KVM: VMX: Ignore userspace MSR filters for x2APIC

Rework the resetting of the MSR bitmap for x2APIC MSRs to ignore userspace
filtering.  Allowing userspace to intercept reads to x2APIC MSRs when
APICV is fully enabled for the guest simply can't work; the LAPIC and thus
virtual APIC is in-kernel and cannot be directly accessed by userspace.
To keep things simple we will in fact forbid intercepting x2APIC MSRs
altogether, independent of the default_allow setting.

Cc: Alexander Graf <graf@amazon.com>
Cc: Aaron Lewis <aaronlewis@google.com>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20201005195532.8674-3-sean.j.christopherson@intel.com>
[Modified to operate even if APICv is disabled, adjust documentation. - Paolo]
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -4735,37 +4735,37 @@ KVM_PV_VM_VERIFY
 	struct kvm_msr_filter_range ranges[KVM_MSR_FILTER_MAX_RANGES];
   };
 
-flags values for struct kvm_msr_filter_range:
+flags values for ``struct kvm_msr_filter_range``:
 
-KVM_MSR_FILTER_READ
+``KVM_MSR_FILTER_READ``
 
   Filter read accesses to MSRs using the given bitmap. A 0 in the bitmap
   indicates that a read should immediately fail, while a 1 indicates that
   a read for a particular MSR should be handled regardless of the default
   filter action.
 
-KVM_MSR_FILTER_WRITE
+``KVM_MSR_FILTER_WRITE``
 
   Filter write accesses to MSRs using the given bitmap. A 0 in the bitmap
   indicates that a write should immediately fail, while a 1 indicates that
   a write for a particular MSR should be handled regardless of the default
   filter action.
 
-KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE
+``KVM_MSR_FILTER_READ | KVM_MSR_FILTER_WRITE``
 
   Filter both read and write accesses to MSRs using the given bitmap. A 0
   in the bitmap indicates that both reads and writes should immediately fail,
   while a 1 indicates that reads and writes for a particular MSR are not
   filtered by this range.
 
-flags values for struct kvm_msr_filter:
+flags values for ``struct kvm_msr_filter``:
 
-KVM_MSR_FILTER_DEFAULT_ALLOW
+``KVM_MSR_FILTER_DEFAULT_ALLOW``
 
   If no filter range matches an MSR index that is getting accessed, KVM will
   fall back to allowing access to the MSR.
 
-KVM_MSR_FILTER_DEFAULT_DENY
+``KVM_MSR_FILTER_DEFAULT_DENY``
 
   If no filter range matches an MSR index that is getting accessed, KVM will
   fall back to rejecting access to the MSR. In this mode, all MSRs that should
@@ -4775,14 +4775,19 @@ This ioctl allows user space to define up to 16 bitmaps of MSR ranges to
 specify whether a certain MSR access should be explicitly filtered for or not.
 
 If this ioctl has never been invoked, MSR accesses are not guarded and the
-old KVM in-kernel emulation behavior is fully preserved.
+default KVM in-kernel emulation behavior is fully preserved.
 
 As soon as the filtering is in place, every MSR access is processed through
-the filtering. If a bit is within one of the defined ranges, read and write
+the filtering except for accesses to the x2APIC MSRs (from 0x800 to 0x8ff);
+x2APIC MSRs are always allowed, independent of the ``default_allow`` setting,
+and their behavior depends on the ``X2APIC_ENABLE`` bit of the APIC base
+register.
+
+If a bit is within one of the defined ranges, read and write
 accesses are guarded by the bitmap's value for the MSR index. If it is not
 defined in any range, whether MSR access is rejected is determined by the flags
-field in the kvm_msr_filter struct: KVM_MSR_FILTER_DEFAULT_ALLOW and
-KVM_MSR_FILTER_DEFAULT_DENY.
+field in the kvm_msr_filter struct: ``KVM_MSR_FILTER_DEFAULT_ALLOW`` and
+``KVM_MSR_FILTER_DEFAULT_DENY``.
 
 Calling this ioctl with an empty set of ranges (all nmsrs == 0) disables MSR
 filtering. In that mode, KVM_MSR_FILTER_DEFAULT_DENY no longer has any effect.

arch/x86/kvm/vmx/vmx.c

@@ -3782,29 +3782,42 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
 	return mode;
 }
 
-static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode)
+static void vmx_reset_x2apic_msrs(struct kvm_vcpu *vcpu, u8 mode)
 {
+	unsigned long *msr_bitmap = to_vmx(vcpu)->vmcs01.msr_bitmap;
+	unsigned long read_intercept;
 	int msr;
 
-	for (msr = 0x800; msr <= 0x8ff; msr++) {
-		bool apicv = !!(mode & MSR_BITMAP_MODE_X2APIC_APICV);
+	read_intercept = (mode & MSR_BITMAP_MODE_X2APIC_APICV) ? 0 : ~0;
+
+	for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
+		unsigned int read_idx = msr / BITS_PER_LONG;
+		unsigned int write_idx = read_idx + (0x800 / sizeof(long));
 
-		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_R, !apicv);
-		vmx_set_intercept_for_msr(vcpu, msr, MSR_TYPE_W, true);
+		msr_bitmap[read_idx] = read_intercept;
+		msr_bitmap[write_idx] = ~0ul;
 	}
+}
+
+static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu, u8 mode)
+{
+	if (!cpu_has_vmx_msr_bitmap())
+		return;
+
+	vmx_reset_x2apic_msrs(vcpu, mode);
 
-	if (mode & MSR_BITMAP_MODE_X2APIC) {
 	/*
 	 * TPR reads and writes can be virtualized even if virtual interrupt
 	 * delivery is not in use.
 	 */
-		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
+	vmx_set_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW,
+				  !(mode & MSR_BITMAP_MODE_X2APIC));
+
 	if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
 		vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW);
 		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
 		vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
 	}
-	}
 }
 
 void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)

arch/x86/kvm/x86.c

@@ -1497,8 +1497,8 @@ bool kvm_msr_allowed(struct kvm_vcpu *vcpu, u32 index, u32 type)
 	bool r = kvm->arch.msr_filter.default_allow;
 	int idx;
 
-	/* MSR filtering not set up, allow everything */
-	if (!count)
+	/* MSR filtering not set up or x2APIC enabled, allow everything */
+	if (!count || (index >= 0x800 && index <= 0x8ff))
 		return true;
 
 	/* Prevent collision with set_msr_filter */