Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:
 "ARM:
   - support for chained PMU counters in guests
   - improved SError handling
   - handle Neoverse N1 erratum #1349291
   - allow side-channel mitigation status to be migrated
   - standardise most AArch64 system register accesses to msr_s/mrs_s
   - fix host MPIDR corruption on 32bit
   - selftests ckleanups

  x86:
   - PMU event {white,black}listing
   - ability for the guest to disable host-side interrupt polling
   - fixes for enlightened VMCS (Hyper-V pv nested virtualization),
   - new hypercall to yield to IPI target
   - support for passing cstate MSRs through to the guest
   - lots of cleanups and optimizations

  Generic:
   - Some txt->rST conversions for the documentation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (128 commits)
  Documentation: virtual: Add toctree hooks
  Documentation: kvm: Convert cpuid.txt to .rst
  Documentation: virtual: Convert paravirt_ops.txt to .rst
  KVM: x86: Unconditionally enable irqs in guest context
  KVM: x86: PMU Event Filter
  kvm: x86: Fix -Wmissing-prototypes warnings
  KVM: Properly check if "page" is valid in kvm_vcpu_unmap
  KVM: arm/arm64: Initialise host's MPIDRs by reading the actual register
  KVM: LAPIC: Retry tune per-vCPU timer_advance_ns if adaptive tuning goes insane
  kvm: LAPIC: write down valid APIC registers
  KVM: arm64: Migrate _elx sysreg accessors to msr_s/mrs_s
  KVM: doc: Add API documentation on the KVM_REG_ARM_WORKAROUNDS register
  KVM: arm/arm64: Add save/restore support for firmware workaround state
  arm64: KVM: Propagate full Spectre v2 workaround state to KVM guests
  KVM: arm/arm64: Support chained PMU counters
  KVM: arm/arm64: Remove pmc->bitmask
  KVM: arm/arm64: Re-create event when setting counter value
  KVM: arm/arm64: Extract duplicated code to own function
  KVM: arm/arm64: Rename kvm_pmu_{enable/disable}_counter functions
  KVM: LAPIC: ARBPRI is a reserved register for x2APIC
  ...

1 files changed, 63 insertions, 0 deletions

diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index ab73a9a639ae..aa5a2597305a 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -19,6 +19,9 @@
 #include "lapic.h"
 #include "pmu.h"
 
+/* This keeps the total size of the filter under 4k. */
+#define KVM_PMU_EVENT_FILTER_MAX_EVENTS 63
+
 /* NOTE:
  * - Each perf counter is defined as "struct kvm_pmc";
  * - There are two types of perf counters: general purpose (gp) and fixed.
@@ -141,6 +144,10 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 {
 	unsigned config, type = PERF_TYPE_RAW;
 	u8 event_select, unit_mask;
+	struct kvm *kvm = pmc->vcpu->kvm;
+	struct kvm_pmu_event_filter *filter;
+	int i;
+	bool allow_event = true;
 
 	if (eventsel & ARCH_PERFMON_EVENTSEL_PIN_CONTROL)
 		printk_once("kvm pmu: pin control bit is ignored\n");
@@ -152,6 +159,22 @@ void reprogram_gp_counter(struct kvm_pmc *pmc, u64 eventsel)
 	if (!(eventsel & ARCH_PERFMON_EVENTSEL_ENABLE) || !pmc_is_enabled(pmc))
 		return;
 
+	filter = srcu_dereference(kvm->arch.pmu_event_filter, &kvm->srcu);
+	if (filter) {
+		for (i = 0; i < filter->nevents; i++)
+			if (filter->events[i] ==
+			    (eventsel & AMD64_RAW_EVENT_MASK_NB))
+				break;
+		if (filter->action == KVM_PMU_EVENT_ALLOW &&
+		    i == filter->nevents)
+			allow_event = false;
+		if (filter->action == KVM_PMU_EVENT_DENY &&
+		    i < filter->nevents)
+			allow_event = false;
+	}
+	if (!allow_event)
+		return;
+
 	event_select = eventsel & ARCH_PERFMON_EVENTSEL_EVENT;
 	unit_mask = (eventsel & ARCH_PERFMON_EVENTSEL_UMASK) >> 8;
 
@@ -348,3 +371,43 @@ void kvm_pmu_destroy(struct kvm_vcpu *vcpu)
 {
 	kvm_pmu_reset(vcpu);
 }
+
+int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
+{
+	struct kvm_pmu_event_filter tmp, *filter;
+	size_t size;
+	int r;
+
+	if (copy_from_user(&tmp, argp, sizeof(tmp)))
+		return -EFAULT;
+
+	if (tmp.action != KVM_PMU_EVENT_ALLOW &&
+	    tmp.action != KVM_PMU_EVENT_DENY)
+		return -EINVAL;
+
+	if (tmp.nevents > KVM_PMU_EVENT_FILTER_MAX_EVENTS)
+		return -E2BIG;
+
+	size = struct_size(filter, events, tmp.nevents);
+	filter = kmalloc(size, GFP_KERNEL_ACCOUNT);
+	if (!filter)
+		return -ENOMEM;
+
+	r = -EFAULT;
+	if (copy_from_user(filter, argp, size))
+		goto cleanup;
+
+	/* Ensure nevents can't be changed between the user copies. */
+	*filter = tmp;
+
+	mutex_lock(&kvm->lock);
+	rcu_swap_protected(kvm->arch.pmu_event_filter, filter,
+			   mutex_is_locked(&kvm->lock));
+	mutex_unlock(&kvm->lock);
+
+	synchronize_srcu_expedited(&kvm->srcu);
+ 	r = 0;
+cleanup:
+	kfree(filter);
+ 	return r;
+}