1 files changed, 387 insertions, 208 deletions

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 8f9af7b7dbbe..6919dee69f18 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -27,20 +27,6 @@
 #include "irq.h"
 #include "svm.h"
 
-#define SVM_AVIC_DOORBELL	0xc001011b
-
-#define AVIC_HPA_MASK	~((0xFFFULL << 52) | 0xFFF)
-
-/*
- * 0xff is broadcast, so the max index allowed for physical APIC ID
- * table is 0xfe.  APIC IDs above 0xff are reserved.
- */
-#define AVIC_MAX_PHYSICAL_ID_COUNT	255
-
-#define AVIC_UNACCEL_ACCESS_WRITE_MASK		1
-#define AVIC_UNACCEL_ACCESS_OFFSET_MASK		0xFF0
-#define AVIC_UNACCEL_ACCESS_VECTOR_MASK		0xFFFFFFFF
-
 /* AVIC GATAG is encoded using VM and VCPU IDs */
 #define AVIC_VCPU_ID_BITS		8
 #define AVIC_VCPU_ID_MASK		((1 << AVIC_VCPU_ID_BITS) - 1)
@@ -54,6 +40,9 @@
 #define AVIC_GATAG_TO_VMID(x)		((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
 #define AVIC_GATAG_TO_VCPUID(x)		(x & AVIC_VCPU_ID_MASK)
 
+static bool force_avic;
+module_param_unsafe(force_avic, bool, 0444);
+
 /* Note:
  * This hash table is used to map VM_ID to a struct kvm_svm,
  * when handling AMD IOMMU GALOG notification to schedule in
@@ -64,6 +53,7 @@ static DEFINE_HASHTABLE(svm_vm_data_hash, SVM_VM_DATA_HASH_BITS);
 static u32 next_vm_id = 0;
 static bool next_vm_id_wrapped = 0;
 static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
+enum avic_modes avic_mode;
 
 /*
  * This is a wrapper of struct amd_iommu_ir_data.
@@ -73,12 +63,54 @@ struct amd_svm_iommu_ir {
 	void *data;		/* Storing pointer to struct amd_ir_data */
 };
 
-enum avic_ipi_failure_cause {
-	AVIC_IPI_FAILURE_INVALID_INT_TYPE,
-	AVIC_IPI_FAILURE_TARGET_NOT_RUNNING,
-	AVIC_IPI_FAILURE_INVALID_TARGET,
-	AVIC_IPI_FAILURE_INVALID_BACKING_PAGE,
-};
+static void avic_activate_vmcb(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
+	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
+
+	vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+
+	/* Note:
+	 * KVM can support hybrid-AVIC mode, where KVM emulates x2APIC
+	 * MSR accesses, while interrupt injection to a running vCPU
+	 * can be achieved using AVIC doorbell. The AVIC hardware still
+	 * accelerate MMIO accesses, but this does not cause any harm
+	 * as the guest is not supposed to access xAPIC mmio when uses x2APIC.
+	 */
+	if (apic_x2apic_mode(svm->vcpu.arch.apic) &&
+	    avic_mode == AVIC_MODE_X2) {
+		vmcb->control.int_ctl |= X2APIC_MODE_MASK;
+		vmcb->control.avic_physical_id |= X2AVIC_MAX_PHYSICAL_ID;
+		/* Disabling MSR intercept for x2APIC registers */
+		svm_set_x2apic_msr_interception(svm, false);
+	} else {
+		/* For xAVIC and hybrid-xAVIC modes */
+		vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID;
+		/* Enabling MSR intercept for x2APIC registers */
+		svm_set_x2apic_msr_interception(svm, true);
+	}
+}
+
+static void avic_deactivate_vmcb(struct vcpu_svm *svm)
+{
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+
+	vmcb->control.int_ctl &= ~(AVIC_ENABLE_MASK | X2APIC_MODE_MASK);
+	vmcb->control.avic_physical_id &= ~AVIC_PHYSICAL_MAX_INDEX_MASK;
+
+	/*
+	 * If running nested and the guest uses its own MSR bitmap, there
+	 * is no need to update L0's msr bitmap
+	 */
+	if (is_guest_mode(&svm->vcpu) &&
+	    vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT))
+		return;
+
+	/* Enabling MSR intercept for x2APIC registers */
+	svm_set_x2apic_msr_interception(svm, true);
+}
 
