- Linux-kselftest-mirror - lists.linaro.org

[linux-next:master] [ptp] 403376ddb4: stress-ng.clock.ops_per_sec -12.7% regression

by kernel test robot

Hello, kernel test robot noticed a -12.7% regression of stress-ng.clock.ops_per_sec on: commit: 403376ddb4221be9db5326ae334773807df71ffe ("ptp: add debugfs interface to see applied channel masks") https://git.kernel.org/cgit/linux/kernel/git/next/linux-next.git master testcase: stress-ng test machine: 36 threads 1 sockets Intel(R) Core(TM) i9-10980XE CPU @ 3.00GHz (Cascade Lake) with 128G memory parameters: nr_threads: 1 disk: 1HDD testtime: 60s class: interrupt test: clock cpufreq_governor: performance 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 <oliver.sang(a)intel.com> | Closes: https://lore.kernel.org/oe-lkp/202310271441.b9fb0896-oliver.sang@intel.com Details are as below: --------------------------------------------------------------------------------------------------> The kernel config and materials to reproduce are available at: https://download.01.org/0day-ci/archive/20231027/202310271441.b9fb0896-oliv… ========================================================================================= class/compiler/cpufreq_governor/disk/kconfig/nr_threads/rootfs/tbox_group/test/testcase/testtime: interrupt/gcc-12/performance/1HDD/x86_64-rhel-8.3/1/debian-11.1-x86_64-20220510.cgz/lkp-csl-d02/clock/stress-ng/60s commit: c5a445b1e9 ("ptp: support event queue reader channel masks") 403376ddb4 ("ptp: add debugfs interface to see applied channel masks") c5a445b1e9347b14 403376ddb4221be9db5326ae334 ---------------- --------------------------- %stddev %change %stddev \ | \ 2.50 +8.3% 2.71 iostat.cpu.system 0.05 ± 3% +0.0 0.06 mpstat.cpu.all.soft% 1.84 +0.2 2.04 mpstat.cpu.all.sys% 200469 -10.7% 178950 vmstat.system.cs 135153 -7.8% 124597 vmstat.system.in 2804514 -12.7% 2448917 stress-ng.clock.ops 46741 -12.7% 40815 stress-ng.clock.ops_per_sec 78.00 +2.6% 80.00 stress-ng.time.percent_of_cpu_this_job_got 5606454 -12.7% 4896355 stress-ng.time.voluntary_context_switches 18583 ± 5% +31.1% 24360 ± 9% turbostat.C1 2.90 ± 2% +0.1 3.03 turbostat.C1E% 5353747 -13.0% 4655189 turbostat.POLL 0.28 -0.0 0.24 turbostat.POLL% 10.11 +1.4% 10.25 turbostat.RAMWatt 88825 -6.6% 82944 proc-vmstat.nr_active_anon 11367 +4.6% 11892 proc-vmstat.nr_mapped 96532 -6.6% 90119 proc-vmstat.nr_shmem 19819 +4.1% 20633 proc-vmstat.nr_slab_reclaimable 88825 -6.6% 82944 proc-vmstat.nr_zone_active_anon 420661 +27.6% 536903 ± 35% proc-vmstat.numa_hit 420556 +27.4% 535725 ± 36% proc-vmstat.numa_local 133275 -6.9% 124053 proc-vmstat.pgactivate 488366 ± 2% +60.4% 783374 proc-vmstat.pgalloc_normal 227687 +3.2% 234860 proc-vmstat.pgfault 323139 ± 3% +94.6% 628694 proc-vmstat.pgfree 0.00 ±141% +325.0% 0.01 ± 26% perf-sched.sch_delay.avg.ms.kjournald2.kthread.ret_from_fork.ret_from_fork_asm 0.01 ±217% +455.3% 0.04 ± 68% perf-sched.sch_delay.max.ms.__cond_resched.__kmem_cache_alloc_node.__kmalloc_node.alloc_cpumask_var_node.clock_was_set 0.10 ± 14% +66.8% 0.16 ± 15% perf-sched.sch_delay.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep_timens.__x64_sys_clock_nanosleep 0.00 ±141% +325.0% 0.01 ± 26% perf-sched.sch_delay.max.ms.kjournald2.kthread.ret_from_fork.ret_from_fork_asm 0.91 ± 21% -53.8% 0.42 ± 55% perf-sched.sch_delay.max.ms.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm 1.27 +18.7% 1.51 perf-sched.total_wait_and_delay.average.ms 1.27 +18.7% 1.51 perf-sched.total_wait_time.average.ms 18.82 ± 20% +59.4% 29.99 ± 27% perf-sched.wait_and_delay.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write 1278 ± 2% +16.3% 1487 ± 3% perf-sched.wait_and_delay.count.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm 220.33 ± 5% +14.1% 251.33 ± 2% perf-sched.wait_and_delay.count.worker_thread.kthread.ret_from_fork.ret_from_fork_asm 0.20 ± 13% +63.7% 0.33 ± 14% perf-sched.wait_and_delay.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep_timens.__x64_sys_clock_nanosleep 18.82 ± 20% +59.4% 29.99 ± 27% perf-sched.wait_time.avg.ms.__cond_resched.generic_perform_write.shmem_file_write_iter.vfs_write.ksys_write 0.01 ±208% +433.3% 0.05 ± 64% perf-sched.wait_time.max.ms.__cond_resched.__kmem_cache_alloc_node.__kmalloc_node.alloc_cpumask_var_node.clock_was_set 0.10 ± 12% +60.7% 0.16 ± 13% perf-sched.wait_time.max.ms.do_nanosleep.hrtimer_nanosleep.common_nsleep_timens.__x64_sys_clock_nanosleep 0.13 +35.1% 0.17 ± 2% perf-stat.i.MPKI 9.417e+08 +4.1% 9.8e+08 perf-stat.i.branch-instructions 4.24 ± 2% +0.6 4.81 ± 2% perf-stat.i.cache-miss-rate% 1107890 +23.8% 1371103 ± 2% perf-stat.i.cache-misses 18969540 +28.6% 24388966 perf-stat.i.cache-references 210406 -11.1% 187069 perf-stat.i.context-switches 1.15 -3.5% 1.11 perf-stat.i.cpi 185.83 ± 2% +7.7% 200.19 ± 4% perf-stat.i.cpu-migrations 56299 ± 6% -64.8% 19830 ± 6% perf-stat.i.cycles-between-cache-misses 1.249e+09 +2.7% 1.283e+09 perf-stat.i.dTLB-loads 0.00 ± 6% +0.0 0.00 ± 4% perf-stat.i.dTLB-store-miss-rate% 7425 ± 5% +12.8% 8373 ± 4% perf-stat.i.dTLB-store-misses 7.573e+08 +2.3% 7.746e+08 perf-stat.i.dTLB-stores 6674913 ± 2% -5.5% 6305796 perf-stat.i.iTLB-load-misses 5.03e+09 +3.1% 5.184e+09 perf-stat.i.instructions 1159 +5.5% 1222 ± 2% perf-stat.i.instructions-per-iTLB-miss 0.89 +3.0% 0.92 perf-stat.i.ipc 536.86 +28.0% 687.18 perf-stat.i.metric.K/sec 81.89 +3.0% 84.38 perf-stat.i.metric.M/sec 2127 +5.2% 2239 ± 2% perf-stat.i.minor-faults 106399 ± 2% +36.0% 144713 ± 3% perf-stat.i.node-loads 106511 ± 5% +71.6% 182771 ± 3% perf-stat.i.node-stores 2127 +5.2% 2239 ± 2% perf-stat.i.page-faults 0.22 +20.1% 0.26 ± 2% perf-stat.overall.MPKI 1.09 -2.6% 1.06 perf-stat.overall.cpi 4955 -18.8% 4021 ± 2% perf-stat.overall.cycles-between-cache-misses 0.00 ± 5% +0.0 0.00 ± 4% perf-stat.overall.dTLB-store-miss-rate% 753.96 +9.1% 822.64 ± 2% perf-stat.overall.instructions-per-iTLB-miss 0.92 +2.7% 0.94 perf-stat.overall.ipc 9.27e+08 +4.1% 9.648e+08 perf-stat.ps.branch-instructions 1090868 +23.8% 1350235 ± 2% perf-stat.ps.cache-misses 18670301 +28.6% 24005580 perf-stat.ps.cache-references 207054 -11.1% 184104 perf-stat.ps.context-switches 182.86 ± 2% +7.7% 197.01 ± 4% perf-stat.ps.cpu-migrations 1.229e+09 +2.7% 1.263e+09 perf-stat.ps.dTLB-loads 7309 ± 5% +12.8% 8244 ± 4% perf-stat.ps.dTLB-store-misses 7.454e+08 +2.3% 7.624e+08 perf-stat.ps.dTLB-stores 6568626 ± 2% -5.5% 6205894 perf-stat.ps.iTLB-load-misses 4.951e+09 +3.1% 5.103e+09 perf-stat.ps.instructions 2094 +5.2% 2204 ± 2% perf-stat.ps.minor-faults 104758 ± 2% +36.0% 142499 ± 3% perf-stat.ps.node-loads 104880 ± 5% +71.6% 179969 ± 3% perf-stat.ps.node-stores 2094 +5.2% 2204 ± 2% perf-stat.ps.page-faults 3.124e+11 +3.9% 3.245e+11 perf-stat.total.instructions 9.42 ± 5% -2.2 7.20 ± 8% perf-profile.calltrace.cycles-pp.clock_gettime 9.26 ± 5% -2.2 7.08 ± 8% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.clock_gettime 9.24 ± 5% -2.2 7.07 ± 8% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_gettime 8.84 ± 5% -2.2 6.67 ± 9% perf-profile.calltrace.cycles-pp.e1000e_read_systim.e1000e_phc_gettimex.pc_clock_gettime.