When restricted injection is active, only #HV exceptions can be injected into
the SEV-SNP guest.

Detect that restricted injection feature is active for the guest, and then
follow the #HV doorbell communication from the GHCB specification to inject the
interrupt or exception.

Co-developed-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Thomas Lendacky <thomas.lendacky@amd.com>
Signed-off-by: Melody Wang <huibo.wang@amd.com>
---
 arch/x86/include/uapi/asm/kvm.h |   1 +
 arch/x86/kvm/svm/sev.c          | 165 ++++++++++++++++++++++++++++++++
 arch/x86/kvm/svm/svm.c          |  16 +++-
 arch/x86/kvm/svm/svm.h          |  21 +++-
 4 files changed, 199 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 88585c1de416..ec82ab4ef70c 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -35,6 +35,7 @@
 #define MC_VECTOR 18
 #define XM_VECTOR 19
 #define VE_VECTOR 20
+#define HV_VECTOR 28
 
 /* Select x86 specific features in <linux/kvm.h> */
 #define __KVM_HAVE_PIT
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index 7cd1c0652d15..77dbc7dea974 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -5028,3 +5028,168 @@ int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
 
 	return level;
 }
+
+static void prepare_hv_injection(struct vcpu_svm *svm, struct hvdb *hvdb)
+{
+	if (hvdb->events.no_further_signal)
+		return;
+
+	svm->vmcb->control.event_inj = HV_VECTOR |
+				       SVM_EVTINJ_TYPE_EXEPT |
+				       SVM_EVTINJ_VALID;
+	svm->vmcb->control.event_inj_err = 0;
+
+	hvdb->events.no_further_signal = 1;
+}
+
+static void unmap_hvdb(struct kvm_vcpu *vcpu, struct kvm_host_map *map)
+{
+	kvm_vcpu_unmap(vcpu, map);
+}
+
+static struct hvdb *map_hvdb(struct kvm_vcpu *vcpu, struct kvm_host_map *map)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!VALID_PAGE(svm->sev_es.hvdb_gpa))
+		return NULL;
+
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(svm->sev_es.hvdb_gpa), map)) {
+		/* Unable to map #HV doorbell page from guest */
+		vcpu_unimpl(vcpu, "snp: error mapping #HV doorbell page [%#llx] from guest\n",
+			    svm->sev_es.hvdb_gpa);
+
+		return NULL;
+	}
+
+	return map->hva;
+}
+
+static void __sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_host_map hvdb_map;
+	struct hvdb *hvdb;
+
+	hvdb = map_hvdb(vcpu, &hvdb_map);
+	if (!hvdb) {
+		WARN_ONCE(1, "restricted injection enabled, hvdb page mapping failed\n");
+		return;
+	}
+
+	hvdb->events.vector = vcpu->arch.interrupt.nr;
+
+	prepare_hv_injection(svm, hvdb);
+
+	unmap_hvdb(vcpu, &hvdb_map);
+}
+
+bool sev_snp_queue_exception(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+
+	if (!sev_snp_is_rinj_active(vcpu))
+		return false;
+
+	/*
+	 * Restricted injection is enabled, only #HV is supported.
+	 * If the vector is not HV_VECTOR, do not inject the exception,
+	 * then return true to skip the original injection path.
+	 */
+	if (WARN_ONCE(vcpu->arch.exception.vector != HV_VECTOR,
+		      "restricted injection enabled, exception vector %u injection not supported\n",
+		      vcpu->arch.exception.vector))
+		return true;
+
+	/*
+	 * An intercept likely occurred during #HV delivery, so re-inject it
+	 * using the current HVDB pending event values.
+	 */
+	svm->vmcb->control.event_inj = HV_VECTOR |
+				       SVM_EVTINJ_TYPE_EXEPT |
+				       SVM_EVTINJ_VALID;
+	svm->vmcb->control.event_inj_err = 0;
+
+	return true;
+}
+
+bool sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu)
+{
+	if (!sev_snp_is_rinj_active(vcpu))
+		return false;
+
+	__sev_snp_inject(type, vcpu);
+
+	return true;
+}
+
+void sev_snp_cancel_injection(struct kvm_vcpu *vcpu)
+{
+	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_host_map hvdb_map;
+	struct hvdb *hvdb;
+
+	if (!sev_snp_is_rinj_active(vcpu))
+		return;
+
+	if (!svm->vmcb->control.event_inj)
+		return;
+
+	if (WARN_ONCE((svm->vmcb->control.event_inj & SVM_EVTINJ_VEC_MASK) != HV_VECTOR,
+			"restricted injection enabled,  %u vector not supported\n",
+			svm->vmcb->control.event_inj & SVM_EVTINJ_VEC_MASK))
+		return;
+
+	/*
+	 * Copy the information in the doorbell page into the event injection
+	 * fields to complete the cancellation flow.
+	 */
+	hvdb = map_hvdb(vcpu, &hvdb_map);
+	if (!hvdb)
+		return;
+
+	if (!hvdb->events.pending_events) {
+		/* No pending events, then event_inj field should be 0 */
+		WARN_ON_ONCE(svm->vmcb->control.event_inj);
+		goto out;
+	}
+
+	/* Copy info back into event_inj field (replaces #HV) */
+	svm->vmcb->control.event_inj = SVM_EVTINJ_VALID;
+
+	if (hvdb->events.vector)
+		svm->vmcb->control.event_inj |= hvdb->events.vector |
+						SVM_EVTINJ_TYPE_INTR;
+
+	hvdb->events.pending_events = 0;
+
+out:
+	unmap_hvdb(vcpu, &hvdb_map);
+}
+
+/*
+* sev_snp_blocked() is for each vector - interrupt, nmi and mce,
+* for example, it is checking if there is an interrupt handled or not by
+* the guest when another interrupt is pending. So hvdb->events.vector will
+* be used for checking. While no_further_signal is signaling to the guest
+* that a #HV is presented by the hypervisor. So no_further_signal is checked
+* when a #HV needs to be presented to the guest.
+*/
+bool sev_snp_blocked(enum inject_type type, struct kvm_vcpu *vcpu)
+{
+	struct kvm_host_map hvdb_map;
+	struct hvdb *hvdb;
+	bool blocked;
+
+	/* Indicate interrupts are blocked if doorbell page can't be mapped */
+	hvdb = map_hvdb(vcpu, &hvdb_map);
+	if (!hvdb)
+		return true;
+
+	/* Indicate interrupts blocked based on guest acknowledgment */
+	blocked = !!hvdb->events.vector;
+
+	unmap_hvdb(vcpu, &hvdb_map);
+
+	return blocked;
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index dd15cc635655..99f35a54b6ad 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -467,6 +467,9 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu)
 	    svm_update_soft_interrupt_rip(vcpu))
 		return;
 
