From 4be1b29795d692d512bb67b770665d6f8ea5cb0b Mon Sep 17 00:00:00 2001 From: Cyril Bur Date: Thu, 12 Feb 2015 15:01:28 -0800 Subject: powerpc: add running_clock for powerpc to prevent spurious softlockup warnings On POWER8 virtualised kernels the VTB register can be read to have a view of time that only increases while the guest is running. This will prevent guests from seeing time jump if a guest is paused for significant amounts of time. On POWER7 and below virtualised kernels stolen time is subtracted from local_clock as a best effort approximation. This will not eliminate spurious warnings in the case of a suspended guest but may reduce the occurance in the case of softlockups due to host over commit. Bare metal kernels should avoid reading the VTB as KVM does not restore sane values when not executing, the approxmation is fine as host kernels won't observe any stolen time. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Cyril Bur Cc: Michael Ellerman Cc: Andrew Jones Acked-by: Don Zickus Cc: Ingo Molnar Cc: Ulrich Obergfell Cc: chai wen Cc: Fabian Frederick Cc: Aaron Tomlin Cc: Ben Zhang Cc: Martin Schwidefsky Cc: John Stultz Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/kernel/time.c | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) (limited to 'arch/powerpc') diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c index fa7c4f12104f..7316dd15278a 100644 --- a/arch/powerpc/kernel/time.c +++ b/arch/powerpc/kernel/time.c @@ -621,6 +621,38 @@ unsigned long long sched_clock(void) return mulhdu(get_tb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; } + +#ifdef CONFIG_PPC_PSERIES + +/* + * Running clock - attempts to give a view of time passing for a virtualised + * kernels. + * Uses the VTB register if available otherwise a next best guess. + */ +unsigned long long running_clock(void) +{ + /* + * Don't read the VTB as a host since KVM does not switch in host + * timebase into the VTB when it takes a guest off the CPU, reading the + * VTB would result in reading 'last switched out' guest VTB. + * + * Host kernels are often compiled with CONFIG_PPC_PSERIES checked, it + * would be unsafe to rely only on the #ifdef above. + */ + if (firmware_has_feature(FW_FEATURE_LPAR) && + cpu_has_feature(CPU_FTR_ARCH_207S)) + return mulhdu(get_vtb() - boot_tb, tb_to_ns_scale) << tb_to_ns_shift; + + /* + * This is a next best approximation without a VTB. + * On a host which is running bare metal there should never be any stolen + * time and on a host which doesn't do any virtualisation TB *should* equal + * VTB so it makes no difference anyway. + */ + return local_clock() - cputime_to_nsecs(kcpustat_this_cpu->cpustat[CPUTIME_STEAL]); +} +#endif + static int __init get_freq(char *name, int cells, unsigned long *val) { struct device_node *cpu; -- cgit v1.2.3