__x64_sys_clock_gettime.do_syscall_64 9.20 ± 5% -2.2 7.04 ± 8% perf-profile.calltrace.cycles-pp.__x64_sys_clock_gettime.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_gettime 8.96 ± 5% -2.2 6.81 ± 8% perf-profile.calltrace.cycles-pp.e1000e_phc_gettimex.pc_clock_gettime.__x64_sys_clock_gettime.do_syscall_64.entry_SYSCALL_64_after_hwframe 9.12 ± 5% -2.1 6.98 ± 8% perf-profile.calltrace.cycles-pp.pc_clock_gettime.__x64_sys_clock_gettime.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_gettime 10.96 ± 2% -2.0 8.98 ± 8% perf-profile.calltrace.cycles-pp.syscall 10.98 ± 3% -1.7 9.28 ± 9% perf-profile.calltrace.cycles-pp.clock_adjtime 10.09 ± 3% -1.5 8.55 ± 10% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.clock_adjtime 9.94 ± 3% -1.5 8.42 ± 10% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_adjtime 9.68 ± 3% -1.5 8.20 ± 10% perf-profile.calltrace.cycles-pp.__do_sys_clock_adjtime.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_adjtime 8.53 ± 4% -1.3 7.22 ± 9% perf-profile.calltrace.cycles-pp.do_adjtimex.__do_sys_clock_adjtime.do_syscall_64.entry_SYSCALL_64_after_hwframe.clock_adjtime 6.44 ± 5% -1.2 5.20 ± 10% perf-profile.calltrace.cycles-pp.poll_idle.cpuidle_enter_state.cpuidle_enter.cpuidle_idle_call.do_idle 6.22 ± 4% -1.1 5.12 ± 11% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.syscall 5.59 ± 3% -1.0 4.59 ± 11% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 6.42 ± 3% -0.9 5.51 ± 10% perf-profile.calltrace.cycles-pp.timekeeping_inject_offset.do_adjtimex.__do_sys_clock_adjtime.do_syscall_64.entry_SYSCALL_64_after_hwframe 5.86 ± 3% -0.9 5.00 ± 9% perf-profile.calltrace.cycles-pp.clock_was_set.timekeeping_inject_offset.do_adjtimex.__do_sys_clock_adjtime.do_syscall_64 3.34 ± 5% -0.7 2.68 ± 11% perf-profile.calltrace.cycles-pp.__x64_sys_clock_gettime.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 2.99 ± 9% -0.6 2.34 ± 14% perf-profile.calltrace.cycles-pp.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.poll_idle.cpuidle_enter_state.cpuidle_enter 2.47 ± 13% -0.5 1.94 ± 15% perf-profile.calltrace.cycles-pp.__sysvec_apic_timer_interrupt.sysvec_apic_timer_interrupt.asm_sysvec_apic_timer_interrupt.poll_idle.cpuidle_enter_state 3.31 ± 3% -0.5 2.83 ± 8% perf-profile.calltrace.cycles-pp._raw_spin_lock_irqsave.clock_was_set.timekeeping_inject_offset.do_adjtimex.__do_sys_clock_adjtime 2.78 ± 3% -0.4 2.42 ± 10% perf-profile.calltrace.cycles-pp.timer_create 2.37 ± 3% -0.3 2.07 ± 10% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.timer_create 2.33 ± 3% -0.3 2.03 ± 10% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.timer_create 1.64 ± 3% -0.3 1.36 ± 10% perf-profile.calltrace.cycles-pp.add_device_randomness.do_adjtimex.__do_sys_clock_adjtime.do_syscall_64.entry_SYSCALL_64_after_hwframe 1.43 ± 3% -0.3 1.16 ± 11% perf-profile.calltrace.cycles-pp.blake2s_compress.blake2s_update.add_device_randomness.do_adjtimex.__do_sys_clock_adjtime 1.52 ± 3% -0.3 1.26 ± 11% perf-profile.calltrace.cycles-pp.blake2s_update.add_device_randomness.do_adjtimex.__do_sys_clock_adjtime.do_syscall_64 1.23 ± 8% -0.2 0.99 ± 12% perf-profile.calltrace.cycles-pp.posix_cpu_clock_get.__x64_sys_clock_gettime.do_syscall_64.entry_SYSCALL_64_after_hwframe.syscall 1.02 ± 5% -0.1 0.88 ± 12% perf-profile.calltrace.cycles-pp.read_tsc.ktime_get_update_offsets_now.clock_was_set.timekeeping_inject_offset.do_adjtimex 0.74 ± 4% -0.1 0.61 ± 13% perf-profile.calltrace.cycles-pp.ttwu_do_activate.try_to_wake_up.hrtimer_wakeup.__hrtimer_run_queues.hrtimer_interrupt 0.47 ± 45% +0.4 0.90 ± 17% perf-profile.calltrace.cycles-pp.smpboot_thread_fn.kthread.ret_from_fork.ret_from_fork_asm 0.00 +0.7 0.69 ± 10% perf-profile.calltrace.cycles-pp.lookup_one_len.start_creating.__debugfs_create_file.ptp_open.posix_clock_open 0.00 +0.7 0.72 ± 12% perf-profile.calltrace.cycles-pp.dput.simple_recursive_removal.debugfs_remove.ptp_release.posix_clock_release 0.00 +0.7 0.75 ± 14% perf-profile.calltrace.cycles-pp.lookup_one_len.start_creating.debugfs_create_dir.ptp_open.posix_clock_open 0.00 +0.8 0.75 ± 12% perf-profile.calltrace.cycles-pp.start_creating.__debugfs_create_file.ptp_open.posix_clock_open.chrdev_open 0.00 +0.9 0.86 ± 15% perf-profile.calltrace.cycles-pp.start_creating.debugfs_create_dir.ptp_open.posix_clock_open.chrdev_open 0.00 +0.9 0.91 ± 14% perf-profile.calltrace.cycles-pp.mnt_get_count.mntput_no_expire.simple_recursive_removal.debugfs_remove.ptp_release 0.00 +1.0 1.05 ± 13% perf-profile.calltrace.cycles-pp.mntput_no_expire.simple_recursive_removal.debugfs_remove.ptp_release.posix_clock_release 0.00 +1.3 1.26 ± 12% perf-profile.calltrace.cycles-pp.__debugfs_create_file.ptp_open.posix_clock_open.chrdev_open.do_dentry_open 0.00 +1.5 1.47 ± 13% perf-profile.calltrace.cycles-pp.debugfs_create_dir.ptp_open.posix_clock_open.chrdev_open.do_dentry_open 0.00 +2.4 2.42 ± 11% perf-profile.calltrace.cycles-pp.simple_recursive_removal.debugfs_remove.ptp_release.posix_clock_release.__fput 0.00 +3.0 2.95 ± 11% perf-profile.calltrace.cycles-pp.debugfs_remove.ptp_release.posix_clock_release.__fput.__x64_sys_close 1.74 ± 5% +3.0 4.71 ± 8% perf-profile.calltrace.cycles-pp.do_dentry_open.do_open.path_openat.do_filp_open.do_sys_openat2 2.90 ± 6% +3.0 5.87 ± 9% perf-profile.calltrace.cycles-pp.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64 1.35 ± 6% +3.0 4.33 ± 8% perf-profile.calltrace.cycles-pp.posix_clock_open.chrdev_open.do_dentry_open.do_open.path_openat 1.42 ± 6% +3.0 4.41 ± 8% perf-profile.calltrace.cycles-pp.chrdev_open.do_dentry_open.do_open.path_openat.do_filp_open 2.02 ± 5% +3.0 5.01 ± 8% perf-profile.calltrace.cycles-pp.do_open.path_openat.do_filp_open.do_sys_openat2.__x64_sys_openat 2.95 ± 6% +3.0 5.95 ± 9% perf-profile.calltrace.cycles-pp.do_filp_open.