Hello, for this change, we reported "[paulmckrcu:dev.2025.12.16a] [rcu] 1ac50ec628: stress-ng.memfd.ops_per_sec 3.4% improvement" in https://lore.kernel.org/all/[email protected]/ now we notice this commit is in linux-next/master. we still catpure similar improvement as below. at the same time, we notice a regression in another stress-ng test. we don't have enough capability to analyze if this change really has performance impact or just the code footprint change and the corresponding cache line change impact these stress-ng tests. since data is stable, we just report out FYI. please educate us if this report is less meaningful. thanks kernel test robot noticed a 7.1% regression of stress-ng.fd-abuse.ops_per_sec on: commit: c27cea4416a396a1c5b6b3529dd925f92a69e7d3 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast") https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master [still regression on linux-next/master f417b7ffcbef7d76b0d8860518f50dae0e7e5eda] testcase: stress-ng config: x86_64-rhel-9.4 compiler: gcc-14 test machine: 256 threads 2 sockets Intel(R) Xeon(R) 6768P CPU @ 2.4GHz (Granite Rapids) with 64G memory parameters: nr_threads: 100% testtime: 60s test: fd-abuse cpufreq_governor: performance In addition to that, the commit also has significant impact on the following tests: +------------------+---------------------------------------------------------------------------------------------+ | testcase: change | stress-ng: stress-ng.memfd.ops_per_sec 3.5% improvement | | test machine | 192 threads 2 sockets Intel(R) Xeon(R) 6740E CPU @ 2.4GHz (Sierra Forest) with 256G memory | | test parameters | cpufreq_governor=performance | | | nr_threads=100% | | | test=memfd | | | testtime=60s | +------------------+---------------------------------------------------------------------------------------------+ If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <[email protected]> | Closes: https://lore.kernel.org/oe-lkp/[email protected] Details are as below: --------------------------------------------------------------------------------------------------> The kernel config and materials to reproduce are available at: https://download.01.org/0day-ci/archive/20260112/[email protected] ========================================================================================= compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime: gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-gnr-2sp4/fd-abuse/stress-ng/60s commit: v6.19-rc1 c27cea4416 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast") v6.19-rc1 c27cea4416a396a1c5b6b3529dd ---------------- --------------------------- %stddev %change %stddev \ | \ 35053 ± 14% +133.6% 81881 ±126% numa-meminfo.node0.Shmem 8763 ± 14% +133.8% 20487 ±126% numa-vmstat.node0.nr_shmem 2.404e+09 -7.1% 2.234e+09 stress-ng.fd-abuse.ops 40118365 -7.1% 37281947 stress-ng.fd-abuse.ops_per_sec 147.78 -6.9% 137.58 stress-ng.time.user_time 94705 ± 2% -4.7% 90252 proc-vmstat.nr_slab_reclaimable 565933 -3.3% 547436 proc-vmstat.nr_slab_unreclaimable 6030483 ± 2% -6.0% 5669811 proc-vmstat.numa_hit 5766412 ± 2% -6.3% 5405494 proc-vmstat.numa_local 8618500 ± 2% -7.1% 8009296 proc-vmstat.pgalloc_normal 6877608 ± 4% -8.6% 6283782 ± 2% proc-vmstat.pgfree 0.28 -7.8% 0.26 perf-stat.i.MPKI 