 /* Note:
  * This function is called from IOMMU driver to notify
@@ -185,9 +217,8 @@ free_avic:
 	return err;
 }
 
-void avic_init_vmcb(struct vcpu_svm *svm)
+void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
 {
-	struct vmcb *vmcb = svm->vmcb;
 	struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
 	phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
 	phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
@@ -196,13 +227,12 @@ void avic_init_vmcb(struct vcpu_svm *svm)
 	vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
 	vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
 	vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
-	vmcb->control.avic_physical_id |= AVIC_MAX_PHYSICAL_ID_COUNT;
 	vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK;
 
 	if (kvm_apicv_activated(svm->vcpu.kvm))
-		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
+		avic_activate_vmcb(svm);
 	else
-		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
+		avic_deactivate_vmcb(svm);
 }
 
 static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
@@ -211,7 +241,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
 	u64 *avic_physical_id_table;
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
 
-	if (index >= AVIC_MAX_PHYSICAL_ID_COUNT)
+	if ((avic_mode == AVIC_MODE_X1 && index > AVIC_MAX_PHYSICAL_ID) ||
+	    (avic_mode == AVIC_MODE_X2 && index > X2AVIC_MAX_PHYSICAL_ID))
 		return NULL;
 
 	avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page);
@@ -258,7 +289,8 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	int id = vcpu->vcpu_id;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (id >= AVIC_MAX_PHYSICAL_ID_COUNT)
+	if ((avic_mode == AVIC_MODE_X1 && id > AVIC_MAX_PHYSICAL_ID) ||
+	    (avic_mode == AVIC_MODE_X2 && id > X2AVIC_MAX_PHYSICAL_ID))
 		return -EINVAL;
 
 	if (!vcpu->arch.apic->regs)
@@ -289,20 +321,166 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
 	return 0;
 }
 
