KVM: x86/pmu: Load/save GLOBAL_CTRL via entry/exit fields for mediated PMU

KVM: x86/pmu: Load/save GLOBAL_CTRL via entry/exit fields for mediated PMU

When running a guest with a mediated PMU, context switch PERF_GLOBAL_CTRL
via the dedicated VMCS fields for both host and guest.  For the host,
always zero GLOBAL_CTRL on exit as the guest's state will still be loaded
in hardware (KVM will context switch the bulk of PMU state outside of the
inner run loop).  For the guest, use the dedicated fields to atomically
load and save PERF_GLOBAL_CTRL on all entry/exits.

For now, require VM_EXIT_SAVE_IA32_PERF_GLOBAL_CTRL support (introduced by
Sapphire Rapids).  KVM can support such CPUs by saving PERF_GLOBAL_CTRL
via the MSR save list, a.k.a. the MSR auto-store list, but defer that
support as it adds a small amount of complexity and is somewhat unique.

To minimize VM-Entry latency, propagate IA32_PERF_GLOBAL_CTRL to the VMCS
on-demand.  But to minimize complexity, read IA32_PERF_GLOBAL_CTRL out of
the VMCS on all non-failing VM-Exits.  I.e. partially cache the MSR.
KVM could track GLOBAL_CTRL as an EXREG and defer all reads, but writes
are rare, i.e. the dirty tracking for an EXREG is unnecessary, and it's
not obvious that shaving ~15-20 cycles per exit is meaningful given the
total overhead associated with mediated PMU context switches.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Dapeng Mi <dapeng1.mi@linux.intel.com>
Co-developed-by: Mingwei Zhang <mizhang@google.com>
Signed-off-by: Mingwei Zhang <mizhang@google.com>
Tested-by: Xudong Hao <xudong.hao@intel.com>
Co-developed-by: Sean Christopherson <seanjc@google.com>
Tested-by: Manali Shukla <manali.shukla@amd.com>
Link: https://patch.msgid.link/20251206001720.468579-22-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>