2.52e+10 -2.2% 2.464e+10 perf-stat.i.branch-instructions 27782554 -10.8% 24789456 perf-stat.i.cache-misses 1.509e+08 ± 5% -7.8% 1.391e+08 perf-stat.i.cache-references 8.10 +2.7% 8.31 perf-stat.i.cpi 34826 +13.6% 39567 perf-stat.i.cycles-between-cache-misses 1.099e+11 -2.6% 1.071e+11 perf-stat.i.instructions 0.13 -2.5% 0.12 perf-stat.i.ipc 0.25 -8.6% 0.23 perf-stat.overall.MPKI 8.18 +2.7% 8.39 perf-stat.overall.cpi 32484 +12.3% 36472 perf-stat.overall.cycles-between-cache-misses 0.12 -2.6% 0.12 perf-stat.overall.ipc 2.48e+10 -2.2% 2.425e+10 perf-stat.ps.branch-instructions 27233991 -10.9% 24262443 perf-stat.ps.cache-misses 1.479e+08 ± 5% -7.8% 1.363e+08 perf-stat.ps.cache-references 1.082e+11 -2.6% 1.054e+11 perf-stat.ps.instructions 6.605e+12 -2.5% 6.443e+12 perf-stat.total.instructions 1.75 -0.1 1.63 perf-profile.calltrace.cycles-pp.stress_fd_lseek 0.56 ± 2% -0.1 0.45 ± 37% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.stress_fd_lseek 0.58 ± 2% -0.0 0.54 ± 2% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.stress_fd_lseek 2.20 +0.0 2.21 perf-profile.calltrace.cycles-pp.inode_sb_list_add.new_inode.__shmem_get_inode.__shmem_file_setup.shmem_zero_setup_desc 49.74 +0.1 49.83 perf-profile.calltrace.cycles-pp.__mmap 49.71 +0.1 49.80 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__mmap 49.70 +0.1 49.80 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 47.24 +0.1 47.34 perf-profile.calltrace.cycles-pp.do_mmap.vm_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 47.24 +0.1 47.35 perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 47.19 +0.1 47.30 perf-profile.calltrace.cycles-pp.__mmap_region.do_mmap.vm_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe 47.09 +0.1 47.21 perf-profile.calltrace.cycles-pp.__mmap_new_vma.__mmap_region.do_mmap.vm_mmap_pgoff.do_syscall_64 46.81 +0.1 46.93 perf-profile.calltrace.cycles-pp.new_inode.__shmem_get_inode.__shmem_file_setup.shmem_zero_setup.__mmap_new_vma 47.01 +0.1 47.13 perf-profile.calltrace.cycles-pp.shmem_zero_setup.__mmap_new_vma.__mmap_region.do_mmap.vm_mmap_pgoff 47.01 +0.1 47.13 perf-profile.calltrace.cycles-pp.__shmem_file_setup.shmem_zero_setup.__mmap_new_vma.__mmap_region.do_mmap 46.89 +0.1 47.01 perf-profile.calltrace.cycles-pp.__shmem_get_inode.__shmem_file_setup.shmem_zero_setup.__mmap_new_vma.__mmap_region 48.80 +0.1 48.93 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.inode_sb_list_add.new_inode.__shmem_get_inode 47.17 +0.1 47.30 perf-profile.calltrace.cycles-pp.__munmap 47.16 +0.1 47.28 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__munmap 47.16 +0.1 47.28 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__munmap 46.74 +0.1 46.87 perf-profile.calltrace.cycles-pp.inode_sb_list_add.new_inode.__shmem_get_inode.__shmem_file_setup.shmem_zero_setup 47.00 +0.1 47.14 perf-profile.calltrace.cycles-pp.__fput.task_work_run.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 46.98 +0.1 47.12 perf-profile.calltrace.cycles-pp.__dentry_kill.finish_dput.__fput.task_work_run.exit_to_user_mode_loop 48.89 +0.1 49.03 perf-profile.calltrace.cycles-pp._raw_spin_lock.inode_sb_list_add.new_inode.__shmem_get_inode.__shmem_file_setup 47.01 +0.1 47.15 perf-profile.calltrace.cycles-pp.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.