+void avic_ring_doorbell(struct kvm_vcpu *vcpu)
+{
+	/*
+	 * Note, the vCPU could get migrated to a different pCPU at any point,
+	 * which could result in signalling the wrong/previous pCPU.  But if
+	 * that happens the vCPU is guaranteed to do a VMRUN (after being
+	 * migrated) and thus will process pending interrupts, i.e. a doorbell
+	 * is not needed (and the spurious one is harmless).
+	 */
+	int cpu = READ_ONCE(vcpu->cpu);
+
+	if (cpu != get_cpu()) {
+		wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
+		trace_kvm_avic_doorbell(vcpu->vcpu_id, kvm_cpu_get_apicid(cpu));
+	}
+	put_cpu();
+}
+
+/*
+ * A fast-path version of avic_kick_target_vcpus(), which attempts to match
+ * destination APIC ID to vCPU without looping through all vCPUs.
+ */
+static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source,
+				       u32 icrl, u32 icrh, u32 index)
+{
+	u32 l1_physical_id, dest;
+	struct kvm_vcpu *target_vcpu;
+	int dest_mode = icrl & APIC_DEST_MASK;
+	int shorthand = icrl & APIC_SHORT_MASK;
+	struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
+
+	if (shorthand != APIC_DEST_NOSHORT)
+		return -EINVAL;
+
+	if (apic_x2apic_mode(source))
+		dest = icrh;
+	else
+		dest = GET_XAPIC_DEST_FIELD(icrh);
+
+	if (dest_mode == APIC_DEST_PHYSICAL) {
+		/* broadcast destination, use slow path */
+		if (apic_x2apic_mode(source) && dest == X2APIC_BROADCAST)
+			return -EINVAL;
+		if (!apic_x2apic_mode(source) && dest == APIC_BROADCAST)
+			return -EINVAL;
+
+		l1_physical_id = dest;
+
+		if (WARN_ON_ONCE(l1_physical_id != index))
+			return -EINVAL;
+
+	} else {
+		u32 bitmap, cluster;
+		int logid_index;
+
+		if (apic_x2apic_mode(source)) {
+			/* 16 bit dest mask, 16 bit cluster id */
+			bitmap = dest & 0xFFFF0000;
+			cluster = (dest >> 16) << 4;
+		} else if (kvm_lapic_get_reg(source, APIC_DFR) == APIC_DFR_FLAT) {
+			/* 8 bit dest mask*/
+			bitmap = dest;
+			cluster = 0;
+		} else {
+			/* 4 bit desk mask, 4 bit cluster id */
+			bitmap = dest & 0xF;
+			cluster = (dest >> 4) << 2;
+		}
+
+		if (unlikely(!bitmap))
+			/* guest bug: nobody to send the logical interrupt to */
+			return 0;
+
+		if (!is_power_of_2(bitmap))
+			/* multiple logical destinations, use slow path */
+			return -EINVAL;
+
+		logid_index = cluster + __ffs(bitmap);
+
+		if (!apic_x2apic_mode(source)) {
+			u32 *avic_logical_id_table =
+				page_address(kvm_svm->avic_logical_id_table_page);
+
+			u32 logid_entry = avic_logical_id_table[logid_index];
+
+			if (WARN_ON_ONCE(index != logid_index))
+				return -EINVAL;
+
+			/* guest bug: non existing/reserved logical destination */
+			if (unlikely(!(logid_entry & AVIC_LOGICAL_ID_ENTRY_VALID_MASK)))
+				return 0;
+
+			l1_physical_id = logid_entry &
+					 AVIC_LOGICAL_ID_ENTRY_GUEST_PHYSICAL_ID_MASK;
+		} else {
+			/*
+			 * For x2APIC logical mode, cannot leverage the index.
+			 * Instead, calculate physical ID from logical ID in ICRH.
+			 */
+			int cluster = (icrh & 0xffff0000) >> 16;
+			int apic = ffs(icrh & 0xffff) - 1;
+
+			/*
+			 * If the x2APIC logical ID sub-field (i.e. icrh[15:0])
+			 * contains anything but a single bit, we cannot use the
+			 * fast path, because it is limited to a single vCPU.
+			 */
+			if (apic < 0 || icrh != (1 << apic))
+				return -EINVAL;
+
+			l1_physical_id = (cluster << 4) + apic;
+		}
+	}
+
+	target_vcpu = kvm_get_vcpu_by_id(kvm, l1_physical_id);
+	if (unlikely(!target_vcpu))
+		/* guest bug: non existing vCPU is a target of this IPI*/
+		return 0;
+
+	target_vcpu->arch.apic->irr_pending = true;
+	svm_complete_interrupt_delivery(target_vcpu,
+					icrl & APIC_MODE_MASK,
+					icrl & APIC_INT_LEVELTRIG,
+					icrl & APIC_VECTOR_MASK);
+	return 0;
+}
+
 static void avic_kick_target_vcpus(struct kvm *kvm, struct kvm_lapic *source,
-				   u32 icrl, u32 icrh)
+				   u32 icrl, u32 icrh, u32 index)
 {
+	unsigned long i;
 	struct kvm_vcpu *vcpu;
-	int i;
 
