from Ingo Molnar: "The biggest change is the rework of the intel/iosf_mbi locking code which used a few non-standard locking patterns, to make it work under lockdep" * 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/platform/uv: Fix kmalloc() NULL check routine x86/platform/intel/iosf_mbi Rewrite locking
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 mm updates from Ingo Molnar: - Make cpumask_of_node() more robust against invalid node IDs - Simplify and speed up load_mm_cr4() - Unexport and remove various unused set_memory_*() APIs - Misc cleanups * 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mm: Fix cpumask_of_node() error condition x86/mm: Remove the unused set_memory_wt() function x86/mm: Remove set_pages_x() and set_pages_nx() x86/mm: Remove the unused set_memory_array_*() functions x86/mm: Unexport set_memory_x() and set_memory_nx() x86/fixmap: Cleanup outdated comments x86/kconfig: Remove X86_DIRECT_GBPAGES dependency on !DEBUG_PAGEALLOC x86/mm: Avoid redundant interrupt disable in load_mm_cr4()
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 entry updates from Ingo Molnar: "This contains x32 and compat syscall improvements, the biggest one of which splits x32 syscalls into their own table, which allows new syscalls to share the x32 and x86-64 number - which turns the 512-547 special syscall numbers range into a legacy wart that won't be extended going forward" * 'x86-entry-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/syscalls: Split the x32 syscalls into their own table x86/syscalls: Disallow compat entries for all types of 64-bit syscalls x86/syscalls: Use the compat versions of rt_sigsuspend() and rt_sigprocmask() x86/syscalls: Make __X32_SYSCALL_BIT be unsigned long
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 cpu-feature updates from Ingo Molnar: - Rework the Intel model names symbols/macros, which were decades of ad-hoc extensions and added random noise. It's now a coherent, easy to follow nomenclature. - Add new Intel CPU model IDs: - "Tiger Lake" desktop and mobile models - "Elkhart Lake" model ID - and the "Lightning Mountain" variant of Airmont, plus support code - Add the new AVX512_VP2INTERSECT instruction to cpufeatures - Remove Intel MPX user-visible APIs and the self-tests, because the toolchain (gcc) is not supporting it going forward. This is the first, lowest-risk phase of MPX removal. - Remove X86_FEATURE_MFENCE_RDTSC - Various smaller cleanups and fixes * 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits) x86/cpu: Update init data for new Airmont CPU model x86/cpu: Add new Airmont variant to Intel family x86/cpu: Add Elkhart Lake to Intel family x86/cpu: Add Tiger Lake to Intel family x86: Correct misc typos x86/intel: Add common OPTDIFFs x86/intel: Aggregate microserver naming x86/intel: Aggregate big core graphics naming x86/intel: Aggregate big core mobile naming x86/intel: Aggregate big core client naming x86/cpufeature: Explain the macro duplication x86/ftrace: Remove mcount() declaration x86/PCI: Remove superfluous returns from void functions x86/msr-index: Move AMD MSRs where they belong x86/cpu: Use constant definitions for CPU models lib: Remove redundant ftrace flag removal x86/crash: Remove unnecessary comparison x86/bitops: Use __builtin_constant_p() directly instead of IS_IMMEDIATE() x86: Remove X86_FEATURE_MFENCE_RDTSC x86/mpx: Remove MPX APIs ... -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 build cleanup from Ingo Molnar: "A single change that removes unnecessary asm-generic wrappers" * 'x86-build-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/build: Remove unneeded uapi asm-generic wrappers
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 boot code cleanup from Ingo Molnar: "Clean up the BUILD_BUG_ON() definition which can cause build warnings" * 'x86-boot-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/boot: Use common BUILD_BUG_ON
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 asm updates from Ingo Molnar: - Add UMIP emulation/spoofing for 64-bit processes as well, because of Wine based gaming. - Clean up symbols/labels in low level asm code - Add an assembly optimized mul_u64_u32_div() implementation on x86-64. * 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/umip: Add emulation (spoofing) for UMIP covered instructions in 64-bit processes as well x86/asm: Make some functions local labels x86/asm/suspend: Get rid of bogus_64_magic x86/math64: Provide a sane mul_u64_u32_div() implementation for x86_64
