@@ -2472,7 +2472,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
* maybe-unecessary write, and both are in the noise anyways.
*/
if (apic_x2apic_mode(apic) && offset == APIC_ICR)
- kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR));
+ WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR)));
else
kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
}
@@ -3186,8 +3186,21 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
return 0;
}
+#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13))
+
int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data)
{
+ if (data & X2APIC_ICR_RESERVED_BITS)
+ return 1;
+
+ /*
+ * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but
+ * only AMD requires it to be zero, Intel essentially just ignores the
+ * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled,
+ * the CPU performs the reserved bits checks, i.e. the underlying CPU
+ * behavior will "win". Arbitrarily clear the BUSY bit, as there is no
+ * sane way to provide consistent behavior with respect to hardware.
+ */
data &= ~APIC_ICR_BUSY;
kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
Inject a #GP on a WRMSR(ICR) that attempts to set any reserved bits that are must-be-zero on both Intel and AMD, i.e. any reserved bits other than the BUSY bit, which Intel ignores and basically says is undefined. KVM's xapic_state_test selftest has been fudging the bug since commit 4b88b1a518b3 ("KVM: selftests: Enhance handling WRMSR ICR register in x2APIC mode"), which essentially removed the testcase instead of fixing the bug. WARN if the nodecode path triggers a #GP, as the CPU is supposed to check reserved bits for ICR when it's partially virtualized. Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson <seanjc@google.com> --- arch/x86/kvm/lapic.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)