+	if (!avic_kick_target_vcpus_fast(kvm, source, icrl, icrh, index))
+		return;
+
+	trace_kvm_avic_kick_vcpu_slowpath(icrh, icrl, index);
+
+	/*
+	 * Wake any target vCPUs that are blocking, i.e. waiting for a wake
+	 * event.  There's no need to signal doorbells, as hardware has handled
+	 * vCPUs that were in guest at the time of the IPI, and vCPUs that have
+	 * since entered the guest will have processed pending IRQs at VMRUN.
+	 */
 	kvm_for_each_vcpu(i, vcpu, kvm) {
-		bool m = kvm_apic_match_dest(vcpu, source,
-					     icrl & APIC_SHORT_MASK,
-					     GET_APIC_DEST_FIELD(icrh),
-					     icrl & APIC_DEST_MASK);
+		u32 dest;
 
-		if (m && !avic_vcpu_is_running(vcpu))
-			kvm_vcpu_wake_up(vcpu);
+		if (apic_x2apic_mode(vcpu->arch.apic))
+			dest = icrh;
+		else
+			dest = GET_XAPIC_DEST_FIELD(icrh);
+
+		if (kvm_apic_match_dest(vcpu, source, icrl & APIC_SHORT_MASK,
+					dest, icrl & APIC_DEST_MASK)) {
+			vcpu->arch.apic->irr_pending = true;
+			svm_complete_interrupt_delivery(vcpu,
+							icrl & APIC_MODE_MASK,
+							icrl & APIC_INT_LEVELTRIG,
+							icrl & APIC_VECTOR_MASK);
+		}
 	}
 }
 
@@ -312,7 +490,7 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	u32 icrh = svm->vmcb->control.exit_info_1 >> 32;
 	u32 icrl = svm->vmcb->control.exit_info_1;
 	u32 id = svm->vmcb->control.exit_info_2 >> 32;
-	u32 index = svm->vmcb->control.exit_info_2 & 0xFF;
+	u32 index = svm->vmcb->control.exit_info_2 & 0x1FF;
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
 	trace_kvm_avic_incomplete_ipi(vcpu->vcpu_id, icrh, icrl, id, index);
@@ -320,18 +498,18 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	switch (id) {
 	case AVIC_IPI_FAILURE_INVALID_INT_TYPE:
 		/*
-		 * AVIC hardware handles the generation of
-		 * IPIs when the specified Message Type is Fixed
-		 * (also known as fixed delivery mode) and
-		 * the Trigger Mode is edge-triggered. The hardware
-		 * also supports self and broadcast delivery modes
-		 * specified via the Destination Shorthand(DSH)
-		 * field of the ICRL. Logical and physical APIC ID
-		 * formats are supported. All other IPI types cause
-		 * a #VMEXIT, which needs to emulated.
+		 * Emulate IPIs that are not handled by AVIC hardware, which
+		 * only virtualizes Fixed, Edge-Triggered INTRs.  The exit is
+		 * a trap, e.g. ICR holds the correct value and RIP has been
+		 * advanced, KVM is responsible only for emulating the IPI.
+		 * Sadly, hardware may sometimes leave the BUSY flag set, in
+		 * which case KVM needs to emulate the ICR write as well in
+		 * order to clear the BUSY flag.
 		 */
-		kvm_lapic_reg_write(apic, APIC_ICR2, icrh);
-		kvm_lapic_reg_write(apic, APIC_ICR, icrl);
+		if (icrl & APIC_ICR_BUSY)
+			kvm_apic_write_nodecode(vcpu, APIC_ICR);
+		else
+			kvm_apic_send_ipi(apic, icrl, icrh);
 		break;
 	case AVIC_IPI_FAILURE_TARGET_NOT_RUNNING:
 		/*
@@ -339,11 +517,9 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 		 * set the appropriate IRR bits on the valid target
 		 * vcpus. So, we just need to kick the appropriate vcpu.
 		 */
-		avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh);
+		avic_kick_target_vcpus(vcpu->kvm, apic, icrl, icrh, index);
 		break;
 	case AVIC_IPI_FAILURE_INVALID_TARGET:
-		WARN_ONCE(1, "Invalid IPI target: index=%u, vcpu=%d, icr=%#0x:%#0x\n",
-			  index, vcpu->vcpu_id, icrh, icrl);
 		break;
 	case AVIC_IPI_FAILURE_INVALID_BACKING_PAGE:
 		WARN_ONCE(1, "Invalid backing page\n");
@@ -355,6 +531,13 @@ int avic_incomplete_ipi_interception(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu)
+{
+	if (is_guest_mode(vcpu))
+		return APICV_INHIBIT_REASON_NESTED;
+	return 0;
+}
+
 static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
 {
 	struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
@@ -407,8 +590,13 @@ static void avic_invalidate_logical_id_entry(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 	bool flat = svm->dfr_reg == APIC_DFR_FLAT;
-	u32 *entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
+	u32 *entry;
 
