When executing the commands below, sometimes the system panics: stress -c 1 -t 10 & pmcstat -t stress -p mem_load_retired.l2_miss sleep 3 panic: [pmc,2749] (ri17, rc1) waiting too long for pmc to be free cpuid = 2 time = 1597858367 KDB: stack backtrace: db_trace_self_wrapper() at db_trace_self_wrapper+0x2b/frame 0xfffffe005fc9a760 vpanic() at vpanic+0x182/frame 0xfffffe005fc9a7b0 panic() at panic+0x43/frame 0xfffffe005fc9a810 pmc_wait_for_pmc_idle() at pmc_wait_for_pmc_idle+0xa2/frame 0xfffffe005fc9a840 pmc_release_pmc_descriptor() at pmc_release_pmc_descriptor+0x204/frame 0xfffffe0 pmc_syscall_handler() at pmc_syscall_handler+0x4be/frame 0xfffffe005fc9a9d0 amd64_syscall() at amd64_syscall+0x140/frame 0xfffffe005fc9aaf0 fast_syscall_common() at fast_syscall_common+0xf8/frame 0xfffffe005fc9aaf0 --- syscall (0, FreeBSD ELF64, nosys), rip = 0x800a8a96a, rsp = 0x7fffffffe368,- KDB: enter: panic [ thread pid 1852 tid 100126 ] Stopped at kdb_enter+0x37: movq $0,0x10bc706(%rip) db> I'm running -CURRENT on an amd64 VM (qemu with kvm). I've performed several different tests with pmcstat and stress and got no panics.