diff options
| author | Roman Kagan <rkagan@virtuozzo.com> | 2017-07-14 16:13:20 +0200 |
|---|---|---|
| committer | Radim Krčmář <rkrcmar@redhat.com> | 2017-07-14 16:28:18 +0200 |
| commit | d3457c877b14aaee8c52923eedf05a3b78af0476 (patch) | |
| tree | 619e33c612f455e8b15d22ce0eee536d657e50f3 /Documentation/virtual | |
| parent | KVM: async_pf: Let guest support delivery of async_pf from guest mode (diff) | |
| download | linux-d3457c877b14aaee8c52923eedf05a3b78af0476.tar.xz linux-d3457c877b14aaee8c52923eedf05a3b78af0476.zip | |
kvm: x86: hyperv: make VP_INDEX managed by userspace
Hyper-V identifies vCPUs by Virtual Processor Index, which can be
queried via HV_X64_MSR_VP_INDEX msr. It is defined by the spec as a
sequential number which can't exceed the maximum number of vCPUs per VM.
APIC ids can be sparse and thus aren't a valid replacement for VP
indices.
Current KVM uses its internal vcpu index as VP_INDEX. However, to make
it predictable and persistent across VM migrations, the userspace has to
control the value of VP_INDEX.
This patch achieves that, by storing vp_index explicitly on vcpu, and
allowing HV_X64_MSR_VP_INDEX to be set from the host side. For
compatibility it's initialized to KVM vcpu index. Also a few variables
are renamed to make clear distinction betweed this Hyper-V vp_index and
KVM vcpu_id (== APIC id). Besides, a new capability,
KVM_CAP_HYPERV_VP_INDEX, is added to allow the userspace to skip
attempting msr writes where unsupported, to avoid spamming error logs.
Signed-off-by: Roman Kagan <rkagan@virtuozzo.com>
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
Diffstat (limited to 'Documentation/virtual')
| -rw-r--r-- | Documentation/virtual/kvm/api.txt | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/Documentation/virtual/kvm/api.txt b/Documentation/virtual/kvm/api.txt index 78ac577c9378..e63a35fafef0 100644 --- a/Documentation/virtual/kvm/api.txt +++ b/Documentation/virtual/kvm/api.txt @@ -4338,3 +4338,12 @@ This capability enables a newer version of Hyper-V Synthetic interrupt controller (SynIC). The only difference with KVM_CAP_HYPERV_SYNIC is that KVM doesn't clear SynIC message and event flags pages when they are enabled by writing to the respective MSRs. + +8.12 KVM_CAP_HYPERV_VP_INDEX + +Architectures: x86 + +This capability indicates that userspace can load HV_X64_MSR_VP_INDEX msr. Its +value is used to denote the target vcpu for a SynIC interrupt. For +compatibilty, KVM initializes this msr to KVM's internal vcpu index. When this +capability is absent, userspace can still query this msr's value. |