KVM: x86, SVM: isolate vcpu->arch.dr6 from vmcb->save.dr6

There are two issues with KVM_EXIT_DEBUG on AMD, whose root cause is the
different handling of DR6 on intercepted #DB exceptions on Intel and AMD.

On Intel, #DB exceptions transmit the DR6 value via the exit qualification
field of the VMCS, and the exit qualification only contains the description
of the precise event that caused a vmexit.

On AMD, instead the DR6 field of the VMCB is filled in as if the #DB exception
was to be injected into the guest.  This has two effects when guest debugging
is in use:

* the guest DR6 is clobbered

* the kvm_run->debug.arch.dr6 field can accumulate more debug events, rather
than just the last one that happened (the testcase in the next patch covers
this issue).

This patch fixes both issues by emulating, so to speak, the Intel behavior
on AMD processors.  The important observation is that (after the previous
patches) the VMCB value of DR6 is only ever observable from the guest is
KVM_DEBUGREG_WONT_EXIT is set.  Therefore we can actually set vmcb->save.dr6
to any value we want as long as KVM_DEBUGREG_WONT_EXIT is clear, which it
will be if guest debugging is enabled.

Therefore it is possible to enter the guest with an all-zero DR6,
reconstruct the #DB payload from the DR6 we get at exit time, and let
kvm_deliver_exception_payload move the newly set bits into vcpu->arch.dr6.
Some extra bits may be included in the payload if KVM_DEBUGREG_WONT_EXIT
is set, but this is harmless.

This may not be the most optimized way to deal with this, but it is
simple and, being confined within SVM code, it gets rid of the set_dr6
callback and kvm_update_dr6.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 21 insertions, 8 deletions

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f03bffafd9e6..a862c768fd54 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1672,12 +1672,14 @@ static void new_asid(struct vcpu_svm *svm, struct svm_cpu_data *sd)
 	mark_dirty(svm->vmcb, VMCB_ASID);
 }
 
-static void svm_set_dr6(struct kvm_vcpu *vcpu, unsigned long value)
+static void svm_set_dr6(struct vcpu_svm *svm, unsigned long value)
 {
-	struct vcpu_svm *svm = to_svm(vcpu);
+	struct vmcb *vmcb = svm->vmcb;
 
-	svm->vmcb->save.dr6 = value;
-	mark_dirty(svm->vmcb, VMCB_DR);
+	if (unlikely(value != vmcb->save.dr6)) {
+		vmcb->save.dr6 = value;
+		mark_dirty(vmcb, VMCB_DR);
+	}
 }
 
 static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
@@ -1688,9 +1690,12 @@ static void svm_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
 	get_debugreg(vcpu->arch.db[1], 1);
 	get_debugreg(vcpu->arch.db[2], 2);
 	get_debugreg(vcpu->arch.db[3], 3);
+	/*
+	 * We cannot reset svm->vmcb->save.dr6 to DR6_FIXED_1|DR6_RTM here,
+	 * because db_interception might need it.  We can do it before vmentry.
+	 */
 	vcpu->arch.dr6 = svm->vmcb->save.dr6;
 	vcpu->arch.dr7 = svm->vmcb->save.dr7;
-
 	vcpu->arch.switch_db_regs &= ~KVM_DEBUGREG_WONT_EXIT;
 	set_dr_intercepts(svm);
 }
@@ -1734,8 +1739,8 @@ static int db_interception(struct vcpu_svm *svm)
 	if (!(svm->vcpu.guest_debug &
 	      (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP)) &&
 		!svm->nmi_singlestep) {
-		vcpu->arch.dr6 = svm->vmcb->save.dr6;
-		kvm_queue_exception(&svm->vcpu, DB_VECTOR);
+		u32 payload = (svm->vmcb->save.dr6 ^ DR6_RTM) & ~DR6_FIXED_1;
+		kvm_queue_exception_p(&svm->vcpu, DB_VECTOR, payload);
 		return 1;
 	}
 
@@ -3313,6 +3318,15 @@ static void svm_vcpu_run(struct kvm_vcpu *vcpu)
 
 	svm->vmcb->save.cr2 = vcpu->arch.cr2;
 
+	/*
+	 * Run with all-zero DR6 unless needed, so that we can get the exact cause
+	 * of a #DB.
+	 */
+	if (unlikely(svm->vcpu.arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
+		svm_set_dr6(svm, vcpu->arch.dr6);
+	else
+		svm_set_dr6(svm, DR6_FIXED_1 | DR6_RTM);
+
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
@@ -3927,7 +3941,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
 	.set_idt = svm_set_idt,
 	.get_gdt = svm_get_gdt,
 	.set_gdt = svm_set_gdt,
-	.set_dr6 = svm_set_dr6,
 	.set_dr7 = svm_set_dr7,
 	.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
 	.cache_reg = svm_cache_reg,