x86/vm_event: add support for VM_EVENT_REASON_INTERRUPT

Added support for a new event type, VM_EVENT_REASON_INTERRUPT,
which is now fired in a one-shot manner when enabled via the new
VM_EVENT_FLAG_GET_NEXT_INTERRUPT vm_event response flag.
The patch also fixes the behaviour of the xc_hvm_inject_trap()
hypercall, which would lead to non-architectural interrupts
overwriting pending (specifically reinjected) architectural ones.

Signed-off-by: Razvan Cojocaru <rcojocaru@bitdefender.com>
Acked-by: Tamas K Lengyel <tamas@tklengyel.com>
Acked-by: Jan Beulich <jbeulich@suse.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>
Acked-by: Julien Grall <julien.grall@arm.com>

xen/arch/arm/vm_event.c

@@ -42,6 +42,11 @@ void vm_event_set_registers(struct vcpu *v, vm_event_response_t *rsp)
     regs->pc = rsp->data.regs.arm.pc;
 }
 
+void vm_event_monitor_next_interrupt(struct vcpu *v)
+{
+    /* Not supported on ARM. */
+}
+
 /*
  * Local variables:
  * mode: C

xen/arch/x86/hvm/hvm.c

@@ -469,6 +469,12 @@ void hvm_migrate_pirqs(struct vcpu *v)
     spin_unlock(&d->event_lock);
 }
 
+static bool hvm_get_pending_event(struct vcpu *v, struct x86_event *info)
+{
+    info->cr2 = v->arch.hvm_vcpu.guest_cr[2];
+    return hvm_funcs.get_pending_event(v, info);
+}
+
 void hvm_do_resume(struct vcpu *v)
 {
     check_wakeup_from_wait();
@@ -535,9 +541,23 @@ void hvm_do_resume(struct vcpu *v)
     /* Inject pending hw/sw trap */
     if ( v->arch.hvm_vcpu.inject_trap.vector != -1 )
     {
-        hvm_inject_event(&v->arch.hvm_vcpu.inject_trap);
+        if ( !hvm_event_pending(v) )
+            hvm_inject_event(&v->arch.hvm_vcpu.inject_trap);
+
         v->arch.hvm_vcpu.inject_trap.vector = -1;
     }
+
+    if ( unlikely(v->arch.vm_event) && v->arch.monitor.next_interrupt_enabled )
+    {
+        struct x86_event info;
+
+        if ( hvm_get_pending_event(v, &info) )
+        {
+            hvm_monitor_interrupt(info.vector, info.type, info.error_code,
+                                  info.cr2);
+            v->arch.monitor.next_interrupt_enabled = false;
+        }
+    }
 }
 
 static int hvm_print_line(

xen/arch/x86/hvm/monitor.c

@@ -149,6 +149,20 @@ int hvm_monitor_cpuid(unsigned long insn_length, unsigned int leaf,
     return monitor_traps(curr, 1, &req);
 }
 
+void hvm_monitor_interrupt(unsigned int vector, unsigned int type,
+                           unsigned int err, uint64_t cr2)
+{
+    vm_event_request_t req = {
+        .reason = VM_EVENT_REASON_INTERRUPT,
+        .u.interrupt.x86.vector = vector,
+        .u.interrupt.x86.type = type,
+        .u.interrupt.x86.error_code = err,
+        .u.interrupt.x86.cr2 = cr2,
+    };
+
+    monitor_traps(current, 1, &req);
+}
+
 /*
  * Local variables:
  * mode: C

xen/arch/x86/hvm/svm/svm.c

@@ -2184,6 +2184,20 @@ static void svm_invlpg(struct vcpu *v, unsigned long vaddr)
     svm_asid_g_invlpg(v, vaddr);
 }
 