__munmap 46.62 +0.1 46.76 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.evict.__dentry_kill.finish_dput 46.98 +0.1 47.13 perf-profile.calltrace.cycles-pp.finish_dput.__fput.task_work_run.exit_to_user_mode_loop.do_syscall_64 47.01 +0.1 47.15 perf-profile.calltrace.cycles-pp.task_work_run.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.__munmap 46.77 +0.1 46.92 perf-profile.calltrace.cycles-pp._raw_spin_lock.evict.__dentry_kill.finish_dput.__fput 46.88 +0.1 47.02 perf-profile.calltrace.cycles-pp.evict.__dentry_kill.finish_dput.__fput.task_work_run 1.76 -0.1 1.63 perf-profile.children.cycles-pp.stress_fd_lseek 0.44 -0.0 0.41 perf-profile.children.cycles-pp.entry_SYSCALL_64 0.47 -0.0 0.44 perf-profile.children.cycles-pp.llseek 0.24 -0.0 0.22 ± 2% perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack 0.11 ± 4% -0.0 0.09 ± 5% perf-profile.children.cycles-pp.__inet_listen_sk 0.20 -0.0 0.19 perf-profile.children.cycles-pp.__vm_munmap 0.20 -0.0 0.19 perf-profile.children.cycles-pp.__x64_sys_munmap 0.11 -0.0 0.10 ± 3% perf-profile.children.cycles-pp.__sys_listen 0.11 -0.0 0.10 ± 3% perf-profile.children.cycles-pp.__x64_sys_listen 0.20 -0.0 0.19 perf-profile.children.cycles-pp.arch_exit_to_user_mode_prepare 0.10 -0.0 0.09 perf-profile.children.cycles-pp.inet_csk_get_port 0.09 -0.0 0.08 perf-profile.children.cycles-pp.__get_unmapped_area 0.09 -0.0 0.08 perf-profile.children.cycles-pp.__x64_sys_pselect6 0.08 -0.0 0.07 perf-profile.children.cycles-pp.alloc_inode 0.12 -0.0 0.11 perf-profile.children.cycles-pp.kmem_cache_alloc_noprof 0.11 -0.0 0.10 perf-profile.children.cycles-pp.rcu_core 0.08 -0.0 0.07 perf-profile.children.cycles-pp.run_ksoftirqd 0.08 -0.0 0.07 perf-profile.children.cycles-pp.smpboot_thread_fn 98.70 +0.1 98.79 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 49.76 +0.1 49.85 perf-profile.children.cycles-pp.__mmap 98.63 +0.1 98.73 perf-profile.children.cycles-pp.do_syscall_64 49.68 +0.1 49.78 perf-profile.children.cycles-pp.vm_mmap_pgoff 49.66 +0.1 49.76 perf-profile.children.cycles-pp.do_mmap 49.55 +0.1 49.66 perf-profile.children.cycles-pp.__mmap_region 47.17 +0.1 47.28 perf-profile.children.cycles-pp.__mmap_new_vma 47.01 +0.1 47.13 perf-profile.children.cycles-pp.shmem_zero_setup 47.25 +0.1 47.37 perf-profile.children.cycles-pp.__munmap 49.22 +0.1 49.35 perf-profile.children.cycles-pp.__shmem_file_setup 47.07 +0.1 47.20 perf-profile.children.cycles-pp.__fput 49.10 +0.1 49.23 perf-profile.children.cycles-pp.__shmem_get_inode 49.02 +0.1 49.15 perf-profile.children.cycles-pp.new_inode 48.94 +0.1 49.08 perf-profile.children.cycles-pp.inode_sb_list_add 47.03 +0.1 47.17 perf-profile.children.cycles-pp.exit_to_user_mode_loop 46.98 +0.1 47.13 perf-profile.children.cycles-pp.__dentry_kill 46.98 +0.1 47.13 perf-profile.children.cycles-pp.finish_dput 47.01 +0.1 47.15 perf-profile.children.cycles-pp.task_work_run 46.88 +0.1 47.02 perf-profile.children.cycles-pp.evict 95.49 +0.3 95.75 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 95.75 +0.3 96.03 perf-profile.children.cycles-pp._raw_spin_lock 0.18 ± 2% -0.0 0.17 ± 2% perf-profile.self.cycles-pp.arch_exit_to_user_mode_prepare 0.16 -0.0 0.15 perf-profile.self.cycles-pp.do_syscall_64 0.23 -0.0 0.22 perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack 0.11 -0.0 0.10 perf-profile.self.cycles-pp.entry_SYSCALL_64 0.08 -0.0 0.07 perf-profile.self.cycles-pp.entry_SYSCALL_64_after_hwframe 0.15 -0.0 0.14 perf-profile.self.cycles-pp.llseek 95.08 +0.3 95.35 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath *************************************************************************************************** lkp-srf-2sp2: 192 threads 2 sockets Intel(R) Xeon(R) 6740E CPU @ 2.4GHz (Sierra Forest) with 256G memory ========================================================================================= compiler/cpufreq_governor/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime: gcc-14/performance/x86_64-rhel-9.4/100%/debian-13-x86_64-20250902.cgz/lkp-srf-2sp2/memfd/stress-ng/60s commit: v6.19-rc1 c27cea4416 ("rcu: Re-implement RCU Tasks Trace in terms of SRCU-fast") v6.19-rc1 c27cea4416a396a1c5b6b3529dd ---------------- --------------------------- %stddev %change %stddev \ | \ 257709 +47.4% 379897 meminfo.AnonHugePages 185.79 +48.4% 275.65 boot-time.boot 35229 +49.0% 52482 boot-time.idle 279.39 +32.1% 369.06 uptime.boot 41662 +41.3% 58880 uptime.idle 107491 -3.7% 103488 stress-ng.memfd.nanosecs_per_memfd_create_call 193402 +3.5% 200220 stress-ng.memfd.ops 3224 +3.5% 3338 stress-ng.memfd.ops_per_sec 99066540 +3.5% 1.026e+08 stress-ng.time.minor_page_faults 190038 +1.7% 193305 proc-vmstat.nr_anon_pages 125.88 +47.4% 185.50 proc-vmstat.nr_anon_transparent_hugepages 39831 -3.0% 38648 proc-vmstat.nr_kernel_stack 1.525e+08 +3.5% 1.579e+08 proc-vmstat.numa_hit 1.523e+08 +3.5% 1.577e+08 proc-vmstat.numa_local 1.629e+08 +3.6% 1.688e+08 proc-vmstat.pgalloc_normal 99551866 +3.5% 1.03e+08 proc-vmstat.pgfault 1.622e+08 +3.6% 1.681e+08 proc-vmstat.pgfree 247638 +36.3% 337493 sched_debug.cpu.clock.avg 247674 +36.3% 337526 sched_debug.cpu.clock.max 247599 +36.3% 337457 sched_debug.cpu.clock.min 247436 +36.3% 337285 sched_debug.cpu.clock_task.avg 247527 +36.3% 337377 sched_debug.cpu.clock_task.max 241459 +36.8% 330354 sched_debug.cpu.clock_task.min 247600 +36.3% 337458 sched_debug.cpu_clk 247342 +36.3% 337200 sched_debug.ktime 248152 +36.1% 337703 sched_debug.sched_clk 2.25 +1.5% 2.29 perf-stat.i.MPKI 1.644e+10 +1.9% 1.675e+10 perf-stat.i.branch-instructions 0.24 ± 4% +0.0 0.25 perf-stat.i.branch-miss-rate% 38026731 ± 5% +9.0% 41438665 perf-stat.i.branch-misses 1.712e+08 +3.6% 1.774e+08 perf-stat.i.cache-misses 2.891e+08 +3.3% 2.987e+08 perf-stat.i.cache-references 7.88 -2.0% 7.72 perf-stat.i.cpi 294.71 +2.6% 302.24 perf-stat.i.cpu-migrations 3506 -3.5% 3385 perf-stat.i.cycles-between-cache-misses 7.629e+10 +2.1% 7.785e+10 perf-stat.i.instructions 0.13 +2.1% 0.13 perf-stat.i.ipc 17.00 +3.5% 17.60 perf-stat.i.metric.K/sec 1632141 +3.5% 1689961 perf-stat.i.minor-faults 1632141 +3.5% 1689961 perf-stat.i.page-faults 2.25 +1.5% 2.28 perf-stat.overall.MPKI 0.23 ± 4% +0.0 0.25 perf-stat.overall.branch-miss-rate% 7.91 -2.0% 7.75 perf-stat.overall.cpi 3521 -3.4% 3401 perf-stat.overall.cycles-between-cache-misses 0.13 +2.0% 0.13 perf-stat.overall.ipc 1.618e+10 +1.8% 1.648e+10 perf-stat.ps.branch-instructions 37315073 ± 5% +9.1% 40712563 perf-stat.ps.branch-misses 1.686e+08 +3.5% 1.745e+08 perf-stat.ps.cache-misses 2.849e+08 +3.2% 2.941e+08 perf-stat.ps.cache-references 6628 +1.1% 6704 perf-stat.ps.context-switches 288.02 +2.7% 295.69 perf-stat.ps.cpu-migrations 7.506e+10 +2.0% 7.657e+10 perf-stat.ps.instructions 1606028 +3.5% 1662399 perf-stat.ps.minor-faults 1606028 +3.5% 1662399 perf-stat.ps.page-faults 45.98 -0.3 45.73 perf-profile.calltrace.cycles-pp._raw_spin_lock.inode_sb_list_add.new_inode.