+	/* Note: x2AVIC does not use logical APIC ID table */
+	if (apic_x2apic_mode(vcpu->arch.apic))
+		return;
+
+	entry = avic_get_logical_id_entry(vcpu, svm->ldr_reg, flat);
 	if (entry)
 		clear_bit(AVIC_LOGICAL_ID_ENTRY_VALID_BIT, (unsigned long *)entry);
 }
@@ -420,6 +608,10 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	u32 ldr = kvm_lapic_get_reg(vcpu->arch.apic, APIC_LDR);
 	u32 id = kvm_xapic_id(vcpu->arch.apic);
 
+	/* AVIC does not support LDR update for x2APIC */
+	if (apic_x2apic_mode(vcpu->arch.apic))
+		return 0;
+
 	if (ldr == svm->ldr_reg)
 		return 0;
 
@@ -434,35 +626,6 @@ static int avic_handle_ldr_update(struct kvm_vcpu *vcpu)
 	return ret;
 }
 
-static int avic_handle_apic_id_update(struct kvm_vcpu *vcpu)
-{
-	u64 *old, *new;
-	struct vcpu_svm *svm = to_svm(vcpu);
-	u32 id = kvm_xapic_id(vcpu->arch.apic);
-
-	if (vcpu->vcpu_id == id)
-		return 0;
-
-	old = avic_get_physical_id_entry(vcpu, vcpu->vcpu_id);
-	new = avic_get_physical_id_entry(vcpu, id);
-	if (!new || !old)
-		return 1;
-
-	/* We need to move physical_id_entry to new offset */
-	*new = *old;
-	*old = 0ULL;
-	to_svm(vcpu)->avic_physical_id_cache = new;
-
-	/*
-	 * Also update the guest physical APIC ID in the logical
-	 * APIC ID table entry if already setup the LDR.
-	 */
-	if (svm->ldr_reg)
-		avic_handle_ldr_update(vcpu);
-
-	return 0;
-}
-
 static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -475,30 +638,24 @@ static void avic_handle_dfr_update(struct kvm_vcpu *vcpu)
 	svm->dfr_reg = dfr;
 }
 
-static int avic_unaccel_trap_write(struct vcpu_svm *svm)
+static int avic_unaccel_trap_write(struct kvm_vcpu *vcpu)
 {
-	struct kvm_lapic *apic = svm->vcpu.arch.apic;
-	u32 offset = svm->vmcb->control.exit_info_1 &
+	u32 offset = to_svm(vcpu)->vmcb->control.exit_info_1 &
 				AVIC_UNACCEL_ACCESS_OFFSET_MASK;
 
 	switch (offset) {
-	case APIC_ID:
-		if (avic_handle_apic_id_update(&svm->vcpu))
-			return 0;
-		break;
 	case APIC_LDR:
-		if (avic_handle_ldr_update(&svm->vcpu))
+		if (avic_handle_ldr_update(vcpu))
 			return 0;
 		break;
 	case APIC_DFR:
-		avic_handle_dfr_update(&svm->vcpu);
+		avic_handle_dfr_update(vcpu);
 		break;
 	default:
 		break;
 	}
 