+	if (sev_snp_queue_exception(vcpu))
+		return;
+
 	svm->vmcb->control.event_inj = ex->vector
 		| SVM_EVTINJ_VALID
 		| (ex->has_error_code ? SVM_EVTINJ_VALID_ERR : 0)
@@ -3679,10 +3682,12 @@ static void svm_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
 
 	trace_kvm_inj_virq(vcpu->arch.interrupt.nr,
 			   vcpu->arch.interrupt.soft, reinjected);
-	++vcpu->stat.irq_injections;
 
-	svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
-				       SVM_EVTINJ_VALID | type;
+	if (!sev_snp_inject(INJECT_IRQ, vcpu))
+		svm->vmcb->control.event_inj = vcpu->arch.interrupt.nr |
+						SVM_EVTINJ_VALID | type;
+
+	++vcpu->stat.irq_injections;
 }
 
 void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
@@ -3827,6 +3832,9 @@ bool svm_interrupt_blocked(struct kvm_vcpu *vcpu)
 	if (!gif_set(svm))
 		return true;
 
+	if (sev_snp_is_rinj_active(vcpu))
+		return sev_snp_blocked(INJECT_IRQ, vcpu);
+
 	if (is_guest_mode(vcpu)) {
 		/* As long as interrupts are being delivered...  */
 		if ((svm->nested.ctl.int_ctl & V_INTR_MASKING_MASK)
@@ -4145,6 +4153,8 @@ static void svm_cancel_injection(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 	struct vmcb_control_area *control = &svm->vmcb->control;
 
+	sev_snp_cancel_injection(vcpu);
+
 	control->exit_int_info = control->event_inj;
 	control->exit_int_info_err = control->event_inj_err;
 	control->event_inj = 0;
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 161bd32b87ad..724e0b197b2c 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -55,6 +55,10 @@ extern bool x2avic_enabled;
 extern bool vnmi;
 extern int lbrv;
 
+enum inject_type {
+	INJECT_IRQ,
+};
+
 /*
  * Clean bits in VMCB.
  * VMCB_ALL_CLEAN_MASK might also need to
@@ -765,6 +769,17 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
 int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
 void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
 int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+bool sev_snp_queue_exception(struct kvm_vcpu *vcpu);
+bool sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu);
+void sev_snp_cancel_injection(struct kvm_vcpu *vcpu);
+bool sev_snp_blocked(enum inject_type type, struct kvm_vcpu *vcpu);
+static inline bool sev_snp_is_rinj_active(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sev_info *sev = &to_kvm_svm(vcpu->kvm)->sev_info;
+
+	return sev_snp_guest(vcpu->kvm) &&
+		(sev->vmsa_features & SVM_SEV_FEAT_RESTRICTED_INJECTION);
+};
 #else
 static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
 {
@@ -795,7 +810,11 @@ static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
 {
 	return 0;
 }
-
+static inline bool sev_snp_queue_exception(struct kvm_vcpu *vcpu) { return false; }
+static inline bool sev_snp_inject(enum inject_type type, struct kvm_vcpu *vcpu) { return false; }
+static inline void sev_snp_cancel_injection(struct kvm_vcpu *vcpu) {}
+static inline bool sev_snp_blocked(enum inject_type type, struct kvm_vcpu *vcpu) { return false; }
+static inline bool sev_snp_is_rinj_active(struct kvm_vcpu *vcpu) { return false; }
 #endif
 
 /* vmenter.S */
-- 
2.34.1