[PATCH 1/4] KVM: x86/pmu: Force reprogramming of all counters on PMU filter change

[Sean Christopherson]

Force vCPUs to reprogram all counters on a PMU filter change to provide
a sane ABI for userspace.  Use the existing KVM_REQ_PMU to do the
programming, and take advantage of the fact that the reprogram_pmi bitmap
fits in a u64 to set all bits in a single atomic update.  Note, setting
the bitmap and making the request needs to be done _after_ the SRCU
synchronization to ensure that vCPUs will reprogram using the new filter.

KVM's current "lazy" approach is confusing and non-deterministic.  It's
confusing because, from a developer perspective, the code is buggy as it
makes zero sense to let userspace modify the filter but then not actually
enforce the new filter.  The lazy approach is non-deterministic because
KVM enforces the filter whenever a counter is reprogrammed, not just on
guest WRMSRs, i.e. a guest might gain/lose access to an event at random
times depending on what is going on in the host.

Note, the resulting behavior is still non-determinstic while the filter
is in flux.  If userspace wants to guarantee deterministic behavior, all
vCPUs should be paused during the filter update.

Fixes: 66bb8a065f5a ("KVM: x86: PMU Event Filter")
Cc: Aaron Lewis <aaronlewis@xxxxxxxxxx>
Jim Mattson <jmattson@xxxxxxxxxx>
Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
---
 arch/x86/include/asm/kvm_host.h | 11 ++++++++++-
 arch/x86/kvm/pmu.c              | 15 +++++++++++++--
 2 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index b3ce723efb43..462f041ede9f 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -519,7 +519,16 @@ struct kvm_pmu {
 	struct kvm_pmc gp_counters[INTEL_PMC_MAX_GENERIC];
 	struct kvm_pmc fixed_counters[KVM_PMC_MAX_FIXED];
 	struct irq_work irq_work;
-	DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+
+	/*
+	 * Overlay the bitmap with a 64-bit atomic so that all bits can be
+	 * set in a single access, e.g. to reprogram all counters when the PMU
+	 * filter changes.
+	 */
+	union {
+		DECLARE_BITMAP(reprogram_pmi, X86_PMC_IDX_MAX);
+		atomic64_t __reprogram_pmi;
+	};
 	DECLARE_BITMAP(all_valid_pmc_idx, X86_PMC_IDX_MAX);
 	DECLARE_BITMAP(pmc_in_use, X86_PMC_IDX_MAX);
 
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index d9b9a0f0db17..4504987cbbe2 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -577,6 +577,8 @@ EXPORT_SYMBOL_GPL(kvm_pmu_trigger_event);
 int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
 {
 	struct kvm_pmu_event_filter tmp, *filter;
+	struct kvm_vcpu *vcpu;
+	unsigned long i;
 	size_t size;
 	int r;
 
@@ -613,9 +615,18 @@ int kvm_vm_ioctl_set_pmu_event_filter(struct kvm *kvm, void __user *argp)
 	mutex_lock(&kvm->lock);
 	filter = rcu_replace_pointer(kvm->arch.pmu_event_filter, filter,
 				     mutex_is_locked(&kvm->lock));
-	mutex_unlock(&kvm->lock);
-
 	synchronize_srcu_expedited(&kvm->srcu);
+
+	BUILD_BUG_ON(sizeof(((struct kvm_pmu *)0)->reprogram_pmi) >
+		     sizeof(((struct kvm_pmu *)0)->__reprogram_pmi));
+
+	kvm_for_each_vcpu(i, vcpu, kvm)
+		atomic64_set(&vcpu_to_pmu(vcpu)->__reprogram_pmi, -1ull);
+
+	kvm_make_all_cpus_request(kvm, KVM_REQ_PMU);
+
+	mutex_unlock(&kvm->lock);
+
 	r = 0;
 cleanup:
 	kfree(filter);
-- 
2.37.3.998.g577e59143f-goog