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull scheduler updates from Ingo Molnar: - MAINTAINERS: Add Mark Rutland as perf submaintainer, Juri Lelli and Vincent Guittot as scheduler submaintainers. Add Dietmar Eggemann, Steven Rostedt, Ben Segall and Mel Gorman as scheduler reviewers. As perf and the scheduler is getting bigger and more complex, document the status quo of current responsibilities and interests, and spread the review pain^H^H^H^H fun via an increase in the Cc: linecount generated by scripts/get_maintainer.pl. :-) - Add another series of patches that brings the -rt (PREEMPT_RT) tree closer to mainline: split the monolithic CONFIG_PREEMPT dependencies into a new CONFIG_PREEMPTION category that will allow the eventual introduction of CONFIG_PREEMPT_RT. Still a few more hundred patches to go though. - Extend the CPU cgroup controller with uclamp.min and uclamp.max to allow the finer shaping of CPU bandwidth usage. - Micro-optimize energy-aware wake-ups from O(CPUS^2) to O(CPUS). - Improve the behavior of high CPU count, high thread count applications running under cpu.cfs_quota_us constraints. - Improve balancing with SCHED_IDLE (SCHED_BATCH) tasks present. - Improve CPU isolation housekeeping CPU allocation NUMA locality. - Fix deadline scheduler bandwidth calculations and logic when cpusets rebuilds the topology, or when it gets deadline-throttled while it's being offlined. - Convert the cpuset_mutex to percpu_rwsem, to allow it to be used from setscheduler() system calls without creating global serialization. Add new synchronization between cpuset topology-changing events and the deadline acceptance tests in setscheduler(), which were broken before. - Rework the active_mm state machine to be less confusing and more optimal. - Rework (simplify) the pick_next_task() slowpath. - Improve load-balancing on AMD EPYC systems. - ... and misc cleanups, smaller fixes and improvements - please see the Git log for more details. * 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (53 commits) sched/psi: Correct overly pessimistic size calculation sched/fair: Speed-up energy-aware wake-ups sched/uclamp: Always use 'enum uclamp_id' for clamp_id values sched/uclamp: Update CPU's refcount on TG's clamp changes sched/uclamp: Use TG's clamps to restrict TASK's clamps sched/uclamp: Propagate system defaults to the root group sched/uclamp: Propagate parent clamps sched/uclamp: Extend CPU's cgroup controller sched/topology: Improve load balancing on AMD EPYC systems arch, ia64: Make NUMA select SMP sched, perf: MAINTAINERS update, add submaintainers and reviewers sched/fair: Use rq_lock/unlock in online_fair_sched_group cpufreq: schedutil: fix equation in comment sched: Rework pick_next_task() slow-path sched: Allow put_prev_task() to drop rq->lock sched/fair: Expose newidle_balance() sched: Add task_struct pointer to sched_class::set_curr_task sched: Rework CPU hotplug task selection sched/{rt,deadline}: Fix set_next_task vs pick_next_task sched: Fix kerneldoc comment for ia64_set_curr_task ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull perf updates from Ingo Molnar: "Kernel side changes: - Improved kbprobes robustness - Intel PEBS support for PT hardware tracing - Other Intel PT improvements: high order pages memory footprint reduction and various related cleanups - Misc cleanups The perf tooling side has been very busy in this cycle, with over 300 commits. This is an incomplete high-level summary of the many improvements done by over 30 developers: - Lots of updates to the following tools: 'perf c2c' 'perf config' 'perf record' 'perf report' 'perf script' 'perf test' 'perf top' 'perf trace' - Updates to libperf and libtraceevent, and a consolidation of the proliferation of x86 instruction decoder libraries. - Vendor event updates for Intel and PowerPC CPUs, - Updates to hardware tracing tooling for ARM and Intel CPUs, - ... and lots of other changes and cleanups - see the shortlog and Git log for details" * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (322 commits) kprobes: Prohibit probing on BUG() and WARN() address perf/x86: Make more stuff static x86, perf: Fix the dependency of the x86 insn decoder selftest objtool: Ignore intentional differences for the x86 insn decoder objtool: Update sync-check.sh from perf's check-headers.sh perf build: Ignore intentional differences for the x86 insn decoder perf intel-pt: Use shared x86 insn decoder perf intel-pt: Remove inat.c from build dependency list perf: Update .gitignore file objtool: Move x86 insn decoder to a common location perf metricgroup: Support multiple events for metricgroup perf metricgroup: Scale the metric result perf pmu: Change convert_scale from static to global perf symbols: Move mem_info and branch_info out of symbol.h perf auxtrace: Uninline functions that touch perf_session perf tools: Remove needless evlist.h include directives perf tools: Remove needless evlist.h include directives perf tools: Remove needless thread_map.h include directives perf tools: Remove needless thread.h include directives perf tools: Remove needless map.h include directives ...