__shmem_get_inode.__shmem_file_setup 46.05 -0.3 45.80 perf-profile.calltrace.cycles-pp.inode_sb_list_add.new_inode.__shmem_get_inode.__shmem_file_setup.__x64_sys_memfd_create 45.86 -0.2 45.61 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.inode_sb_list_add.new_inode.__shmem_get_inode 46.28 -0.2 46.03 perf-profile.calltrace.cycles-pp.__shmem_get_inode.__shmem_file_setup.__x64_sys_memfd_create.do_syscall_64.entry_SYSCALL_64_after_hwframe 46.19 -0.2 45.94 perf-profile.calltrace.cycles-pp.new_inode.__shmem_get_inode.__shmem_file_setup.__x64_sys_memfd_create.do_syscall_64 46.54 -0.2 46.30 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.memfd_create 46.49 -0.2 46.25 perf-profile.calltrace.cycles-pp.__shmem_file_setup.__x64_sys_memfd_create.do_syscall_64.entry_SYSCALL_64_after_hwframe.memfd_create 46.54 -0.2 46.30 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.memfd_create 46.56 -0.2 46.33 perf-profile.calltrace.cycles-pp.memfd_create 46.53 -0.2 46.30 perf-profile.calltrace.cycles-pp.__x64_sys_memfd_create.do_syscall_64.entry_SYSCALL_64_after_hwframe.memfd_create 45.51 -0.2 45.29 perf-profile.calltrace.cycles-pp._raw_spin_lock.evict.__dentry_kill.finish_dput.__fput 45.34 -0.2 45.13 perf-profile.calltrace.cycles-pp.native_queued_spin_lock_slowpath._raw_spin_lock.evict.__dentry_kill.finish_dput 46.33 -0.2 46.15 perf-profile.calltrace.cycles-pp.evict.__dentry_kill.finish_dput.__fput.task_work_run 46.54 -0.2 46.36 perf-profile.calltrace.cycles-pp.finish_dput.__fput.task_work_run.exit_to_user_mode_loop.do_syscall_64 46.67 -0.2 46.48 perf-profile.calltrace.cycles-pp.close_range 46.54 -0.2 46.36 perf-profile.calltrace.cycles-pp.__dentry_kill.finish_dput.__fput.task_work_run.exit_to_user_mode_loop 46.62 -0.2 46.44 perf-profile.calltrace.cycles-pp.__fput.task_work_run.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe 46.67 -0.2 46.48 perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.close_range 46.67 -0.2 46.48 perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.close_range 46.64 -0.2 46.46 perf-profile.calltrace.cycles-pp.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.close_range 46.64 -0.2 46.46 perf-profile.calltrace.cycles-pp.task_work_run.exit_to_user_mode_loop.do_syscall_64.entry_SYSCALL_64_after_hwframe.close_range 1.03 +0.0 1.05 perf-profile.calltrace.cycles-pp.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault.stress_memfd_child 1.28 +0.0 1.31 perf-profile.calltrace.cycles-pp.asm_exc_page_fault.stress_memfd_child 1.00 +0.0 1.02 perf-profile.calltrace.cycles-pp.__handle_mm_fault.handle_mm_fault.do_user_addr_fault.exc_page_fault.asm_exc_page_fault 1.12 +0.0 1.15 perf-profile.calltrace.cycles-pp.exc_page_fault.asm_exc_page_fault.stress_memfd_child 0.78 ± 2% +0.0 0.82 perf-profile.calltrace.cycles-pp.shmem_evict_inode.evict.__dentry_kill.finish_dput.__fput 0.75 ± 2% +0.0 0.79 perf-profile.calltrace.cycles-pp.shmem_undo_range.shmem_evict_inode.evict.