+static bool svm_get_pending_event(struct vcpu *v, struct x86_event *info)
+{
+    const struct vmcb_struct *vmcb = v->arch.hvm_svm.vmcb;
+
+    if ( vmcb->eventinj.fields.v )
+        return false;
+
+    info->vector = vmcb->eventinj.fields.vector;
+    info->type = vmcb->eventinj.fields.type;
+    info->error_code = vmcb->eventinj.fields.errorcode;
+
+    return true;
+}
+
 static struct hvm_function_table __initdata svm_function_table = {
     .name                 = "SVM",
     .cpu_up_prepare       = svm_cpu_up_prepare,
@@ -2215,6 +2229,7 @@ static struct hvm_function_table __initdata svm_function_table = {
     .inject_event         = svm_inject_event,
     .init_hypercall_page  = svm_init_hypercall_page,
     .event_pending        = svm_event_pending,
+    .get_pending_event    = svm_get_pending_event,
     .invlpg               = svm_invlpg,
     .wbinvd_intercept     = svm_wbinvd_intercept,
     .fpu_dirty_intercept  = svm_fpu_dirty_intercept,

xen/arch/x86/hvm/vmx/vmx.c

@@ -2072,6 +2072,25 @@ static int vmx_set_mode(struct vcpu *v, int mode)
     return 0;
 }
 
+static bool vmx_get_pending_event(struct vcpu *v, struct x86_event *info)
+{
+    unsigned long intr_info, error_code;
+
+    vmx_vmcs_enter(v);
+    __vmread(VM_ENTRY_INTR_INFO, &intr_info);
+    __vmread(VM_ENTRY_EXCEPTION_ERROR_CODE, &error_code);
+    vmx_vmcs_exit(v);
+
+    if ( !(intr_info & INTR_INFO_VALID_MASK) )
+        return false;
+
+    info->vector = MASK_EXTR(intr_info, INTR_INFO_VECTOR_MASK);
+    info->type = MASK_EXTR(intr_info, INTR_INFO_INTR_TYPE_MASK);
+    info->error_code = error_code;
+
+    return true;
+}
+
 static struct hvm_function_table __initdata vmx_function_table = {
     .name                 = "VMX",
     .cpu_up_prepare       = vmx_cpu_up_prepare,
@@ -2102,6 +2121,7 @@ static struct hvm_function_table __initdata vmx_function_table = {
     .inject_event         = vmx_inject_event,
     .init_hypercall_page  = vmx_init_hypercall_page,
     .event_pending        = vmx_event_pending,
+    .get_pending_event    = vmx_get_pending_event,
     .invlpg               = vmx_invlpg,
     .cpu_up               = vmx_cpu_up,
     .cpu_down             = vmx_cpu_down,

xen/arch/x86/vm_event.c

@@ -134,6 +134,11 @@ void vm_event_set_registers(struct vcpu *v, vm_event_response_t *rsp)
     v->arch.user_regs.eip = rsp->data.regs.x86.rip;
 }
 
+void vm_event_monitor_next_interrupt(struct vcpu *v)
+{
+    v->arch.monitor.next_interrupt_enabled = true;
+}
+
 void vm_event_fill_regs(vm_event_request_t *req)
 {
     const struct cpu_user_regs *regs = guest_cpu_user_regs();

xen/common/vm_event.c

@@ -433,6 +433,9 @@ void vm_event_resume(struct domain *d, struct vm_event_domain *ved)
             if ( rsp.flags & VM_EVENT_FLAG_SET_REGISTERS )
                 vm_event_set_registers(v, &rsp);
 
+            if ( rsp.flags & VM_EVENT_FLAG_GET_NEXT_INTERRUPT )
+                vm_event_monitor_next_interrupt(v);
+
             if ( rsp.flags & VM_EVENT_FLAG_VCPU_PAUSED )
                 vm_event_vcpu_unpause(v);
         }

xen/include/asm-x86/domain.h

@@ -577,6 +577,10 @@ struct arch_vcpu
     XEN_GUEST_HANDLE(vcpu_time_info_t) time_info_guest;
 
     struct arch_vm_event *vm_event;
+
+    struct {
+        bool next_interrupt_enabled;
+    } monitor;
 };
 
 smap_check_policy_t smap_policy_change(struct vcpu *v,

xen/include/asm-x86/hvm/hvm.h

@@ -150,6 +150,7 @@ struct hvm_function_table {
     void (*init_hypercall_page)(struct domain *d, void *hypercall_page);
 
     int  (*event_pending)(struct vcpu *v);
+    bool (*get_pending_event)(struct vcpu *v, struct x86_event *info);
     void (*invlpg)(struct vcpu *v, unsigned long vaddr);
 
     int  (*cpu_up_prepare)(unsigned int cpu);

xen/include/asm-x86/hvm/monitor.h

@@ -42,6 +42,8 @@ int hvm_monitor_debug(unsigned long rip, enum hvm_monitor_debug_type type,
                       unsigned long trap_type, unsigned long insn_length);
 int hvm_monitor_cpuid(unsigned long insn_length, unsigned int leaf,
                       unsigned int subleaf);
+void hvm_monitor_interrupt(unsigned int vector, unsigned int type,
+                           unsigned int err, uint64_t cr2);
 