-	kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
-
+	kvm_apic_write_nodecode(vcpu, offset);
 	return 1;
 }
 
@@ -548,7 +705,7 @@ int avic_unaccelerated_access_interception(struct kvm_vcpu *vcpu)
 	if (trap) {
 		/* Handling Trap */
 		WARN_ONCE(!write, "svm: Handling trap read.\n");
-		ret = avic_unaccel_trap_write(svm);
+		ret = avic_unaccel_trap_write(vcpu);
 	} else {
 		/* Handling Fault */
 		ret = kvm_emulate_instruction(vcpu, 0);
@@ -576,28 +733,25 @@ int avic_init_vcpu(struct vcpu_svm *svm)
 	return ret;
 }
 
-void avic_post_state_restore(struct kvm_vcpu *vcpu)
+void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 {
-	if (avic_handle_apic_id_update(vcpu) != 0)
-		return;
 	avic_handle_dfr_update(vcpu);
 	avic_handle_ldr_update(vcpu);
 }
 
-void svm_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
+void avic_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 {
-	return;
-}
-
-void svm_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr)
-{
-}
+	if (!lapic_in_kernel(vcpu) || avic_mode == AVIC_MODE_NONE)
+		return;
 
-void svm_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
-{
+	if (kvm_get_apic_mode(vcpu) == LAPIC_MODE_INVALID) {
+		WARN_ONCE(true, "Invalid local APIC state (vcpu_id=%d)", vcpu->vcpu_id);
+		return;
+	}
+	avic_refresh_apicv_exec_ctrl(vcpu);
 }
 
-static int svm_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
+static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
 	int ret = 0;
 	unsigned long flags;
@@ -629,68 +783,6 @@ out:
 	return ret;
 }
 
-void svm_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
-{
-	struct vcpu_svm *svm = to_svm(vcpu);
-	struct vmcb *vmcb = svm->vmcb01.ptr;
-	bool activated = kvm_vcpu_apicv_active(vcpu);
-
-	if (!enable_apicv)
-		return;
-
-	if (activated) {
-		/**
-		 * During AVIC temporary deactivation, guest could update
-		 * APIC ID, DFR and LDR registers, which would not be trapped
-		 * by avic_unaccelerated_access_interception(). In this case,
-		 * we need to check and update the AVIC logical APIC ID table
-		 * accordingly before re-activating.
-		 */
-		avic_post_state_restore(vcpu);
-		vmcb->control.int_ctl |= AVIC_ENABLE_MASK;
-	} else {
-		vmcb->control.int_ctl &= ~AVIC_ENABLE_MASK;
-	}
-	vmcb_mark_dirty(vmcb, VMCB_AVIC);
-
-	if (activated)
-		avic_vcpu_load(vcpu, vcpu->cpu);
-	else
-		avic_vcpu_put(vcpu);
-
-	svm_set_pi_irte_mode(vcpu, activated);
-}
-
-void svm_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
-{
-	return;
-}
-
-int svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
-{
-	if (!vcpu->arch.apicv_active)
-		return -1;
-
-	kvm_lapic_set_irr(vec, vcpu->arch.apic);
-	smp_mb__after_atomic();
-
-	if (avic_vcpu_is_running(vcpu)) {
-		int cpuid = vcpu->cpu;
-
-		if (cpuid != get_cpu())
-			wrmsrl(SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpuid));
-		put_cpu();
-	} else
-		kvm_vcpu_wake_up(vcpu);
-
-	return 0;
-}
-
-bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
-{
-	return false;
-}
-
 static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
@@ -788,7 +880,7 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 }
 