__dentry_kill.finish_dput 0.87 +0.0 0.91 ± 3% perf-profile.calltrace.cycles-pp.__mmap_region.mmap_region.do_mmap.vm_mmap_pgoff.ksys_mmap_pgoff 0.88 +0.0 0.92 ± 3% perf-profile.calltrace.cycles-pp.mmap_region.do_mmap.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64 1.09 +0.1 1.15 ± 2% perf-profile.calltrace.cycles-pp.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 1.10 +0.1 1.17 ± 2% perf-profile.calltrace.cycles-pp.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 1.12 +0.1 1.18 ± 2% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__mmap 1.12 +0.1 1.19 ± 3% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__mmap 1.07 +0.1 1.14 ± 3% perf-profile.calltrace.cycles-pp.do_mmap.vm_mmap_pgoff.ksys_mmap_pgoff.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.30 +0.1 1.37 ± 2% perf-profile.calltrace.cycles-pp.__mmap 0.60 ± 4% +0.1 0.70 ± 5% perf-profile.calltrace.cycles-pp.folios_put_refs.shmem_undo_range.shmem_fallocate.vfs_fallocate.__x64_sys_fallocate 1.16 ± 3% +0.2 1.35 ± 7% perf-profile.calltrace.cycles-pp.shmem_undo_range.shmem_fallocate.vfs_fallocate.__x64_sys_fallocate.do_syscall_64 1.71 ± 2% +0.2 1.93 ± 5% perf-profile.calltrace.cycles-pp.shmem_fallocate.vfs_fallocate.__x64_sys_fallocate.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.74 ± 2% +0.2 1.97 ± 5% perf-profile.calltrace.cycles-pp.__x64_sys_fallocate.do_syscall_64.entry_SYSCALL_64_after_hwframe 2.26 +0.2 2.48 ± 4% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe 2.25 +0.2 2.48 ± 4% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.72 ± 2% +0.2 1.95 ± 5% perf-profile.calltrace.cycles-pp.vfs_fallocate.__x64_sys_fallocate.do_syscall_64.entry_SYSCALL_64_after_hwframe 92.24 -0.5 91.78 perf-profile.children.cycles-pp._raw_spin_lock 46.05 -0.3 45.80 perf-profile.children.cycles-pp.inode_sb_list_add 46.28 -0.2 46.03 perf-profile.children.cycles-pp.__shmem_get_inode 46.19 -0.2 45.94 perf-profile.children.cycles-pp.new_inode 46.49 -0.2 46.25 perf-profile.children.cycles-pp.__shmem_file_setup 46.54 -0.2 46.30 perf-profile.children.cycles-pp.__x64_sys_memfd_create 46.57 -0.2 46.34 perf-profile.children.cycles-pp.memfd_create 92.33 -0.2 92.11 perf-profile.children.cycles-pp.native_queued_spin_lock_slowpath 46.82 -0.2 46.63 perf-profile.children.cycles-pp.evict 47.03 -0.2 46.84 perf-profile.children.cycles-pp.finish_dput 47.03 -0.2 46.84 perf-profile.children.cycles-pp.__dentry_kill 47.11 -0.2 46.92 perf-profile.children.cycles-pp.__fput 46.65 -0.2 46.46 perf-profile.children.cycles-pp.exit_to_user_mode_loop 46.65 -0.2 46.46 perf-profile.children.cycles-pp.task_work_run 46.67 -0.2 46.49 perf-profile.children.cycles-pp.close_range 97.54 -0.1 97.44 perf-profile.children.cycles-pp.do_syscall_64 97.56 -0.1 97.46 perf-profile.children.cycles-pp.entry_SYSCALL_64_after_hwframe 0.26 -0.0 0.24 perf-profile.children.cycles-pp.shmem_add_to_page_cache 0.24 ± 2% -0.0 0.23 perf-profile.children.cycles-pp.xas_store 0.19 ± 2% -0.0 0.17 ± 2% perf-profile.children.cycles-pp.truncate_inode_folio 0.54 -0.0 0.53 perf-profile.children.cycles-pp.shmem_alloc_and_add_folio 0.13 -0.0 0.12 perf-profile.children.cycles-pp.