-
- 16 Sep, 2019 10 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull locking updates from Ingo Molnar: - improve rwsem scalability - add uninitialized rwsem debugging check - reduce lockdep's stacktrace memory usage and add diagnostics - misc cleanups, code consolidation and constification * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: mutex: Fix up mutex_waiter usage locking/mutex: Use mutex flags macro instead of hard code locking/mutex: Make __mutex_owner static to mutex.c locking/qspinlock,x86: Clarify virt_spin_lock_key locking/rwsem: Check for operations on an uninitialized rwsem locking/rwsem: Make handoff writer optimistically spin on owner locking/lockdep: Report more stack trace statistics locking/lockdep: Reduce space occupied by stack traces stacktrace: Constify 'entries' arguments locking/lockdep: Make it clear that what lock_class::key points at is not modified
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull EFI updates from Ingo Molnar: - refactor the EFI config table handling across architectures - add support for the Dell EMC OEM config table - include AER diagnostic output to CPER handling of fatal PCIe errors * 'efi-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: efi: cper: print AER info of PCIe fatal error efi: Export Runtime Configuration Interface table to sysfs efi: ia64: move SAL systab handling out of generic EFI code efi/x86: move UV_SYSTAB handling into arch/x86 efi: x86: move efi_is_table_address() into arch/x86
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull stacktrace fixlet from Ingo Molnar: "Two comment fixes" * 'core-stacktrace-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: lib/stackdepot: Fix outdated comments
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull RCU updates from Ingo Molnar: "This cycle's RCU changes were: - A few more RCU flavor consolidation cleanups. - Updates to RCU's list-traversal macros improving lockdep usability. - Forward-progress improvements for no-CBs CPUs: Avoid ignoring incoming callbacks during grace-period waits. - Forward-progress improvements for no-CBs CPUs: Use ->cblist structure to take advantage of others' grace periods. - Also added a small commit that avoids needlessly inflicting scheduler-clock ticks on callback-offloaded CPUs. - Forward-progress improvements for no-CBs CPUs: Reduce contention on ->nocb_lock guarding ->cblist. - Forward-progress improvements for no-CBs CPUs: Add ->nocb_bypass list to further reduce contention on ->nocb_lock guarding ->cblist. - Miscellaneous fixes. - Torture-test updates. - minor LKMM updates" * 'core-rcu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (86 commits) MAINTAINERS: Update from paulmck@linux.ibm.com to paulmck@kernel.org rcu: Don't include <linux/ktime.h> in rcutiny.h rcu: Allow rcu_do_batch() to dynamically adjust batch sizes rcu/nocb: Don't wake no-CBs GP kthread if timer posted under overload rcu/nocb: Reduce __call_rcu_nocb_wake() leaf rcu_node ->lock contention rcu/nocb: Reduce nocb_cb_wait() leaf rcu_node ->lock contention rcu/nocb: Advance CBs after merge in rcutree_migrate_callbacks() rcu/nocb: Avoid synchronous wakeup in __call_rcu_nocb_wake() rcu/nocb: Print no-CBs diagnostics when rcutorture writer unduly delayed rcu/nocb: EXP Check use and usefulness of ->nocb_lock_contended rcu/nocb: Add bypass callback queueing rcu/nocb: Atomic ->len field in rcu_segcblist structure rcu/nocb: Unconditionally advance and wake for excessive CBs rcu/nocb: Reduce ->nocb_lock contention with separate ->nocb_gp_lock rcu/nocb: Reduce contention at no-CBs invocation-done time rcu/nocb: Reduce contention at no-CBs registry-time CB advancement rcu/nocb: Round down for number of no-CBs grace-period kthreads rcu/nocb: Avoid ->nocb_lock capture by corresponding CPU rcu/nocb: Avoid needless wakeups of no-CBs grace-period kthread rcu/nocb: Make __call_rcu_nocb_wake() safe for many callbacks ... -
