KVM: x86/pmu: Update AMD PMC sample period to fix guest NMI-watchdog
authorLike Xu <likexu@tencent.com>
Sat, 9 Apr 2022 01:52:26 +0000 (09:52 +0800)
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>
Wed, 27 Apr 2022 12:39:00 +0000 (14:39 +0200)
commit2b4417acd3c6ea3ed58d44ef4fed15b239a45f75
treeb33733ac2229dd2b469864ec911ad03071055ff5
parent87d95ff0ca27d39a1595964aa8317e9a962e3588
KVM: x86/pmu: Update AMD PMC sample period to fix guest NMI-watchdog

commit 75189d1de1b377e580ebd2d2c55914631eac9c64 upstream.

NMI-watchdog is one of the favorite features of kernel developers,
but it does not work in AMD guest even with vPMU enabled and worse,
the system misrepresents this capability via /proc.

This is a PMC emulation error. KVM does not pass the latest valid
value to perf_event in time when guest NMI-watchdog is running, thus
the perf_event corresponding to the watchdog counter will enter the
old state at some point after the first guest NMI injection, forcing
the hardware register PMC0 to be constantly written to 0x800000000001.

Meanwhile, the running counter should accurately reflect its new value
based on the latest coordinated pmc->counter (from vPMC's point of view)
rather than the value written directly by the guest.

Fixes: 168d918f2643 ("KVM: x86: Adjust counter sample period after a wrmsr")
Reported-by: Dongli Cao <caodongli@kingsoft.com>
Signed-off-by: Like Xu <likexu@tencent.com>
Reviewed-by: Yanan Wang <wangyanan55@huawei.com>
Tested-by: Yanan Wang <wangyanan55@huawei.com>
Reviewed-by: Jim Mattson <jmattson@google.com>
Message-Id: <20220409015226.38619-1-likexu@tencent.com>
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
arch/x86/kvm/pmu.h
arch/x86/kvm/svm/pmu.c
arch/x86/kvm/vmx/pmu_intel.c