On 08/25/2014 02:32 PM, Paolo Bonzini wrote: >> Ok I see now where this patch doesn't make sense. >> With the latest kvm tree I get: >> >> sudo ./x86-run x86/pmu.flat -smp 1 -cpu host | grep -v PASS >> >> >> qemu-system-x86_64 -enable-kvm -device pc-testdev -device >> isa-debug-exit,iobase=0xf4,iosize=0x4 -display none -serial stdio >> -device pci-testdev -kernel x86/pmu.flat -smp 1 -cpu host >> enabling apic >> paging enabled >> cr0 = 80010011 >> cr3 = 7fff000 >> cr4 = 20 >> PMU version: 2 >> GP counters: 4 >> GP counter width: 48 >> Mask length: 7 >> Fixed counters: 3 >> Fixed counter width: 48 >> FAIL: all counters >> >> SUMMARY: 67 tests, 1 unexpected failures >> Return value from qemu: 3 >> >> I've tested this on a few Intel platforms (sandybridge/haswell), I'll >> look into the code more then. > > > Are you using the NMI watchdog in the host? It eats one PMU counter > and makes this test fail. > > Paolo > Ah, I didn't know that. Yes disabling NMI watchdog via: echo 0 | sudo tee /proc/sys/kernel/nmi_watchdog Allows this test to pass. Would it make sense to have a check if nmi_watchdog is enabled in this test case, and skip the all counters test? --chris j arges -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html