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull objtool build fix from Ingo Molnar: "Fix objtool builds with more exotic, user-defined CFLAGS" * 'core-objtool-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: objtool: Clobber user CFLAGS variable
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull header documentation fix from Ingo Molnar: "Fix the parameter description <asm-generic/div64.h>" * 'core-headers-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: asm-generic/div64: Fix documentation of do_div() parameter
-
git://git.kernel.org/pub/scm/linux/kernel/git/soc/socLinus Torvalds authored
Pull ARM DT updates from Arnd Bergmann: "This is another huge branch with close to 450 changessets related to devicetree files, roughly half of this for 32-bit and 64-bit respectively. There are lots of cleanups and additional hardware support for platforms we already support based on SoCs from Renesas, ST-Microelectronics, Intel/Altera, Rockchips, Allwinner, Broadcom and other manufacturers. A total of 6 new SoCs and 37 new boards gets added this time, one more SoC will come in a follow-up branch. Most of the new boards are for 64-bit ARM SoCs, the others are typically for the 32-bit Cortex-A7. Going more into details for SoC platforms with new hardware support: - The Snapdragon 855 (SM8150) is Qualcomm's current high-end phone platform, usually paired with an external 5G modem. So far we only support the Qualcomm SM8150 MTP reference platform, but no actual products. - For the slightly older Qualcomm platforms, support for several interesting products is getting added: Three laptops based on Snapdragon 835/MSM8998 (Asus NovaGo, HP Envy X2 and Lenovo Miix 630), one laptop based on Snapdragon 850/sdm850 (Lenovo Yoga C630) and several phones based on the older Snapdragon 410/MSM8916 (Samsung A3 and A5, Longcheer L8150 aka Android One 2nd gen "seed" aka Wileyfox Swift). - Mediatek MT7629 is a new wireless network router chip, similar to the older MT7623. It gets added together with the reference board implementation. - Allwinner V3 is a repackaged version of the existing low-end V3s chip, and is used in the tiny Lichee Pi Zero plus, also added here. There is also a new TV set-top box based on Allwinner H6, the Tanix TX6, and the eMMC variant of the Olimex A64-Olinuxino development board. - NXP i.MX8M Nano is a new member of the ever-expanding i.MX SoC family, similar to the i.MX8M Mini. As usual, there is a large number of new boards for i.MX SoCs: Einfochips i.MX8QXP AI_ML, SolidRun Hummingboard Pulse baseboard and System-on-Module, Boundary Devices i.MX8MQ Nitrogen8M, and TechNexion PICO-PI-IMX8M-DEV for the 64-bit i.MX8 line. For 32-bit, we get the Kontron i.MX6UL N6310 SoM with two baseboards, the PHYTEC phyBOARD-Segin SoM with three baseboards, and the Zodiac Inflight Innovations i.MX7 RMU2 board. - In a different NXP product line, the Layerscape LS1046A "Freeway" reference board gets added. - Amlogic SM1 (S905X3) and G12B (S922X, A311D) are updated chips from their set-top-box line and smart speaker with newer CPU and GPU cores compared to their predecessors. Both are now also supported by the Khadas VIM3 development board series, and the dts files for that get reorganized a bit to better deal with all variants. Another board based on SM1 that gets added is the SEI Robotics SEI610. - There are a handful of new x86 and Power9 server boards using Aspeed BMC chips that are gaining support for running Linux on the BMC through the OpenBMC project: Facebook Minipack/Wedge100/Wedge40, Lenovo Hr855xg2, and Mihawk. Notably these are still new machines using SoCs based on the ARM9 and ARM11 CPU cores, as support for the new Cortex-A7 based AST2600 is still ramping up. - There are three new end-user products using 32-bit Rockchips SoCs: Mecer Xtreme Mini S6 is an Android "mini PC" box based on the low-end RK3229 chip, while