 /*
- * svm_update_pi_irte - set IRTE for Posted-Interrupts
+ * avic_pi_update_irte - set IRTE for Posted-Interrupts
  *
  * @kvm: kvm
  * @host_irq: host irq of the interrupt
@@ -796,12 +888,12 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
  * @set: set or unset PI
  * returns 0 on success, < 0 on failure
  */
-int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
-		       uint32_t guest_irq, bool set)
+int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
+			uint32_t guest_irq, bool set)
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
-	int idx, ret = -EINVAL;
+	int idx, ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) ||
 	    !irq_remapping_cap(IRQ_POSTING_CAP))
@@ -812,7 +904,13 @@ int svm_update_pi_irte(struct kvm *kvm, unsigned int host_irq,
 
 	idx = srcu_read_lock(&kvm->irq_srcu);
 	irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-	WARN_ON(guest_irq >= irq_rt->nr_rt_entries);
+
+	if (guest_irq >= irq_rt->nr_rt_entries ||
+		hlist_empty(&irq_rt->map[guest_irq])) {
+		pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
+			     guest_irq, irq_rt->nr_rt_entries);
+		goto out;
+	}
 
 	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
 		struct vcpu_data vcpu_info;
@@ -897,7 +995,7 @@ out:
 	return ret;
 }
 
-bool svm_check_apicv_inhibit_reasons(ulong bit)
+bool avic_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason)
 {
 	ulong supported = BIT(APICV_INHIBIT_REASON_DISABLE) |
 			  BIT(APICV_INHIBIT_REASON_ABSENT) |
@@ -905,10 +1003,12 @@ bool svm_check_apicv_inhibit_reasons(ulong bit)
 			  BIT(APICV_INHIBIT_REASON_NESTED) |
 			  BIT(APICV_INHIBIT_REASON_IRQWIN) |
 			  BIT(APICV_INHIBIT_REASON_PIT_REINJ) |
-			  BIT(APICV_INHIBIT_REASON_X2APIC) |
-			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ);
+			  BIT(APICV_INHIBIT_REASON_BLOCKIRQ) |
+			  BIT(APICV_INHIBIT_REASON_SEV)      |
+			  BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) |
+			  BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED);
 
-	return supported & BIT(bit);
+	return supported & BIT(reason);
 }
 
 
@@ -945,30 +1045,32 @@ out:
 void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
 	u64 entry;
-	/* ID = 0xff (broadcast), ID > 0xff (reserved) */
 	int h_physical_id = kvm_cpu_get_apicid(cpu);
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
+	if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
+		return;
+
 	/*
-	 * Since the host physical APIC id is 8 bits,
-	 * we can support host APIC ID upto 255.
+	 * No need to update anything if the vCPU is blocking, i.e. if the vCPU
+	 * is being scheduled in after being preempted.  The CPU entries in the
+	 * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
+	 * If the vCPU was migrated, its new CPU value will be stuffed when the
+	 * vCPU unblocks.
 	 */
-	if (WARN_ON(h_physical_id > AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
+	if (kvm_vcpu_is_blocking(vcpu))
 		return;
 
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
-	WARN_ON(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;
-	if (svm->avic_is_running)
-		entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+	entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
-	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id,
-					svm->avic_is_running);
+	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
 }
 
 void avic_vcpu_put(struct kvm_vcpu *vcpu)
@@ -976,42 +1078,119 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	u64 entry;
 	struct vcpu_svm *svm = to_svm(vcpu);
 
+	lockdep_assert_preemption_disabled();
+
 	entry = READ_ONCE(*(svm->avic_physical_id_cache));
-	if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
-		avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+
+	/* Nothing to do if IsRunning == '0' due to vCPU blocking. */
+	if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
+		return;
+
+	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
 }
 
-/*
- * This function is called during VCPU halt/unhalt.
- */
-static void avic_set_running(struct kvm_vcpu *vcpu, bool is_run)
+
+void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	int cpu = get_cpu();
+	struct vmcb *vmcb = svm->vmcb01.ptr;
+	bool activated = kvm_vcpu_apicv_active(vcpu);
 
-	WARN_ON(cpu != vcpu->cpu);
-	svm->avic_is_running = is_run;
+	if (!enable_apicv)
+		return;
 
