[21/67] KVM: SVM: Add enable_ipiv param, never set IsRunning if disabled

Commit Message

Sean Christopherson April 4, 2025, 7:38 p.m. UTC

From: Maxim Levitsky <[e-mail]>

Let userspace "disable" IPI virtualization for AVIC via the enable_ipiv
module param, by never setting IsRunning.  SVM doesn't provide a way to
disable IPI virtualization in hardware, but by ensuring CPUs never see
IsRunning=1, every IPI in the guest (except for self-IPIs) will generate a
VM-Exit.

To avoid setting the real IsRunning bit, while still allowing KVM to use
each vCPU's entry to update GA log entries, simply maintain a shadow of
the entry, without propagating IsRunning updates to the real table when
IPI virtualization is disabled.

Providing a way to effectively disable IPI virtualization will allow KVM
to safely enable AVIC on hardware that is susceptible to erratum #1235,
which causes hardware to sometimes fail to detect that the IsRunning bit
has been cleared by software.

Note, the table _must_ be fully populated, as broadcast IPIs skip invalid
entries, i.e. won't generate VM-Exit if every entry is invalid, and so
simply pointing the VMCB at a common dummy table won't work.

Alternatively, KVM could allocate a shadow of the entire table, but that'd
be a waste of 4KiB since the per-vCPU entry doesn't actually consume an
additional 8 bytes of memory (vCPU structures are large enough that they
are backed by order-N pages).

Signed-off-by: Maxim Levitsky <[e-mail]>
[sean: keep "entry" variables, reuse enable_ipiv, split from erratum]
Signed-off-by: Sean Christopherson <[e-mail]>
---
 arch/x86/kvm/svm/avic.c | 32 ++++++++++++++++++++++++++------
 arch/x86/kvm/svm/svm.c  |  2 ++
 arch/x86/kvm/svm/svm.h  |  9 +++++++++
 3 files changed, 37 insertions(+), 6 deletions(-)

Patch

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index c4e6c97b736f..eea362cd415d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -301,6 +301,13 @@  static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	/* Setting AVIC backing page address in the phy APIC ID table */
 	new_entry = avic_get_backing_page_address(svm) |
 		    AVIC_PHYSICAL_ID_ENTRY_VALID_MASK;
+	svm->avic_physical_id_entry = new_entry;
+
+	/*
+	 * Initialize the real table, as vCPUs must have a valid entry in order
+	 * for broadcast IPIs to function correctly (broadcast IPIs ignore
+	 * invalid entries, i.e. aren't guaranteed to generate a VM-Exit).
+	 */
 	WRITE_ONCE(kvm_svm->avic_physical_id_table[id], new_entry);
 
 	return 0;
@@ -778,8 +785,6 @@  static int svm_ir_list_add(struct vcpu_svm *svm,
 			   struct amd_iommu_pi_data *pi)
 {
 	struct kvm_vcpu *vcpu = &svm->vcpu;
-	struct kvm *kvm = vcpu->kvm;
-	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
 	unsigned long flags;
 	u64 entry;
 
@@ -797,7 +802,7 @@  static int svm_ir_list_add(struct vcpu_svm *svm,
 	 * will update the pCPU info when the vCPU awkened and/or scheduled in.
 	 * See also avic_vcpu_load().
 	 */
-	entry = READ_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id]);
+	entry = svm->avic_physical_id_entry;
 	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
 		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
 				    true, pi->ir_data);
@@ -1010,14 +1015,26 @@  void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
-	entry = READ_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id]);
+	entry = svm->avic_physical_id_entry;
 	WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
 	entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
 	entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 
+	svm->avic_physical_id_entry = entry;
+
+	/*
+	 * If IPI virtualization is disabled, clear IsRunning when updating the
+	 * actual Physical ID table, so that the CPU never sees IsRunning=1.
+	 * Keep the APIC ID up-to-date in the entry to minimize the chances of
+	 * things going sideways if hardware peeks at the ID.
+	 */
+	if (!enable_ipiv)
+		entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+
 	WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+
 	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
 
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
@@ -1042,7 +1059,7 @@  void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	 * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
 	 * recursively.
 	 */
-	entry = READ_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id]);
+	entry = svm->avic_physical_id_entry;
 
 	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
 	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
@@ -1061,7 +1078,10 @@  void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
-	WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+	svm->avic_physical_id_entry = entry;
+
+	if (enable_ipiv)
+		WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
 
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index def76e63562d..43c4933d7da6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -230,6 +230,7 @@  module_param(tsc_scaling, int, 0444);
  */
 static bool avic;
 module_param(avic, bool, 0444);
+module_param(enable_ipiv, bool, 0444);
 
 module_param(enable_device_posted_irqs, bool, 0444);
 
@@ -5440,6 +5441,7 @@  static __init int svm_hardware_setup(void)
 	enable_apicv = avic = avic && avic_hardware_setup();
 
 	if (!enable_apicv) {
+		enable_ipiv = false;
 		svm_x86_ops.vcpu_blocking = NULL;
 		svm_x86_ops.vcpu_unblocking = NULL;
 		svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e223e57f7def..6ad0aa86f78d 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -302,6 +302,15 @@  struct vcpu_svm {
 	u32 ldr_reg;
 	u32 dfr_reg;
 
+	/*
+	 * This is essentially a shadow of the vCPU's actual entry in the
+	 * Physical ID table that is programmed into the VMCB, i.e. that is
+	 * seen by the CPU.  If IPI virtualization is disabled, IsRunning is
+	 * only ever set in the shadow, i.e. is never propagated to the "real"
+	 * table, so that hardware never sees IsRunning=1.
+	 */
+	u64 avic_physical_id_entry;
+
 	/*
 	 * Per-vcpu list of struct amd_svm_iommu_ir:
 	 * This is used mainly to store interrupt remapping information used