 #endif /* __ASM_X86_HVM_MONITOR_H__ */
 

xen/include/asm-x86/monitor.h

@@ -76,7 +76,8 @@ static inline uint32_t arch_monitor_get_capabilities(struct domain *d)
                    (1U << XEN_DOMCTL_MONITOR_EVENT_SOFTWARE_BREAKPOINT) |
                    (1U << XEN_DOMCTL_MONITOR_EVENT_GUEST_REQUEST) |
                    (1U << XEN_DOMCTL_MONITOR_EVENT_DEBUG_EXCEPTION) |
-                   (1U << XEN_DOMCTL_MONITOR_EVENT_CPUID);
+                   (1U << XEN_DOMCTL_MONITOR_EVENT_CPUID) |
+                   (1U << XEN_DOMCTL_MONITOR_EVENT_INTERRUPT);
 
     /* Since we know this is on VMX, we can just call the hvm func */
     if ( hvm_is_singlestep_supported() )

xen/include/public/domctl.h

@@ -1086,6 +1086,7 @@ DEFINE_XEN_GUEST_HANDLE(xen_domctl_psr_cmt_op_t);
 #define XEN_DOMCTL_MONITOR_EVENT_DEBUG_EXCEPTION       5
 #define XEN_DOMCTL_MONITOR_EVENT_CPUID                 6
 #define XEN_DOMCTL_MONITOR_EVENT_PRIVILEGED_CALL       7
+#define XEN_DOMCTL_MONITOR_EVENT_INTERRUPT             8
 
 struct xen_domctl_monitor_op {
     uint32_t op; /* XEN_DOMCTL_MONITOR_OP_* */

xen/include/public/vm_event.h

@@ -105,6 +105,11 @@
  * if any of those flags are set, only those will be honored).
  */
 #define VM_EVENT_FLAG_SET_EMUL_INSN_DATA (1 << 9)
+/*
+ * Have a one-shot VM_EVENT_REASON_INTERRUPT event sent for the first
+ * interrupt pending after resuming the VCPU.
+ */
+#define VM_EVENT_FLAG_GET_NEXT_INTERRUPT (1 << 10)
 
 /*
  * Reasons for the vm event request
@@ -139,6 +144,8 @@
  *       These kinds of events will be filtered out in future versions.
  */
 #define VM_EVENT_REASON_PRIVILEGED_CALL         11
+/* An interrupt has been delivered. */
+#define VM_EVENT_REASON_INTERRUPT               12
 
 /* Supported values for the vm_event_write_ctrlreg index. */
 #define VM_EVENT_X86_CR0    0
@@ -259,6 +266,14 @@ struct vm_event_cpuid {
     uint32_t _pad;
 };
 
+struct vm_event_interrupt_x86 {
+    uint32_t vector;
+    uint32_t type;
+    uint32_t error_code;
+    uint32_t _pad;
+    uint64_t cr2;
+};
+
 #define MEM_PAGING_DROP_PAGE       (1 << 0)
 #define MEM_PAGING_EVICT_FAIL      (1 << 1)
 
@@ -302,6 +317,9 @@ typedef struct vm_event_st {
         struct vm_event_debug                 software_breakpoint;
         struct vm_event_debug                 debug_exception;
         struct vm_event_cpuid                 cpuid;
+        union {
+            struct vm_event_interrupt_x86     x86;
+        } interrupt;
     } u;
 
     union {

xen/include/xen/vm_event.h

@@ -78,6 +78,8 @@ void vm_event_vcpu_unpause(struct vcpu *v);
 void vm_event_fill_regs(vm_event_request_t *req);
 void vm_event_set_registers(struct vcpu *v, vm_event_response_t *rsp);
 
+void vm_event_monitor_next_interrupt(struct vcpu *v);
+
 #endif /* __VM_EVENT_H__ */
 
 /*