__filemap_remove_folio 0.07 -0.0 0.06 perf-profile.children.cycles-pp.mas_walk 0.09 -0.0 0.08 perf-profile.children.cycles-pp.vms_gather_munmap_vmas 0.17 +0.0 0.18 perf-profile.children.cycles-pp.do_ftruncate 0.09 +0.0 0.10 perf-profile.children.cycles-pp.notify_change 0.31 +0.0 0.32 perf-profile.children.cycles-pp.llseek 0.23 +0.0 0.24 ± 2% perf-profile.children.cycles-pp.ftruncate64 0.15 ± 3% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.flush_tlb_mm_range 1.03 +0.0 1.05 perf-profile.children.cycles-pp.handle_mm_fault 0.13 ± 3% +0.0 0.15 ± 2% perf-profile.children.cycles-pp.unmapped_area_topdown 0.46 +0.0 0.48 perf-profile.children.cycles-pp.run_ksoftirqd 0.16 ± 2% +0.0 0.18 ± 2% perf-profile.children.cycles-pp.__get_unmapped_area 0.15 ± 2% +0.0 0.17 ± 2% perf-profile.children.cycles-pp.arch_get_unmapped_area_topdown 1.00 +0.0 1.02 perf-profile.children.cycles-pp.__handle_mm_fault 0.52 +0.0 0.54 perf-profile.children.cycles-pp.rcu_core 0.16 ± 3% +0.0 0.18 ± 3% perf-profile.children.cycles-pp.shmem_get_unmapped_area 0.32 +0.0 0.34 perf-profile.children.cycles-pp.unmap_page_range 0.30 +0.0 0.32 perf-profile.children.cycles-pp.zap_pmd_range 0.20 ± 2% +0.0 0.22 perf-profile.children.cycles-pp.zap_page_range_single_batched 0.28 +0.0 0.31 perf-profile.children.cycles-pp.zap_pte_range 0.23 +0.0 0.26 perf-profile.children.cycles-pp.unmap_mapping_range 0.13 ± 3% +0.0 0.16 ± 3% perf-profile.children.cycles-pp.vm_unmapped_area 0.15 +0.0 0.18 perf-profile.children.cycles-pp.perf_event_mmap 0.14 +0.0 0.17 perf-profile.children.cycles-pp.perf_event_mmap_event 0.21 +0.0 0.24 perf-profile.children.cycles-pp.zap_page_range_single 1.44 +0.0 1.47 perf-profile.children.cycles-pp.asm_exc_page_fault 0.78 ± 2% +0.0 0.82 perf-profile.children.cycles-pp.shmem_evict_inode 0.87 +0.0 0.91 ± 3% perf-profile.children.cycles-pp.__mmap_region 0.88 +0.0 0.92 ± 3% perf-profile.children.cycles-pp.mmap_region 0.00 +0.1 0.05 perf-profile.children.cycles-pp.fault_dirty_shared_page 0.00 +0.1 0.05 perf-profile.children.cycles-pp.shmem_recalc_inode 1.07 +0.1 1.14 ± 3% perf-profile.children.cycles-pp.do_mmap 1.10 +0.1 1.17 ± 2% perf-profile.children.cycles-pp.ksys_mmap_pgoff 1.09 +0.1 1.16 ± 3% perf-profile.children.cycles-pp.vm_mmap_pgoff 1.30 +0.1 1.38 ± 2% perf-profile.children.cycles-pp.__mmap 0.41 ± 3% +0.1 0.51 ± 11% perf-profile.children.cycles-pp.__folio_batch_release 0.41 ± 3% +0.1 0.51 ± 11% perf-profile.children.cycles-pp.folio_batch_move_lru 0.41 ± 3% +0.1 0.51 ± 11% perf-profile.children.cycles-pp.lru_add_drain_cpu 0.51 ± 4% +0.1 0.65 ± 11% perf-profile.children.cycles-pp.__page_cache_release 1.11 ± 3% +0.1 1.24 ± 4% perf-profile.children.cycles-pp.folios_put_refs 1.71 ± 2% +0.2 1.93 ± 5% perf-profile.children.cycles-pp.shmem_fallocate 1.74 ± 2% +0.2 1.97 ± 5% perf-profile.children.cycles-pp.__x64_sys_fallocate 1.72 ± 2% +0.2 1.95 ± 5% perf-profile.children.cycles-pp.vfs_fallocate 0.66 ± 4% +0.2 0.89 ± 14% perf-profile.children.cycles-pp.folio_lruvec_lock_irqsave 0.70 ± 4% +0.2 0.93 ± 14% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 1.92 ± 2% +0.2 2.15 ± 5% perf-profile.children.cycles-pp.shmem_undo_range 91.97 -0.2 91.76 perf-profile.self.cycles-pp.native_queued_spin_lock_slowpath 0.07 -0.0 0.06 perf-profile.self.cycles-pp.mas_walk 0.08 +0.0 0.09 perf-profile.self.cycles-pp.entry_SYSCALL_64 Disclaimer: Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki