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe 3.51 ± 6% +3.0 6.51 ± 9% perf-profile.calltrace.cycles-pp.do_sys_openat2.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 3.54 ± 6% +3.0 6.55 ± 9% perf-profile.calltrace.cycles-pp.__x64_sys_openat.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 1.18 ± 6% +3.0 4.21 ± 8% perf-profile.calltrace.cycles-pp.ptp_open.posix_clock_open.chrdev_open.do_dentry_open.do_open 3.57 ± 6% +3.0 6.61 ± 9% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.open64 3.75 ± 6% +3.1 6.82 ± 10% perf-profile.calltrace.cycles-pp.open64 3.58 ± 6% +3.1 6.66 ± 10% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.open64 0.93 ± 11% +3.2 4.16 ± 11% perf-profile.calltrace.cycles-pp.entry_SYSCALL_64_after_hwframe.__close 0.90 ± 11% +3.2 4.13 ± 11% perf-profile.calltrace.cycles-pp.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close 0.87 ± 11% +3.2 4.10 ± 12% perf-profile.calltrace.cycles-pp.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close 1.06 ± 8% +3.2 4.30 ± 11% perf-profile.calltrace.cycles-pp.__close 0.51 ± 45% +3.4 3.91 ± 12% perf-profile.calltrace.cycles-pp.__fput.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe.__close 0.00 +3.6 3.59 ± 11% perf-profile.calltrace.cycles-pp.ptp_release.posix_clock_release.__fput.__x64_sys_close.do_syscall_64 0.00 +3.7 3.68 ± 11% perf-profile.calltrace.cycles-pp.posix_clock_release.__fput.__x64_sys_close.do_syscall_64.entry_SYSCALL_64_after_hwframe 12.58 ± 4% -2.8 9.74 ± 9% perf-profile.children.cycles-pp.__x64_sys_clock_gettime 9.42 ± 5% -2.2 7.20 ± 8% perf-profile.children.cycles-pp.clock_gettime 8.84 ± 5% -2.2 6.67 ± 9% perf-profile.children.cycles-pp.e1000e_read_systim 8.97 ± 5% -2.2 6.81 ± 8% perf-profile.children.cycles-pp.e1000e_phc_gettimex 9.12 ± 5% -2.1 6.98 ± 8% perf-profile.children.cycles-pp.pc_clock_gettime 10.92 ± 3% -1.8 9.07 ± 8% perf-profile.children.cycles-pp.syscall 11.24 ± 3% -1.7 9.51 ± 10% perf-profile.children.cycles-pp.clock_adjtime 9.69 ± 3% -1.5 8.21 ± 10% perf-profile.children.cycles-pp.__do_sys_clock_adjtime 7.19 ± 4% -1.4 5.80 ± 10% perf-profile.children.cycles-pp.poll_idle 8.53 ± 4% -1.3 7.22 ± 9% perf-profile.children.cycles-pp.do_adjtimex 6.42 ± 3% -0.9 5.51 ± 10% perf-profile.children.cycles-pp.timekeeping_inject_offset 5.93 ± 3% -0.9 5.06 ± 9% perf-profile.children.cycles-pp.clock_was_set 4.47 ± 3% -0.5 3.98 ± 7% perf-profile.children.cycles-pp._raw_spin_lock_irqsave 2.37 ± 3% -0.4 1.95 ± 9% perf-profile.children.cycles-pp.entry_SYSRETQ_unsafe_stack 2.88 ± 2% -0.4 2.50 ± 10% perf-profile.children.cycles-pp.timer_create 2.08 ± 3% -0.3 1.74 ± 9% perf-profile.children.cycles-pp.read_tsc 1.65 ± 3% -0.3 1.37 ± 11% perf-profile.children.cycles-pp.add_device_randomness 1.43 ± 3% -0.3 1.16 ± 11% perf-profile.children.cycles-pp.blake2s_compress 1.53 ± 3% -0.3 1.26 ± 11% perf-profile.children.cycles-pp.blake2s_update 1.74 ± 5% -0.3 1.48 ± 8% perf-profile.children.cycles-pp.hrtimer_wakeup 1.24 ± 8% -0.2 1.00 ± 12% perf-profile.children.cycles-pp.posix_cpu_clock_get 1.70 ± 5% -0.2 1.46 ± 8% perf-profile.children.cycles-pp.try_to_wake_up 1.81 ± 6% -0.2 1.59 ± 11% perf-profile.children.cycles-pp.ktime_get_update_offsets_now 1.14 ± 3% -0.2 0.96 ± 10% perf-profile.children.cycles-pp.ttwu_do_activate 0.91 ± 3% -0.2 0.73 ± 13% perf-profile.children.cycles-pp.rep_movs_alternative 1.20 ± 6% -0.2 1.02 ± 9% perf-profile.children.cycles-pp.lapic_next_deadline 1.04 ± 4% -0.2 0.87 ± 13% perf-profile.children.cycles-pp.hrtimer_start_range_ns 1.00 ± 4% -0.1 0.86 ± 10% perf-profile.children.cycles-pp.activate_task 0.96 ± 5% -0.1 0.83 ± 10% perf-profile.children.cycles-pp.syscall_exit_to_user_mode 0.46 ± 7% -0.1 0.33 ± 15% perf-profile.children.cycles-pp._raw_spin_unlock_irqrestore 0.54 ± 8% -0.1 0.42 ± 16% perf-profile.children.cycles-pp.clockevents_program_min_delta 1.04 ± 4% -0.1 0.94 ± 6% perf-profile.children.cycles-pp.memset_orig 0.52 ± 8% -0.1 0.42 ± 10% perf-profile.children.cycles-pp.entry_SYSCALL_64_safe_stack 0.22 ± 17% -0.1 0.14 ± 34% perf-profile.children.cycles-pp.posix_get_monotonic_timespec 0.22 ± 20% -0.1 0.14 ± 20% perf-profile.children.cycles-pp.ktime_get_real_ts64 0.11 ± 20% -0.1 0.05 ± 51% perf-profile.children.cycles-pp.__cgroup_account_cputime 0.22 ± 9% -0.1 0.16 ± 16% perf-profile.children.cycles-pp.posix_get_boottime_timespec 0.12 ± 7% -0.0 0.08 ± 27% perf-profile.children.cycles-pp.update_curr_fair 0.06 ± 46% +0.0 0.10 ± 25% perf-profile.children.cycles-pp.memcpy_orig 0.01 ±223% +0.1 0.07 ± 21% perf-profile.children.cycles-pp.rcu_nocb_try_bypass 0.00 +0.1 0.06 ± 14% perf-profile.children.cycles-pp.default_pointer 0.00 +0.1 0.07 ± 15% perf-profile.children.cycles-pp.__srcu_read_unlock 0.00 +0.1 0.08 ± 32% perf-profile.children.cycles-pp.iput 0.00 +0.1 0.08 ± 23% perf-profile.children.cycles-pp.lookup_one_common 0.00 +0.1 0.09 ± 18% perf-profile.children.cycles-pp.inode_init_once 0.00 +0.1 0.09 ± 22% perf-profile.children.cycles-pp.__srcu_read_lock 0.00 +0.1 0.09 ± 26% perf-profile.children.cycles-pp.up_write 0.00 +0.1 0.09 ± 20% perf-profile.children.cycles-pp.__d_lookup 0.00 +0.1 0.10 ± 19% perf-profile.children.cycles-pp.setup_object 0.14 ± 20% +0.1 0.24 ± 13% perf-profile.children.cycles-pp.get_obj_cgroup_from_current 0.00 +0.1 0.10 ± 27% perf-profile.children.cycles-pp.shrink_dcache_parent 0.02 ±142% +0.1 0.12 ± 9% perf-profile.children.cycles-pp.lockref_put_or_lock 0.00 +0.1 0.10 ± 20% perf-profile.children.cycles-pp.d_lookup 0.00 +0.1 0.10 ± 18% perf-profile.children.cycles-pp.__wake_up_common_lock 0.00 +0.1 0.11 ± 17% perf-profile.children.cycles-pp.lookup_dcache 0.00 +0.1 0.11 ± 22% perf-profile.children.cycles-pp.shuffle_freelist 0.00 +0.1 0.12 ± 17% perf-profile.children.cycles-pp.d_instantiate 0.00 +0.1 0.12 ± 24% perf-profile.children.cycles-pp.down_write 0.10 ± 36% +0.1 0.23 ± 29% perf-profile.children.cycles-pp.obj_cgroup_charge 0.00 +0.1 0.14 ± 24% perf-profile.children.cycles-pp.allocate_slab 0.00 +0.1 0.14 ± 36% perf-profile.children.cycles-pp.memcg_list_lru_alloc 0.00 +0.1 0.14 ± 34% perf-profile.children.cycles-pp.d_walk 0.00 +0.1 0.14 ± 5% perf-profile.children.cycles-pp.number 0.00 +0.2 0.16 ± 16% perf-profile.children.cycles-pp.__destroy_inode 0.00 +0.2 0.16 ± 16% perf-profile.children.cycles-pp.dentry_unlink_inode 0.10 ± 26% +0.2 0.26 ± 18% perf-profile.children.cycles-pp.___slab_alloc 0.00 +0.2 0.17 ± 17% perf-profile.children.cycles-pp.destroy_inode 0.00 +0.2 0.18 ± 13% perf-profile.children.cycles-pp.fsnotify_grab_connector 0.27 ± 20% +0.2 0.44 ± 12% perf-profile.children.cycles-pp.__call_rcu_common 0.34 ± 14% +0.2 0.52 ± 15% perf-profile.children.cycles-pp.mod_objcg_state 0.00 +0.2 0.19 ± 8% perf-profile.children.cycles-pp.inode_init_always 0.00 +0.2 0.22 ± 15% perf-profile.children.cycles-pp.fsnotify_destroy_marks 0.40 ± 12% +0.3 0.66 ± 18% perf-profile.children.cycles-pp.memcg_slab_post_alloc_hook 0.00 +0.3 0.26 ± 22% perf-profile.children.cycles-pp.d_invalidate 0.00 +0.3 0.28 ± 10% perf-profile.children.cycles-pp.__d_add 0.00 +0.3 0.30 ± 11% perf-profile.children.cycles-pp.simple_lookup 0.00 +0.3 0.32 ± 15% perf-profile.children.cycles-pp.evict 0.55 ± 9% +0.4 0.90 ± 17% perf-profile.children.cycles-pp.smpboot_thread_fn 0.14 ± 24% +0.4 0.50 ± 15% perf-profile.children.cycles-pp._find_next_bit 0.00 +0.4 0.37 ± 11% perf-profile.children.cycles-pp.sprintf 0.00 +0.4 0.37 ± 11% perf-profile.children.cycles-pp.vsnprintf 0.00 +0.4 0.43 ± 15% perf-profile.children.cycles-pp.slab_pre_alloc_hook 0.00 +0.6 0.58 ± 12% perf-profile.children.cycles-pp.__d_alloc 1.69 ± 7% +0.6 2.30 ± 14% perf-profile.children.cycles-pp.__do_softirq 1.15 ± 4% +0.6 1.80 ± 17% perf-profile.children.cycles-pp.rcu_do_batch 1.26 ± 4% +0.6 1.91 ± 15% perf-profile.children.cycles-pp.rcu_core 0.00 +0.7 0.70 ± 14% perf-profile.children.cycles-pp.alloc_inode 0.00 +0.8 0.76 ± 10% perf-profile.children.cycles-pp.d_alloc 0.00 +0.8 0.84 ± 11% perf-profile.children.cycles-pp.d_alloc_parallel 0.59 ± 6% +0.9 1.46 ± 5% perf-profile.children.cycles-pp._raw_spin_lock 0.00 +0.9 0.91 ± 11% perf-profile.children.cycles-pp.new_inode 0.00 +1.0 1.01 ± 15% perf-profile.children.cycles-pp.kmem_cache_alloc_lru 0.00 +1.0 1.05 ± 11% perf-profile.children.cycles-pp.__dentry_kill 0.00 +1.1 1.10 ± 11% perf-profile.children.cycles-pp.dentry_kill 0.00 +1.2 1.16 ± 11% perf-profile.children.cycles-pp.__lookup_slow 0.10 ± 30% +1.2 1.31 ± 10% perf-profile.children.cycles-pp.dput 0.00 +1.3 1.26 ± 12% perf-profile.children.cycles-pp.__debugfs_create_file 0.00 +1.4 1.44 ± 13% perf-profile.children.cycles-pp.mnt_get_count 0.00 +1.4 1.44 ± 11% perf-profile.children.cycles-pp.lookup_one_len 0.00 +1.5 1.47 ± 13% perf-profile.children.cycles-pp.debugfs_create_dir 0.01 ±223% +1.6 1.60 ± 13% perf-profile.children.cycles-pp.mntput_no_expire 0.00 +1.6 1.61 ± 11% perf-profile.children.cycles-pp.start_creating 0.00 +2.4 2.43 ± 12% perf-profile.children.cycles-pp.simple_recursive_removal 0.00 +3.0 2.96 ± 11% perf-profile.children.cycles-pp.debugfs_remove 1.75 ± 5% +3.0 4.71 ± 8% perf-profile.children.cycles-pp.do_dentry_open 1.35 ± 6% +3.0 4.33 ± 8% perf-profile.children.cycles-pp.posix_clock_open 2.93 ± 5% +3.0 5.91 ± 9% perf-profile.children.cycles-pp.path_openat 1.42 ± 6% +3.0 4.41 ± 8% perf-profile.children.cycles-pp.chrdev_open 2.03 ± 5% +3.0 5.02 ± 8% perf-profile.children.cycles-pp.do_open 2.97 ± 6% +3.0 5.98 ± 9% perf-profile.children.cycles-pp.do_filp_open 3.54 ± 6% +3.0 6.56 ± 9% perf-profile.children.cycles-pp.do_sys_openat2 3.57 ± 6% +3.0 6.59 ± 9% perf-profile.children.cycles-pp.__x64_sys_openat 1.18 ± 6% +3.0 4.22 ± 8% perf-profile.children.cycles-pp.ptp_open 3.79 ± 6% +3.1 6.84 ± 10% perf-profile.children.cycles-pp.open64 0.87 ± 11% +3.2 4.10 ± 12% perf-profile.children.cycles-pp.__x64_sys_close 1.09 ± 9% +3.2 4.34 ± 11% perf-profile.children.cycles-pp.__close 0.59 ± 11% +3.3 3.92 ± 12% perf-profile.children.cycles-pp.__fput 0.31 ± 19% +3.4 3.68 ± 11% perf-profile.children.cycles-pp.posix_clock_release 0.18 ± 15% +3.4 3.59 ± 11% perf-profile.children.cycles-pp.ptp_release 8.84 ± 5% -2.2 6.67 ± 9% perf-profile.self.cycles-pp.e1000e_read_systim 3.55 ± 7% -0.8 2.72 ± 14% perf-profile.self.cycles-pp.poll_idle 4.42 ± 3% -0.5 3.92 ± 7% perf-profile.self.cycles-pp._raw_spin_lock_irqsave 2.32 ± 4% -0.4 1.90 ± 9% perf-profile.self.cycles-pp.entry_SYSRETQ_unsafe_stack 2.01 ± 3% -0.3 1.70 ± 8% perf-profile.self.cycles-pp.read_tsc 1.78 ± 5% -0.3 1.50 ± 9% perf-profile.self.cycles-pp.syscall 1.43 ± 3% -0.3 1.16 ± 11% perf-profile.self.cycles-pp.blake2s_compress 1.08 ± 5% -0.2 0.88 ± 15% perf-profile.self.cycles-pp._copy_to_user 1.20 ± 6% -0.2 1.02 ± 9% perf-profile.self.cycles-pp.lapic_next_deadline 0.56 ± 4% -0.1 0.44 ± 17% perf-profile.self.cycles-pp.rep_movs_alternative 0.42 ± 8% -0.1 0.30 ± 16% perf-profile.self.cycles-pp._raw_spin_unlock_irqrestore 0.52 ± 8% -0.1 0.42 ± 10% perf-profile.self.cycles-pp.entry_SYSCALL_64_safe_stack 0.38 ± 10% -0.1 0.30 ± 19% perf-profile.self.cycles-pp.syscall_enter_from_user_mode 0.44 ± 9% -0.1 0.36 ± 9% perf-profile.self.cycles-pp.__schedule 0.28 ± 14% -0.1 0.20 ± 10% perf-profile.self.cycles-pp.exit_to_user_mode_prepare 0.09 ± 29% -0.1 0.04 ± 72% perf-profile.self.cycles-pp.do_adjtimex 0.21 ± 13% -0.0 0.16 ± 10% perf-profile.self.cycles-pp.__update_load_avg_se 0.12 ± 8% -0.0 0.08 ± 22% perf-profile.self.cycles-pp.update_curr_fair 0.13 ± 20% -0.0 0.10 ± 10% perf-profile.self.cycles-pp.apparmor_capable 0.06 ± 50% +0.0 0.10 ± 16% perf-profile.self.cycles-pp.get_obj_cgroup_from_current 0.02 ±144% +0.1 0.07 ± 17% perf-profile.self.cycles-pp.do_filp_open 0.17 ± 16% +0.1 0.23 ± 12% perf-profile.self.cycles-pp.put_timespec64 0.02 ±141% +0.1 0.08 ± 27% perf-profile.self.cycles-pp.___slab_alloc 0.00 +0.1 0.07 ± 15% perf-profile.self.cycles-pp.__srcu_read_unlock 0.02 ±141% +0.1 0.09 ± 24% perf-profile.self.cycles-pp.lockref_put_or_lock 0.44 ± 9% +0.1 0.52 ± 9% perf-profile.self.cycles-pp.kmem_cache_free 0.00 +0.1 0.09 ± 21% perf-profile.self.cycles-pp.inode_init_once 0.00 +0.1 0.09 ± 21% perf-profile.self.cycles-pp.__srcu_read_lock 0.00 +0.1 0.09 ± 25% perf-profile.self.cycles-pp.up_write 0.00 +0.1 0.09 ± 21% perf-profile.self.cycles-pp.__d_lookup 0.00 +0.1 0.09 ± 26% perf-profile.self.cycles-pp.down_write 0.00 +0.1 0.09 ± 27% perf-profile.self.cycles-pp.slab_pre_alloc_hook 0.01 ±223% +0.1 0.11 ± 51% perf-profile.self.cycles-pp.mntput_no_expire 0.00 +0.1 0.11 ± 9% perf-profile.self.cycles-pp.kmem_cache_alloc_lru 0.00 +0.1 0.12 ± 12% perf-profile.self.cycles-pp.inode_init_always 0.00 +0.1 0.14 ± 5% perf-profile.self.cycles-pp.number 0.26 ± 19% +0.2 0.44 ± 18% perf-profile.self.cycles-pp.memcg_slab_post_alloc_hook 0.11 ± 29% +0.3 0.39 ± 18% perf-profile.self.cycles-pp._find_next_bit 0.58 ± 7% +0.8 1.42 ± 5% perf-profile.self.cycles-pp._raw_spin_lock 0.00 +1.1 1.14 ± 14% perf-profile.self.cycles-pp.mnt_get_count 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

2 years

2
1
0 0

[syzbot] [iommu?] divide error in iommufd_test

by syzbot

Hello, syzbot found the following issue on: HEAD commit: e8361b005d7c Add linux-next specific files for 20231023 git tree: linux-next console+strace: https://syzkaller.appspot.com/x/log.txt?x=13e4cb83680000 kernel config: https://syzkaller.appspot.com/x/.config?x=75e8fc3570ec9a74 dashboard link: https://syzkaller.appspot.com/bug?extid=25dc7383c30ecdc83c38 compiler: gcc (Debian 12.2.0-14) 12.2.0, GNU ld (GNU Binutils for Debian) 2.40 syz repro: https://syzkaller.appspot.com/x/repro.syz?x=119bad5d680000 C reproducer: https://syzkaller.appspot.com/x/repro.c?x=1062e393680000 Downloadable assets: disk image: https://storage.googleapis.com/syzbot-assets/e28a7944599e/disk-e8361b00.raw… vmlinux: https://storage.googleapis.com/syzbot-assets/7dd355dbe055/vmlinux-e8361b00.… kernel image: https://storage.googleapis.com/syzbot-assets/7b2a9050635d/bzImage-e8361b00.… The issue was bisected to: commit 5e054083ce6929b567c6aadbf8bf627b0f028353 Author: Joao Martins <joao.m.martins(a)oracle.com> Date: Fri Oct 20 22:28:02 2023 +0000 iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP bisection log: https://syzkaller.appspot.com/x/bisect.txt?x=14a49a35680000 final oops: https://syzkaller.appspot.com/x/report.txt?x=16a49a35680000 console output: https://syzkaller.appspot.com/x/log.txt?x=12a49a35680000 IMPORTANT: if you fix the issue, please add the following tag to the commit: Reported-by: syzbot+25dc7383c30ecdc83c38(a)syzkaller.appspotmail.com Fixes: 5e054083ce69 ("iommufd/selftest: Test IOMMU_HWPT_GET_DIRTY_BITMAP") divide error: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 5053 Comm: syz-executor178 Not tainted 6.6.0-rc6-next-20231023-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/06/2023 RIP: 0010:iommufd_test_dirty drivers/iommu/iommufd/selftest.c:1098 [inline] RIP: 0010:iommufd_test+0x1fd/0x35c0 drivers/iommu/iommufd/selftest.c:1203 Code: 04 02 48 89 4c 24 28 84 c0 74 09 3c 03 7f 05 e8 69 ac 2f fd 48 8b 04 24 31 d2 31 ff 48 8b 5c 24 20 44 8b 68 08 48 8b 44 24 28 <48> f7 f3 48 89 d5 48 89 d6 e8 85 cf d8 fc 48 85 ed 0f 85 ce 22 00 RSP: 0018:ffffc90003937cb0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff84affaf2 RDI: 0000000000000000 RBP: 000000000000000d R08: 0000000000000005 R09: 000000000000000d R10: 000000000000000d R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: ffffc90003937e40 R15: ffffc90003937e00 FS: 00005555560d7380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020006000 CR3: 0000000075a85000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> iommufd_fops_ioctl+0x35a/0x4e0 drivers/iommu/iommufd/main.c:404 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:871 [inline] __se_sys_ioctl fs/ioctl.c:857 [inline] __x64_sys_ioctl+0x18f/0x210 fs/ioctl.c:857 do_syscall_x64 arch/x86/entry/common.c:51 [inline] do_syscall_64+0x3f/0x110 arch/x86/entry/common.c:82 entry_SYSCALL_64_after_hwframe+0x62/0x6a RIP: 0033:0x7f5fb02172e9 Code: 48 83 c4 28 c3 e8 37 17 00 00 0f 1f 80 00 00 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffd74d26068 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007ffd74d26238 RCX: 00007f5fb02172e9 RDX: 0000000020000140 RSI: 0000000000003ba0 RDI: 0000000000000003 RBP: 00007f5fb028a610 R08: 0000000000000000 R09: 00007ffd74d26238 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000001 R13: 00007ffd74d26228 R14: 0000000000000001 R15: 0000000000000001 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:iommufd_test_dirty drivers/iommu/iommufd/selftest.c:1098 [inline] RIP: 0010:iommufd_test+0x1fd/0x35c0 drivers/iommu/iommufd/selftest.c:1203 Code: 04 02 48 89 4c 24 28 84 c0 74 09 3c 03 7f 05 e8 69 ac 2f fd 48 8b 04 24 31 d2 31 ff 48 8b 5c 24 20 44 8b 68 08 48 8b 44 24 28 <48> f7 f3 48 89 d5 48 89 d6 e8 85 cf d8 fc 48 85 ed 0f 85 ce 22 00 RSP: 0018:ffffc90003937cb0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffffffff84affaf2 RDI: 0000000000000000 RBP: 000000000000000d R08: 0000000000000005 R09: 000000000000000d R10: 000000000000000d R11: 0000000000000000 R12: 0000000000000000 R13: 0000000000000000 R14: ffffc90003937e40 R15: ffffc90003937e00 FS: 00005555560d7380(0000) GS:ffff8880b9900000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020006000 CR3: 0000000075a85000 CR4: 00000000003506f0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 ---------------- Code disassembly (best guess): 0: 04 02 add $0x2,%al 2: 48 89 4c 24 28 mov %rcx,0x28(%rsp) 7: 84 c0 test %al,%al 9: 74 09 je 0x14 b: 3c 03 cmp $0x3,%al d: 7f 05 jg 0x14 f: e8 69 ac 2f fd call 0xfd2fac7d 14: 48 8b 04 24 mov (%rsp),%rax 18: 31 d2 xor %edx,%edx 1a: 31 ff xor %edi,%edi 1c: 48 8b 5c 24 20 mov 0x20(%rsp),%rbx 21: 44 8b 68 08 mov 0x8(%rax),%r13d 25: 48 8b 44 24 28 mov 0x28(%rsp),%rax * 2a: 48 f7 f3 div %rbx <-- trapping instruction 2d: 48 89 d5 mov %rdx,%rbp 30: 48 89 d6 mov %rdx,%rsi 33: e8 85 cf d8 fc call 0xfcd8cfbd 38: 48 85 ed test %rbp,%rbp 3b: 0f .byte 0xf 3c: 85 ce test %ecx,%esi 3e: 22 00 and (%rax),%al --- This report is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at syzkaller(a)googlegroups.com. syzbot will keep track of this issue. See: https://goo.gl/tpsmEJ#status for how to communicate with syzbot. For information about bisection process see: https://goo.gl/tpsmEJ#bisection If the bug is already fixed, let syzbot know by replying with: #syz fix: exact-commit-title If you want syzbot to run the reproducer, reply with: #syz test: git://repo/address.git branch-or-commit-hash If you attach or paste a git patch, syzbot will apply it before testing. If you want to overwrite bug's subsystems, reply with: #syz set subsystems: new-subsystem (See the list of subsystem names on the web dashboard) If the bug is a duplicate of another bug, reply with: #syz dup: exact-subject-of-another-report If you want to undo deduplication, reply with: #syz undup

2 years

2
1
0 0

[RFC PATCH 0/2] Add test to verify probe of devices from discoverable busses on DT platforms

by Nícolas F. R. A. Prado

This is part of an effort to improve detection of regressions impacting device probe on all platforms. The recently merged DT kselftest [1] detects probe issues for all devices described statically in the DT. That leaves out devices discovered at run-time from discoverable busses. This is where this test comes in. All of the devices that are connected through discoverable busses (ie USB and PCI), and which are internal and therefore always present, can be described in a per-platform file so they can be checked for. The test will check that the device has been instantiated and bound to a driver. Patch 1 introduces the test. Patch 2 adds the test definitions for the google,spherion machine (Acer Chromebook 514) as an example. This is the sample output from the test running on Spherion: TAP version 13 Using board file: boards/google,spherion 1..10 ok 1 usb.camera.0.device ok 2 usb.camera.0.driver ok 3 usb.camera.1.device ok 4 usb.camera.1.driver ok 5 usb.bluetooth.0.device ok 6 usb.bluetooth.0.driver ok 7 usb.bluetooth.1.device ok 8 usb.bluetooth.1.driver ok 9 pci.wifi.device ok 10 pci.wifi.driver Totals: pass:10 fail:0 xfail:0 xpass:0 skip:0 error:0 [1] https://lore.kernel.org/all/20230828211424.2964562-1-nfraprado@collabora.co… Nícolas F. R. A. Prado (2): kselftest: Add test to verify probe of devices from discoverable busses kselftest: devices: Add board file for google,spherion tools/testing/selftests/Makefile | 1 + tools/testing/selftests/devices/.gitignore | 1 + tools/testing/selftests/devices/Makefile | 8 + .../selftests/devices/boards/google,spherion | 3 + .../devices/test_discoverable_devices.sh | 165 ++++++++++++++++++ 5 files changed, 178 insertions(+) create mode 100644 tools/testing/selftests/devices/.gitignore create mode 100644 tools/testing/selftests/devices/Makefile create mode 100644 tools/testing/selftests/devices/boards/google,spherion create mode 100755 tools/testing/selftests/devices/test_discoverable_devices.sh -- 2.42.0

2 years

2
6
0 0

[PATCH] selftests:proc ProtectionKey check in smpas test

by Swarup Laxman Kotiaklapudi

Check ProtectionKey field in /proc/*/smaps output, if system supports page-based memory permissions. Signed-off-by: Swarup Laxman Kotiaklapudi <swarupkotikalapudi(a)gmail.com> --- tools/testing/selftests/proc/proc-empty-vm.c | 38 ++++++++++++-------- 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/tools/testing/selftests/proc/proc-empty-vm.c b/tools/testing/selftests/proc/proc-empty-vm.c index b16c13688b88..4842f923235c 100644 --- a/tools/testing/selftests/proc/proc-empty-vm.c +++ b/tools/testing/selftests/proc/proc-empty-vm.c @@ -37,6 +37,7 @@ #include <sys/types.h> #include <sys/wait.h> #include <unistd.h> +#include "../kselftest.h" #ifdef __amd64__ #define TEST_VSYSCALL @@ -83,10 +84,7 @@ static const char proc_pid_smaps_vsyscall_1[] = "SwapPss: 0 kB\n" "Locked: 0 kB\n" "THPeligible: 0\n" -/* - * "ProtectionKey:" field is conditional. It is possible to check it as well, - * but I don't have such machine. - */ +"ProtectionKey: 0\n" ; static const char proc_pid_smaps_vsyscall_2[] = @@ -113,10 +111,7 @@ static const char proc_pid_smaps_vsyscall_2[] = "SwapPss: 0 kB\n" "Locked: 0 kB\n" "THPeligible: 0\n" -/* - * "ProtectionKey:" field is conditional. It is possible to check it as well, - * but I'm too tired. - */ +"ProtectionKey: 0\n" ; static void sigaction_SIGSEGV(int _, siginfo_t *__, void *___) @@ -241,13 +236,26 @@ static int test_proc_pid_smaps(pid_t pid) } else { ssize_t rv = read(fd, buf, sizeof(buf)); close(fd); - if (g_vsyscall == 0) { - assert(rv == 0); - } else { - size_t len = strlen(g_proc_pid_maps_vsyscall); - /* TODO "ProtectionKey:" */ - assert(rv > len); - assert(memcmp(buf, g_proc_pid_maps_vsyscall, len) == 0); + assert(rv >= 0); + assert(rv <= sizeof(buf)); + if (g_vsyscall != 0) { + int pkey = pkey_alloc(0, 0); + + if (pkey < 0) { + size_t len = strlen(g_proc_pid_maps_vsyscall); + + assert(rv > len); + assert(memcmp(buf, g_proc_pid_maps_vsyscall, len) == 0); + } else { + pkey_free(pkey); + static const char * const S[] = { + "ProtectionKey: 0\n" + }; + int i; + + for (i = 0; i < ARRAY_SIZE(S); i++) + assert(memmem(buf, rv, S[i], strlen(S[i]))); + } } return EXIT_SUCCESS; } -- 2.34.1

2 years

2
1
0 0

[PATCH][next] selftests: sched: Fix spelling mistake "hiearchy" -> "hierarchy"

by Colin Ian King

There is a spelling mistake in a printf message. Fix it. Signed-off-by: Colin Ian King <colin.i.king(a)gmail.com> --- tools/testing/selftests/sched/cs_prctl_test.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/testing/selftests/sched/cs_prctl_test.c b/tools/testing/selftests/sched/cs_prctl_test.c index 3e1619b6bf2d..7b4fc02a0d05 100644 --- a/tools/testing/selftests/sched/cs_prctl_test.c +++ b/tools/testing/selftests/sched/cs_prctl_test.c @@ -276,7 +276,7 @@ int main(int argc, char *argv[]) if (setpgid(0, 0) != 0) handle_error("process group"); - printf("\n## Create a thread/process/process group hiearchy\n"); + printf("\n## Create a thread/process/process group hierarchy\n"); create_processes(num_processes, num_threads, procs); need_cleanup = 1; disp_processes(num_processes, procs); -- 2.39.2

2 years

1
0
0 0

[PATCH bpf-next 0/2] bpf: Fix incorrect immediate spill

by Hao Sun

Immediate is incorrectly cast to u32 before being spilled, losing sign information. The range information is incorrect after load again. Fix immediate spill by remove the cast. The second patch add a test case for this. Signed-off-by: Hao Sun <sunhao.th(a)gmail.com> --- Hao Sun (2): bpf: Fix check_stack_write_fixed_off() to correctly spill imm selftests/bpf: Add test for immediate spilled to stack kernel/bpf/verifier.c | 2 +- tools/testing/selftests/bpf/verifier/bpf_st_mem.c | 32 +++++++++++++++++++++++ 2 files changed, 33 insertions(+), 1 deletion(-) --- base-commit: 399f6185a1c02f39bcadb8749bc2d9d48685816f change-id: 20231026-fix-check-stack-write-c40996694dfa Best regards, -- Hao Sun <sunhao.th(a)gmail.com>

2 years

3
7
0 0

[PATCH bpf-next v2 1/2] selftests/bpf: Convert CHECK macros to ASSERT_* macros in bpf_iter

by Yuran Pereira

As it was pointed out by Yonghong Song [1], in the bpf selftests the use of the ASSERT_* series of macros is preferred over the CHECK macro. This patch replaces all CHECK calls in bpf_iter with the appropriate ASSERT_* macros. [1] https://lore.kernel.org/lkml/0a142924-633c-44e6-9a92-2dc019656bf2@linux.dev Suggested-by: Yonghong Song <yonghong.song(a)linux.dev> Signed-off-by: Yuran Pereira <yuran.pereira(a)hotmail.com> --- .../selftests/bpf/prog_tests/bpf_iter.c | 82 +++++++++---------- 1 file changed, 39 insertions(+), 43 deletions(-) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 1f02168103dd..7db6972ed952 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -34,8 +34,6 @@ #include "bpf_iter_ksym.skel.h" #include "bpf_iter_sockmap.skel.h" -static int duration; - static void test_btf_id_or_null(void) { struct bpf_iter_test_kern3 *skel; @@ -64,7 +62,7 @@ static void do_dummy_read_opts(struct bpf_program *prog, struct bpf_iter_attach_ /* not check contents, but ensure read() ends without error */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - CHECK(len < 0, "read", "read failed: %s\n", strerror(errno)); + ASSERT_GE(len, 0, "read"); close(iter_fd); @@ -413,7 +411,7 @@ static int do_btf_read(struct bpf_iter_task_btf *skel) goto free_link; } - if (CHECK(err < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(err, 0, "read")) goto free_link; ASSERT_HAS_SUBSTR(taskbuf, "(struct task_struct)", @@ -526,11 +524,11 @@ static int do_read_with_fd(int iter_fd, const char *expected, start = 0; while ((len = read(iter_fd, buf + start, read_buf_len)) > 0) { start += len; - if (CHECK(start >= 16, "read", "read len %d\n", len)) + if (!ASSERT_LT(start, 16, "read")) return -1; read_buf_len = read_one_char ? 1 : 16 - start; } - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) return -1; if (!ASSERT_STREQ(buf, expected, "read")) @@ -571,8 +569,7 @@ static int do_read(const char *path, const char *expected) int err, iter_fd; iter_fd = open(path, O_RDONLY); - if (CHECK(iter_fd < 0, "open", "open %s failed: %s\n", - path, strerror(errno))) + if (!ASSERT_GE(iter_fd, 0, "open")) return -1; err = do_read_with_fd(iter_fd, expected, false); @@ -600,7 +597,7 @@ static void test_file_iter(void) unlink(path); err = bpf_link__pin(link, path); - if (CHECK(err, "pin_iter", "pin_iter to %s failed: %d\n", path, err)) + if (!ASSERT_OK(err, "pin_iter")) goto free_link; err = do_read(path, "abcd"); @@ -651,12 +648,10 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) * overflow and needs restart. */ map1_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); - if (CHECK(map1_fd < 0, "bpf_map_create", - "map_creation failed: %s\n", strerror(errno))) + if (!ASSERT_GE(map1_fd, 0, "bpf_map_create")) goto out; map2_fd = bpf_map_create(BPF_MAP_TYPE_ARRAY, NULL, 4, 8, 1, NULL); - if (CHECK(map2_fd < 0, "bpf_map_create", - "map_creation failed: %s\n", strerror(errno))) + if (!ASSERT_GE(map2_fd, 0, "bpf_map_create")) goto free_map1; /* bpf_seq_printf kernel buffer is 8 pages, so one map @@ -685,14 +680,12 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) /* setup filtering map_id in bpf program */ map_info_len = sizeof(map_info); err = bpf_map_get_info_by_fd(map1_fd, &map_info, &map_info_len); - if (CHECK(err, "get_map_info", "get map info failed: %s\n", - strerror(errno))) + if (!ASSERT_OK(err, "get_map_info")) goto free_map2; skel->bss->map1_id = map_info.id; err = bpf_map_get_info_by_fd(map2_fd, &map_info, &map_info_len); - if (CHECK(err, "get_map_info", "get map info failed: %s\n", - strerror(errno))) + if (!ASSERT_OK(err, "get_map_info")) goto free_map2; skel->bss->map2_id = map_info.id; @@ -714,16 +707,15 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) while ((len = read(iter_fd, buf, expected_read_len)) > 0) total_read_len += len; - CHECK(len != -1 || errno != E2BIG, "read", - "expected ret -1, errno E2BIG, but get ret %d, error %s\n", - len, strerror(errno)); + if (!ASSERT_EQ(len, -1, "read")) + goto free_buf; + ASSERT_EQ(errno, E2BIG, "read"); goto free_buf; } else if (!ret1) { while ((len = read(iter_fd, buf, expected_read_len)) > 0) total_read_len += len; - if (CHECK(len < 0, "read", "read failed: %s\n", - strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto free_buf; } else { do { @@ -732,8 +724,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) total_read_len += len; } while (len > 0 || len == -EAGAIN); - if (CHECK(len < 0, "read", "read failed: %s\n", - strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto free_buf; } @@ -836,7 +827,7 @@ static void test_bpf_hash_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -917,7 +908,7 @@ static void test_bpf_percpu_hash_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -983,17 +974,15 @@ static void test_bpf_array_map(void) start = 0; while ((len = read(iter_fd, buf + start, sizeof(buf) - start)) > 0) start += len; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ res_first_key = *(__u32 *)buf; res_first_val = *(__u64 *)(buf + sizeof(__u32)); - if (CHECK(res_first_key != 0 || res_first_val != first_val, - "bpf_seq_write", - "seq_write failure: first key %u vs expected 0, " - " first value %llu vs expected %llu\n", - res_first_key, res_first_val, first_val)) + if (!ASSERT_EQ(res_first_key, 0, "bpf_seq_write")) + goto close_iter; + else if (!ASSERT_EQ(res_first_val, first_val, "bpf_seq_write")) goto close_iter; if (!ASSERT_EQ(skel->bss->key_sum, expected_key, "key_sum")) @@ -1092,7 +1081,7 @@ static void test_bpf_percpu_array_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ @@ -1131,6 +1120,7 @@ static void test_bpf_sk_storage_delete(void) sock_fd = socket(AF_INET6, SOCK_STREAM, 0); if (!ASSERT_GE(sock_fd, 0, "socket")) goto out; + err = bpf_map_update_elem(map_fd, &sock_fd, &val, BPF_NOEXIST); if (!ASSERT_OK(err, "map_update")) goto out; @@ -1151,14 +1141,20 @@ static void test_bpf_sk_storage_delete(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - if (CHECK(!err || errno != ENOENT, "bpf_map_lookup_elem", - "map value wasn't deleted (err=%d, errno=%d)\n", err, errno)) + + /* Note: The following assertions serve to ensure + * the value was deleted. It does so by asserting + * that bpf_map_lookup_elem has failed. This might + * seem counterintuitivei at first. + */ + if (!ASSERT_ERR(err, "bpf_map_lookup_elem")) goto close_iter; + ASSERT_EQ(errno, ENOENT, "bpf_map_lookup_elem"); close_iter: close(iter_fd); @@ -1203,17 +1199,17 @@ static void test_bpf_sk_storage_get(void) do_dummy_read(skel->progs.fill_socket_owner); err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - if (CHECK(err || val != getpid(), "bpf_map_lookup_elem", - "map value wasn't set correctly (expected %d, got %d, err=%d)\n", - getpid(), val, err)) + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto close_socket; + else if (!ASSERT_EQ(val, getpid(), "bpf_map_lookup_elem")) goto close_socket; do_dummy_read(skel->progs.negate_socket_local_storage); err = bpf_map_lookup_elem(map_fd, &sock_fd, &val); - CHECK(err || val != -getpid(), "bpf_map_lookup_elem", - "map value wasn't set correctly (expected %d, got %d, err=%d)\n", - -getpid(), val, err); + if (!ASSERT_OK(err, "bpf_map_lookup_elem")) + goto close_socket; + ASSERT_EQ(val, -getpid(), "bpf_map_lookup_elem"); close_socket: close(sock_fd); @@ -1290,7 +1286,7 @@ static void test_bpf_sk_storage_map(void) /* do some tests */ while ((len = read(iter_fd, buf, sizeof(buf))) > 0) ; - if (CHECK(len < 0, "read", "read failed: %s\n", strerror(errno))) + if (!ASSERT_GE(len, 0, "read")) goto close_iter; /* test results */ -- 2.25.1

2 years

3
2
0 0

[PATCH bpf-next v2 2/2] selftests/bpf: Add malloc failure checks in bpf_iter

by Yuran Pereira

Since some malloc calls in bpf_iter may at times fail, this patch adds the appropriate fail checks, and ensures that any previously allocated resource is appropriately destroyed before returning the function. Signed-off-by: Yuran Pereira <yuran.pereira(a)hotmail.com> --- tools/testing/selftests/bpf/prog_tests/bpf_iter.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c index 7db6972ed952..955d374ba656 100644 --- a/tools/testing/selftests/bpf/prog_tests/bpf_iter.c +++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter.c @@ -698,7 +698,7 @@ static void test_overflow(bool test_e2big_overflow, bool ret1) goto free_link; buf = malloc(expected_read_len); - if (!buf) + if (!ASSERT_OK_PTR(buf, "malloc")) goto close_iter; /* do read */ @@ -869,6 +869,8 @@ static void test_bpf_percpu_hash_map(void) skel->rodata->num_cpus = bpf_num_possible_cpus(); val = malloc(8 * bpf_num_possible_cpus()); + if (!ASSERT_OK_PTR(val, "malloc")) + goto out; err = bpf_iter_bpf_percpu_hash_map__load(skel); if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_hash_map__load")) @@ -1046,6 +1048,8 @@ static void test_bpf_percpu_array_map(void) skel->rodata->num_cpus = bpf_num_possible_cpus(); val = malloc(8 * bpf_num_possible_cpus()); + if (!ASSERT_OK_PTR(val, "malloc")) + goto out; err = bpf_iter_bpf_percpu_array_map__load(skel); if (!ASSERT_OK_PTR(skel, "bpf_iter_bpf_percpu_array_map__load")) -- 2.25.1

2 years

3
2
0 0

[PATCH v3] kunit: Warn if tests are slow

by Maxime Ripard

Kunit recently gained support to setup attributes, the first one being the speed of a given test, then allowing to filter out slow tests. A slow test is defined in the documentation as taking more than one second. There's an another speed attribute called "super slow" but whose definition is less clear. Add support to the test runner to check the test execution time, and report tests that should be marked as slow but aren't. Signed-off-by: Maxime Ripard <mripard(a)kernel.org> --- To: Brendan Higgins <brendan.higgins(a)linux.dev> To: David Gow <davidgow(a)google.com> Cc: Jani Nikula <jani.nikula(a)linux.intel.com> Cc: Rae Moar <rmoar(a)google.com> Cc: linux-kselftest(a)vger.kernel.org Cc: kunit-dev(a)googlegroups.com Cc: linux-kernel(a)vger.kernel.org Changes from v2: - Add defines and comments to make the warning reporting threshold more obvious - Switch the duration comparisons to timespec64_compare to be more accurate - Link: https://lore.kernel.org/all/20230920084903.1522728-1-mripard@kernel.org/ Changes from v1: - Split the patch out of the series - Change to trigger the warning only if the runtime is twice the threshold (Jani, Rae) - Split the speed check into a separate function (Rae) - Link: https://lore.kernel.org/all/20230911-kms-slow-tests-v1-0-d3800a69a1a1@kerne… --- lib/kunit/test.c | 38 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) diff --git a/lib/kunit/test.c b/lib/kunit/test.c index 49698a168437..4b710c92340a 100644 --- a/lib/kunit/test.c +++ b/lib/kunit/test.c @@ -372,6 +372,36 @@ void kunit_init_test(struct kunit *test, const char *name, char *log) } EXPORT_SYMBOL_GPL(kunit_init_test); +/* Only warn when a test takes more than twice the threshold */ +#define KUNIT_SPEED_WARNING_MULTIPLIER 2 + +/* Slow tests are defined as taking more than 1s */ +#define KUNIT_SPEED_SLOW_THRESHOLD_S 1 + +#define KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S \ + (KUNIT_SPEED_WARNING_MULTIPLIER * KUNIT_SPEED_SLOW_THRESHOLD_S) + +#define s_to_timespec64(s) ns_to_timespec64((s) * NSEC_PER_SEC) + +static void kunit_run_case_check_speed(struct kunit *test, + struct kunit_case *test_case, + struct timespec64 duration) +{ + struct timespec64 slow_thr = + s_to_timespec64(KUNIT_SPEED_SLOW_WARNING_THRESHOLD_S); + enum kunit_speed speed = test_case->attr.speed; + + if (timespec64_compare(&duration, &slow_thr) < 0) + return; + + if (speed == KUNIT_SPEED_VERY_SLOW || speed == KUNIT_SPEED_SLOW) + return; + + kunit_warn(test, + "Test should be marked slow (runtime: %lld.%09lds)", + duration.tv_sec, duration.tv_nsec); +} + /* * Initializes and runs test case. Does not clean up or do post validations. */ @@ -379,6 +409,8 @@ static void kunit_run_case_internal(struct kunit *test, struct kunit_suite *suite, struct kunit_case *test_case) { + struct timespec64 start, end; + if (suite->init) { int ret; @@ -390,7 +422,13 @@ static void kunit_run_case_internal(struct kunit *test, } } + ktime_get_ts64(&start); + test_case->run_case(test); + + ktime_get_ts64(&end); + + kunit_run_case_check_speed(test, test_case, timespec64_sub(end, start)); } static void kunit_case_internal_cleanup(struct kunit *test) -- 2.41.0

2 years

2
1
0 0

[PATCH v8 0/8] Add Intel VT-d nested translation (part 1/2)

by Yi Liu

This is the first part to add Intel VT-d nested translation based on IOMMUFD nesting infrastructure. As the iommufd nesting infrastructure series[1], iommu core supports new ops to allocate domains with user data. For nesting, the user data is vendor-specific, IOMMU_HWPT_DATA_VTD_S1 is defined for the Intel VT-d stage-1 page table, it will be used in the stage-1 domain allocation path. struct iommu_hwpt_vtd_s1 is defined to pass user_data for the Intel VT-d stage-1 domain allocation. This series does not have the cache invalidation path, it would be added in part 2/2. The first Intel platform supporting nested translation is Sapphire Rapids which, unfortunately, has a hardware errata [2] requiring special treatment. This errata happens when a stage-1 page table page (either level) is located in a stage-2 read-only region. In that case the IOMMU hardware may ignore the stage-2 RO permission and still set the A/D bit in stage-1 page table entries during page table walking. A flag IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17 is introduced to report this errata to userspace. With that restriction the user should either disable nested translation to favor RO stage-2 mappings or ensure no RO stage-2 mapping to enable nested translation. Intel-iommu driver is armed with necessary checks to prevent such mix in patch8 of this series. Qemu currently does add RO mappings though. The vfio agent in Qemu simply maps all valid regions in the GPA address space which certainly includes RO regions e.g. vbios. In reality we don't know a usage relying on DMA reads from the BIOS region. Hence finding a way to skip RO regions (e.g. via a discard manager) in Qemu might be an acceptable tradeoff. The actual change needs more discussion in Qemu community. For now we just hacked Qemu to test. Complete code can be found in [3], corresponding QEMU could can be found in [4]. [1] https://lore.kernel.org/linux-iommu/20231026043938.63898-1-yi.l.liu@intel.c… [2] https://www.intel.com/content/www/us/en/content-details/772415/content-deta… [3] https://github.com/yiliu1765/iommufd/tree/iommufd_nesting [4] https://github.com/yiliu1765/qemu/tree/zhenzhong/wip/iommufd_nesting_rfcv1 Change log: v8: - Adopt changes suggested by Jason on domain_alloc_user() op https://lore.kernel.org/linux-iommu/20231024230319.GW3952@nvidia.com/ - Add Kevin's r-b on patch 06 - Fix description for IOMMU_HW_INFO_VTD_ERRATA_772415_SPR17 (Kevin) v7: https://lore.kernel.org/linux-iommu/20231024151412.50046-1-yi.l.liu@intel.c… - Rebase on top of latest iommufd nesting part 1/2 - Add the nested_parent flag in patch 07 and sanitize it for nested domain allocation (Baolu) - Fail the nested domain allocation if dirty tracking flag is set v6: https://lore.kernel.org/linux-iommu/20231020093246.17015-1-yi.l.liu@intel.c… - Add Kevin's r-b for patch 1 and 8 - Drop Kevin's r-b for patch 7 - Address comments from Kevin - Split the VT-d nesting series into two parts 1/2 and 2/2 v5: https://lore.kernel.org/linux-iommu/20230921075431.125239-1-yi.l.liu@intel.… - Add Kevin's r-b for patch 2, 3 ,5 8, 10 - Drop enforce_cache_coherency callback from the nested type domain ops (Kevin) - Remove duplicate agaw check in patch 04 (Kevin) - Remove duplicate domain_update_iommu_cap() in patch 06 (Kevin) - Check parent's force_snooping to set pgsnp in the pasid entry (Kevin) - uapi data structure check (Kevin) - Simplify the errata handling as user can allocate nested parent domain v4: https://lore.kernel.org/linux-iommu/20230724111335.107427-1-yi.l.liu@intel.… - Remove ascii art tables (Jason) - Drop EMT (Tina, Jason) - Drop MTS and related definitions (Kevin) - Rename macro IOMMU_VTD_PGTBL_ to IOMMU_VTD_S1_ (Kevin) - Rename struct iommu_hwpt_intel_vtd_ to iommu_hwpt_vtd_ (Kevin) - Rename struct iommu_hwpt_intel_vtd to iommu_hwpt_vtd_s1 (Kevin) - Put the vendor specific hwpt alloc data structure before enuma iommu_hwpt_type (Kevin) - Do not trim the higher page levels of S2 domain in nested domain attachment as the S2 domain may have been used independently. (Kevin) - Remove the first-stage pgd check against the maximum address of s2_domain as hw can check it anyhow. It makes sense to check every pfns used in the stage-1 page table. But it cannot make it. So just leave it to hw. (Kevin) - Split the iotlb flush part into an order of uapi, helper and callback implementation (Kevin) - Change the policy of VT-d nesting errata, disallow RO mapping once a domain is used as parent domain of a nested domain. This removes the nested_users counting. (Kevin) - Minor fix for "make htmldocs" v3: https://lore.kernel.org/linux-iommu/20230511145110.27707-1-yi.l.liu@intel.c… - Further split the patches into an order of adding helpers for nested domain, iotlb flush, nested domain attachment and nested domain allocation callback, then report the hw_info to userspace. - Add batch support in cache invalidation from userspace - Disallow nested translation usage if RO mappings exists in stage-2 domain due to errata on readonly mappings on Sapphire Rapids platform. v2: https://lore.kernel.org/linux-iommu/20230309082207.612346-1-yi.l.liu@intel.… - The iommufd infrastructure is split to be separate series. v1: https://lore.kernel.org/linux-iommu/20230209043153.14964-1-yi.l.liu@intel.c… Regards, Yi Liu Lu Baolu (5): iommu/vt-d: Extend dmar_domain to support nested domain iommu/vt-d: Add helper for nested domain allocation iommu/vt-d: Add helper to setup pasid nested translation iommu/vt-d: Add nested domain allocation iommu/vt-d: Disallow read-only mappings to nest parent domain Yi Liu (3): iommufd: Add data structure for Intel VT-d stage-1 domain allocation iommu/vt-d: Make domain attach helpers to be extern iommu/vt-d: Set the nested domain to a device drivers/iommu/intel/Makefile | 2 +- drivers/iommu/intel/iommu.c | 60 +++++++++--------- drivers/iommu/intel/iommu.h | 46 ++++++++++++-- drivers/iommu/intel/nested.c | 117 +++++++++++++++++++++++++++++++++++ drivers/iommu/intel/pasid.c | 112 +++++++++++++++++++++++++++++++++ drivers/iommu/intel/pasid.h | 2 + include/uapi/linux/iommufd.h | 42 ++++++++++++- 7 files changed, 345 insertions(+), 36 deletions(-) create mode 100644 drivers/iommu/intel/nested.c -- 2.34.1

2 years

3
11
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-kselftest-mirror