mirror of
https://github.com/Fishwaldo/Star64_linux.git
synced 2025-05-29 18:48:01 +00:00
e192832869
Pull locking updates from Ingo Molnar: "The main changes in this cycle are: - rwsem scalability improvements, phase #2, by Waiman Long, which are rather impressive: "On a 2-socket 40-core 80-thread Skylake system with 40 reader and writer locking threads, the min/mean/max locking operations done in a 5-second testing window before the patchset were: 40 readers, Iterations Min/Mean/Max = 1,807/1,808/1,810 40 writers, Iterations Min/Mean/Max = 1,807/50,344/151,255 After the patchset, they became: 40 readers, Iterations Min/Mean/Max = 30,057/31,359/32,741 40 writers, Iterations Min/Mean/Max = 94,466/95,845/97,098" There's a lot of changes to the locking implementation that makes it similar to qrwlock, including owner handoff for more fair locking. Another microbenchmark shows how across the spectrum the improvements are: "With a locking microbenchmark running on 5.1 based kernel, the total locking rates (in kops/s) on a 2-socket Skylake system with equal numbers of readers and writers (mixed) before and after this patchset were: # of Threads Before Patch After Patch ------------ ------------ ----------- 2 2,618 4,193 4 1,202 3,726 8 802 3,622 16 729 3,359 32 319 2,826 64 102 2,744" The changes are extensive and the patch-set has been through several iterations addressing various locking workloads. There might be more regressions, but unless they are pathological I believe we want to use this new implementation as the baseline going forward. - jump-label optimizations by Daniel Bristot de Oliveira: the primary motivation was to remove IPI disturbance of isolated RT-workload CPUs, which resulted in the implementation of batched jump-label updates. Beyond the improvement of the real-time characteristics kernel, in one test this patchset improved static key update overhead from 57 msecs to just 1.4 msecs - which is a nice speedup as well. - atomic64_t cross-arch type cleanups by Mark Rutland: over the last ~10 years of atomic64_t existence the various types used by the APIs only had to be self-consistent within each architecture - which means they became wildly inconsistent across architectures. Mark puts and end to this by reworking all the atomic64 implementations to use 's64' as the base type for atomic64_t, and to ensure that this type is consistently used for parameters and return values in the API, avoiding further problems in this area. - A large set of small improvements to lockdep by Yuyang Du: type cleanups, output cleanups, function return type and othr cleanups all around the place. - A set of percpu ops cleanups and fixes by Peter Zijlstra. - Misc other changes - please see the Git log for more details" * 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits) locking/lockdep: increase size of counters for lockdep statistics locking/atomics: Use sed(1) instead of non-standard head(1) option locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING x86/jump_label: Make tp_vec_nr static x86/percpu: Optimize raw_cpu_xchg() x86/percpu, sched/fair: Avoid local_clock() x86/percpu, x86/irq: Relax {set,get}_irq_regs() x86/percpu: Relax smp_processor_id() x86/percpu: Differentiate this_cpu_{}() and __this_cpu_{}() locking/rwsem: Guard against making count negative locking/rwsem: Adaptive disabling of reader optimistic spinning locking/rwsem: Enable time-based spinning on reader-owned rwsem locking/rwsem: Make rwsem->owner an atomic_long_t locking/rwsem: Enable readers spinning on writer locking/rwsem: Clarify usage of owner's nonspinaable bit locking/rwsem: Wake up almost all readers in wait queue locking/rwsem: More optimal RT task handling of null owner locking/rwsem: Always release wait_lock before waking up tasks locking/rwsem: Implement lock handoff to prevent lock starvation locking/rwsem: Make rwsem_spin_on_owner() return owner state ... |
||
|---|---|---|
| .. | ||
| native | ||
| sn | ||
| uv | ||
| acenv.h | ||
| acpi-ext.h | ||
| acpi.h | ||
| agp.h | ||
| asm-offsets.h | ||
| asm-prototypes.h | ||
| asmmacro.h | ||
| atomic.h | ||
| barrier.h | ||
| bitops.h | ||
| bug.h | ||
| bugs.h | ||
| cache.h | ||
| cacheflush.h | ||
| checksum.h | ||
| clocksource.h | ||
| cpu.h | ||
| cputime.h | ||
| current.h | ||
| cyclone.h | ||
| delay.h | ||
| device.h | ||
| div64.h | ||
| dma-mapping.h | ||
| dma.h | ||
| dmi.h | ||
| early_ioremap.h | ||
| elf.h | ||
| emergency-restart.h | ||
| esi.h | ||
| exception.h | ||
| export.h | ||
| extable.h | ||
| fb.h | ||
| fpswa.h | ||
| ftrace.h | ||
| futex.h | ||
| gcc_intrin.h | ||
| hardirq.h | ||
| hpsim.h | ||
| hugetlb.h | ||
| hw_irq.h | ||
| idle.h | ||
| intrinsics.h | ||
| io.h | ||
| iommu.h | ||
| iommu_table.h | ||
| iosapic.h | ||
| irq.h | ||
| irq_regs.h | ||
| irq_remapping.h | ||
| irqflags.h | ||
| Kbuild | ||
| kdebug.h | ||
| kexec.h | ||
| kmap_types.h | ||
| kprobes.h | ||
| kregs.h | ||
| libata-portmap.h | ||
| linkage.h | ||
| local.h | ||
| local64.h | ||
| machvec.h | ||
| machvec_dig.h | ||
| machvec_dig_vtd.h | ||
| machvec_hpsim.h | ||
| machvec_hpzx1.h | ||
| machvec_hpzx1_swiotlb.h | ||
| machvec_init.h | ||
| machvec_sn2.h | ||
| machvec_uv.h | ||
| mca.h | ||
| mca_asm.h | ||
| meminit.h | ||
| mman.h | ||
| mmiowb.h | ||
| mmu.h | ||
| mmu_context.h | ||
| mmzone.h | ||
| module.h | ||
| msidef.h | ||
| nodedata.h | ||
| numa.h | ||
| page.h | ||
| pal.h | ||
| param.h | ||
| parport.h | ||
| patch.h | ||
| pci.h | ||
| percpu.h | ||
| perfmon.h | ||
| pgalloc.h | ||
| pgtable.h | ||
| processor.h | ||
| ptrace.h | ||
| sal.h | ||
| sections.h | ||
| serial.h | ||
| shmparam.h | ||
| signal.h | ||
| smp.h | ||
| sparsemem.h | ||
| spinlock.h | ||
| spinlock_types.h | ||
| string.h | ||
| switch_to.h | ||
| syscall.h | ||
| termios.h | ||
| thread_info.h | ||
| timex.h | ||
| tlb.h | ||
| tlbflush.h | ||
| topology.h | ||
| types.h | ||
| uaccess.h | ||
| unaligned.h | ||
| uncached.h | ||
| unistd.h | ||
| unwind.h | ||
| user.h | ||
| ustack.h | ||
| vga.h | ||
| xor.h | ||