the two AOpen products Chromebox Mini (Fievel) and Chromebase Mini (Tiger) run ChromeOS and are meant for commercial settings(digital signage, PoS, ...). - One more single-board computer based on the popular 64-bit RK3399 is added: the Leez RK3399 P710" * tag 'armsoc-dt' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (467 commits) arm64: dts: qcom: Add Lenovo Yoga C630 ARM: dts: aspeed-g5: Fixe gpio-ranges upper limit ARM; dts: aspeed: mihawk: File should not be executable ARM: dts: aspeed: swift: Change power supplies to version 2 ARM: dts: aspeed: vesnin: Add secondary SPI flash chip ARM: dts: aspeed: vesnin: Add wdt2 with alt-boot option ARM: dts: aspeed-g4: Add all flash chips ARM: dts: exynos: Enable GPU/Mali T604 on Arndale board ARM: dts: exynos: Enable GPU/Mali T604 on Chromebook Snow ARM: dts: exynos: Add GPU/Mali T604 node to Exynos5250 ARM: dts: exynos: Fix min/max buck4 for GPU on Arndale board ARM: dts: exynos: Mark LDO10 as always-on on Peach Pit/Pi Chromebooks ARM: dts: exynos: Remove not accurate secondary ADC compatible arm64: dts: rockchip: limit clock rate of MMC controllers for RK3328 arm64: dts: meson-sm1-sei610: add stdout-path property back arm64: dts: meson-sm1-sei610: enable DVFS arm64: dts: khadas-vim3: add support for the SM1 based VIM3L dt-bindings: arm: amlogic: add Amlogic SM1 based Khadas VIM3L bindings arm64: dts: khadas-vim3: move common nodes into meson-khadas-vim3.dtsi arm64: dts: meson: g12a: add reset to tdm formatters ... -
git://git.kernel.org/pub/scm/linux/kernel/git/soc/socLinus Torvalds authored
Pull ARM SoC defconfig updates from Arnd Bergmann: "As usual, a bunch of commits, mostly adding drivers and other options to defconfigs after the code was merged through another tree" * tag 'armsoc-defconfig' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (32 commits) arm64: defconfig: Enable Qualcomm QUSB2 PHY arm64: defconfig: Enable the EFI Framebuffer arm64: defconfig: Enable Qualcomm GENI based I2C controller ARM: multi_v7_defconfig: Make MAX77802 regulator driver built-in arm64: defconfig: Enable CPU clock drivers for Qualcomm msm8916 arm64: defconfig: Add DRM_MSM to defconfigs with ARCH_QCOM ARM: multi_v7_defconfig: Add DRM_MSM to defconfigs with ARCH_QCOM ARM: qcom_defconfig: Add DRM_MSM to defconfigs with ARCH_QCOM ARM: configs: aspeed_g5: Enable AST2600 ARM: configs: multi_v7: Add ASPEED G6 arm64: defconfig: Enable SM8150 GCC and pinctrl driver arm64: defconfig: Enable CONFIG_ACPI_APEI_PCIEAER arm64: defconfig: Enable the DesignWare watchdog ARM: multi_v7_defconfig: Enable SPI_STM32_QSPI support ARM: imx_v6_v7_defconfig: Enable the PSCI CPUidle driver arm64: defconfig: Enable the PSCI CPUidle driver arm64: defconfig: Enable Sun4i SPDIF module ARM: exynos_defconfig: Enable AHCI-platform SATA driver arm64: defconfig: CONFIG_DRM_ETNAVIV=m ARM: imx_v6_v7_defconfig: Select the OV5645 camera driver ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/soc/socLinus Torvalds authored
Pull ARM SoC driver updates from Arnd Bergmann: "This contains driver changes that are tightly connected to SoC specific code. Aside from smaller cleanups and bug fixes, here is a list of the notable changes. New device drivers: - The Turris Mox router has a new "moxtet" bus driver for its on-board pluggable extension bus. The same platform also gains a firmware driver. - The Samsung Exynos family gains a new Chipid driver exporting using the soc device sysfs interface - A similar socinfo driver for Qualcomm Snapdragon chips. - A firmware driver for the NXP i.MX DSP IPC protocol using shared memory and a mailbox Other changes: - The i.MX reset controller driver now supports the NXP i.MX8MM chip - Amlogic SoC specific drivers gain support for the S905X3 and A311D chips - A rework of the TI Davinci framebuffer driver to allow important cleanups in the platform code - A couple of device drivers for removed ARM SoC platforms are removed. Most of the removals were picked up by other maintainers, this contains whatever was left" * tag 'armsoc-drivers' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (123 commits) bus: uniphier-system-bus: use devm_platform_ioremap_resource() soc: ti: ti_sci_pm_domains: Add support for exclusive and shared access dt-bindings: ti_sci_pm_domains: Add support for exclusive and shared access firmware: ti_sci: Allow for device shared and exclusive requests bus: imx-weim: remove incorrect __init annotations fbdev: remove w90x900/nuc900 platform drivers spi: remove w90x900 driver net: remove w90p910-ether driver net: remove ks8695 driver firmware: turris-mox-rwtm: Add sysfs documentation firmware: Add Turris Mox rWTM firmware driver dt-bindings: firmware: Document cznic,turris-mox-rwtm binding bus: moxtet: fix unsigned comparison to less than zero bus: moxtet: remove set but not used variable 'dummy' ARM: scoop: Use the right include dt-bindings: power: add Amlogic Everything-Else power domains bindings soc: amlogic: Add support for Everything-Else power domains controller fbdev: da8xx: use resource management for dma fbdev: da8xx-fb: drop a redundant if fbdev: da8xx-fb: use devm_platform_ioremap_resource() ... -
git://git.kernel.org/pub/scm/linux/kernel/git/soc/socLinus Torvalds authored
Pull ARM SoC platform updates from Arnd Bergmann: "The main change this time around is a cleanup of some of the oldest platforms based on the XScale and ARM9 CPU cores, which are between 10 and 20 years old. The Kendin/Micrel/Microchip KS8695, Winbond/Nuvoton W90x900 and Intel IOP33x/IOP13xx platforms are removed after we determined that nobody is using them any more. The TI Davinci and NXP LPC32xx platforms on the other hand are still in active use and are converted to the ARCH_MULTIPLATFORM build, meaning that we can compile a kernel that works on these along with most other ARMv5 platforms. Changes toward that goal are also merged for IOP32x, but additional work is needed to complete this. Patches for the remaining ARMv5 platforms have started but need more work and some testing. Support for the new ASpeed AST2600 gets added, this is based on the Cortex-A7 ARMv7 core, and is a newer version of the existing ARMv5 and ARMv6 chips in the same family. Other changes include a cleanup of the ST-Ericsson ux500 platform and the move of the TI Davinci platform to a new clocksource driver" [ The changes had marked INTEL_IOP_ADMA and USB_LPC32XX as being buildable on other platforms through COMPILE_TEST, but that causes new warnings that I most definitely do not want to see during the merge window as that could hide other issues. So the COMPILE_TEST option got disabled for them again - Linus ] * tag 'armsoc-soc' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: (61 commits) ARM: multi_v5_defconfig: make DaVinci part of the ARM v5 multiplatform build ARM: davinci: support multiplatform build for ARM v5 arm64: exynos: Enable exynos-chipid driver ARM: OMAP2+: Delete an unnecessary kfree() call in omap_hsmmc_pdata_init() ARM: OMAP2+: move platform-specific asm-offset.h to arch/arm/mach-omap2 ARM: davinci: dm646x: Fix a typo in the comment ARM: davinci: dm646x: switch to using the clocksource driver ARM: davinci: dm644x: switch to using the clocksource driver ARM: aspeed: Enable SMP boot ARM: aspeed: Add ASPEED AST2600 architecture ARM: aspeed: Select timer in each SoC dt-bindings: arm: cpus: Add ASPEED SMP ARM: imx: stop adjusting ar8031 phy tx delay mailmap: map old company name to new one @microchip.com MAINTAINERS: at91: remove the TC entry MAINTAINERS: at91: Collect all pinctrl/gpio drivers in same entry ARM: at91: move platform-specific asm-offset.h to arch/arm/mach-at91 MAINTAINERS: Extend patterns for Samsung SoC, Security Subsystem and clock drivers ARM: s3c64xx: squash samsung_usb_phy.h into setup-usb-phy.c ARM: debug-ll: Add support for r7s9210 ...
-
