simple_udelay_calibration() relies on x86_platform's calibration ops. For KVM these ops are set late in setup_arch() and so simple_udelay_calibration() ends up using native version.
Besides being possibly incorrect, this significantly increases kernel boot time. For example, on my laptop executing start_kernel() by a guest takes ~10 times more than when KVM's ops are used. Signed-off-by: Boris Ostrovsky <[email protected]> --- Alternatively, we could start calling simple_udelay_calibration() only on bare metal: My understanding is that the only reason it exists is to help with USB3 earlyprink driver, which I don't think is useful to guests anyway. arch/x86/kernel/setup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f81823695014..749439fba076 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1039,8 +1039,6 @@ void __init setup_arch(char **cmdline_p) */ init_hypervisor_platform(); - simple_udelay_calibration(); - x86_init.resources.probe_roms(); /* after parse_early_param, so could debug it */ @@ -1221,6 +1219,8 @@ void __init setup_arch(char **cmdline_p) kvmclock_init(); #endif + simple_udelay_calibration(); + x86_init.paging.pagetable_init(); kasan_init(); -- 2.11.0