-	if (kvm_vcpu_apicv_active(vcpu)) {
-		if (is_run)
-			avic_vcpu_load(vcpu, cpu);
-		else
-			avic_vcpu_put(vcpu);
+	if (activated) {
+		/**
+		 * During AVIC temporary deactivation, guest could update
+		 * APIC ID, DFR and LDR registers, which would not be trapped
+		 * by avic_unaccelerated_access_interception(). In this case,
+		 * we need to check and update the AVIC logical APIC ID table
+		 * accordingly before re-activating.
+		 */
+		avic_apicv_post_state_restore(vcpu);
+		avic_activate_vmcb(svm);
+	} else {
+		avic_deactivate_vmcb(svm);
 	}
-	put_cpu();
+	vmcb_mark_dirty(vmcb, VMCB_AVIC);
+
+	if (activated)
+		avic_vcpu_load(vcpu, vcpu->cpu);
+	else
+		avic_vcpu_put(vcpu);
+
+	avic_set_pi_irte_mode(vcpu, activated);
 }
 
-void svm_vcpu_blocking(struct kvm_vcpu *vcpu)
+void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
 {
-	avic_set_running(vcpu, false);
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+       /*
+        * Unload the AVIC when the vCPU is about to block, _before_
+        * the vCPU actually blocks.
+        *
+        * Any IRQs that arrive before IsRunning=0 will not cause an
+        * incomplete IPI vmexit on the source, therefore vIRR will also
+        * be checked by kvm_vcpu_check_block() before blocking.  The
+        * memory barrier implicit in set_current_state orders writing
+        * IsRunning=0 before reading the vIRR.  The processor needs a
+        * matching memory barrier on interrupt delivery between writing
+        * IRR and reading IsRunning; the lack of this barrier might be
+        * the cause of errata #1235).
+        */
+	avic_vcpu_put(vcpu);
 }
 
-void svm_vcpu_unblocking(struct kvm_vcpu *vcpu)
+void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
 {
-	if (kvm_check_request(KVM_REQ_APICV_UPDATE, vcpu))
-		kvm_vcpu_update_apicv(vcpu);
-	avic_set_running(vcpu, true);
+	if (!kvm_vcpu_apicv_active(vcpu))
+		return;
+
+	avic_vcpu_load(vcpu, vcpu->cpu);
+}
+
+/*
+ * Note:
+ * - The module param avic enable both xAPIC and x2APIC mode.
+ * - Hypervisor can support both xAVIC and x2AVIC in the same guest.
+ * - The mode can be switched at run-time.
+ */
+bool avic_hardware_setup(struct kvm_x86_ops *x86_ops)
+{
+	if (!npt_enabled)
+		return false;
+
+	if (boot_cpu_has(X86_FEATURE_AVIC)) {
+		avic_mode = AVIC_MODE_X1;
+		pr_info("AVIC enabled\n");
+	} else if (force_avic) {
+		/*
+		 * Some older systems does not advertise AVIC support.
+		 * See Revision Guide for specific AMD processor for more detail.
+		 */
+		avic_mode = AVIC_MODE_X1;
+		pr_warn("AVIC is not supported in CPUID but force enabled");
+		pr_warn("Your system might crash and burn");
+	}
+
+	/* AVIC is a prerequisite for x2AVIC. */
+	if (boot_cpu_has(X86_FEATURE_X2AVIC)) {
+		if (avic_mode == AVIC_MODE_X1) {
+			avic_mode = AVIC_MODE_X2;
+			pr_info("x2AVIC enabled\n");
+		} else {
+			pr_warn(FW_BUG "Cannot support x2AVIC due to AVIC is disabled");
+			pr_warn(FW_BUG "Try enable AVIC using force_avic option");
+		}
+	}
+
+	if (avic_mode != AVIC_MODE_NONE)
+		amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
+
+	return !!avic_mode;
 }