[PATCH v3 0/3] Enable notify VM exit

[PATCH v3 0/3] Enable notify VM exit

[Chenyi Qiang]

Notify VM exit is introduced to mitigate the potential DOS attach from
malicious VM. This series is the userspace part to enable this feature
through a new KVM capability KVM_CAP_X86_NOTIFY_VMEXIT. The detailed
info can be seen in Patch 3.

The corresponding KVM patches are avaiable at:
https://lore.kernel.org/lkml/20220421072958.16375-1-chenyi.qiang@intel.com/

---
Change logs:
v2 -> v3
- Extend the argument to include both the notify window and some flags
  when enabling KVM_CAP_X86_BUS_LOCK_EXIT CAP.
- Change to use KVM_VCPUEVENTS_VALID_TRIPLE_FAULT in flags field and add
  pending_triple_fault field in struct kvm_vcpu_events.
- v2: https://lore.kernel.org/qemu-devel/20220318082934.25030-1-chenyi.qiang@intel.com/

v1 -> v2
- Add some commit message to explain why we disable Notify VM exit by default.
- Rename KVM_VCPUEVENT_SHUTDOWN to KVM_VCPUEVENT_TRIPLE_FAULT.
- Do the corresponding change to use the KVM_VCPUEVENTS_TRIPLE_FAULT
  to save/restore the triple fault event to avoid lose some synthesized
  triple fault from KVM.
- v1: https://lore.kernel.org/qemu-devel/20220310090205.10645-1-chenyi.qiang@intel.com/

---

Chenyi Qiang (3):
  linux-header: update linux header
  i386: kvm: Save&restore triple fault event
  i386: Add notify VM exit support

 hw/i386/x86.c               | 45 ++++++++++++++++++++++++
 include/hw/i386/x86.h       |  5 +++
 linux-headers/asm-x86/kvm.h |  4 ++-
 linux-headers/linux/kvm.h   | 10 ++++++
 target/i386/cpu.c           |  1 +
 target/i386/cpu.h           |  1 +
 target/i386/kvm/kvm.c       | 70 ++++++++++++++++++++++++++-----------
 7 files changed, 114 insertions(+), 22 deletions(-)

-- 
2.17.1

[PATCH v3 1/3] linux-header: update linux header

[Chenyi Qiang]

This linux-header update is only a reference to include some definitions
related to notify VM exit.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
---
 linux-headers/asm-x86/kvm.h |  4 +++-
 linux-headers/linux/kvm.h   | 10 ++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/linux-headers/asm-x86/kvm.h b/linux-headers/asm-x86/kvm.h
index bf6e96011d..41541561ed 100644
--- a/linux-headers/asm-x86/kvm.h
+++ b/linux-headers/asm-x86/kvm.h
@@ -325,6 +325,7 @@ struct kvm_reinject_control {
 #define KVM_VCPUEVENT_VALID_SHADOW	0x00000004
 #define KVM_VCPUEVENT_VALID_SMM		0x00000008
 #define KVM_VCPUEVENT_VALID_PAYLOAD	0x00000010
+#define KVM_VCPUEVENT_VALID_TRIPLE_FAULT	0x00000020
 
 /* Interrupt shadow states */
 #define KVM_X86_SHADOW_INT_MOV_SS	0x01
@@ -359,7 +360,8 @@ struct kvm_vcpu_events {
 		__u8 smm_inside_nmi;
 		__u8 latched_init;
 	} smi;
-	__u8 reserved[27];
+	__u8 triple_fault_pending;
+	__u8 reserved[26];
 	__u8 exception_has_payload;
 	__u64 exception_payload;
 };
diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index d232feaae9..67c0f6a938 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -270,6 +270,7 @@ struct kvm_xen_exit {
 #define KVM_EXIT_X86_BUS_LOCK     33
 #define KVM_EXIT_XEN              34
 #define KVM_EXIT_RISCV_SBI        35
+#define KVM_EXIT_NOTIFY           36
 
 /* For KVM_EXIT_INTERNAL_ERROR */
 /* Emulate instruction failed. */
@@ -487,6 +488,11 @@ struct kvm_run {
 			unsigned long args[6];
 			unsigned long ret[2];
 		} riscv_sbi;
+		/* KVM_EXIT_NOTIFY */
+		struct {
+#define KVM_NOTIFY_CONTEXT_INVALID	(1 << 0)
+			__u32 flags;
+		} notify;
 		/* Fix the size of the union. */
 		char padding[256];
 	};
@@ -1134,6 +1140,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_VM_GPA_BITS 207
 #define KVM_CAP_XSAVE2 208
 #define KVM_CAP_SYS_ATTRIBUTES 209
+#define KVM_CAP_X86_NOTIFY_VMEXIT  215
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -2051,4 +2058,7 @@ struct kvm_stats_desc {
 /* Available with KVM_CAP_XSAVE2 */
 #define KVM_GET_XSAVE2		  _IOR(KVMIO,  0xcf, struct kvm_xsave)
 
+#define KVM_X86_NOTIFY_VMEXIT_ENABLED		(1ULL << 0)
+#define KVM_X86_NOTIFY_VMEXIT_USER		(1ULL << 1)
+
 #endif /* __LINUX_KVM_H */
-- 
2.17.1

[PATCH v3 2/3] i386: kvm: Save&restore triple fault event

[Chenyi Qiang]

For the direct triple faults, i.e. hardware detected and KVM morphed
to VM-Exit, KVM will never lose them. But for triple faults sythesized
by KVM, e.g. the RSM path, if KVM exits to userspace before the request
is serviced, userspace could migrate the VM and lose the triple fault.

A new flag KVM_VCPUEVENT_VALID_TRIPLE_FAULT is defined to signal that
the event.triple_fault_pending field contains a valid state.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
---
 target/i386/cpu.c     | 1 +
 target/i386/cpu.h     | 1 +
 target/i386/kvm/kvm.c | 8 +++++++-
 3 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index cb6b5467d0..276058d52e 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -5998,6 +5998,7 @@ static void x86_cpu_reset(DeviceState *dev)
     env->exception_has_payload = false;
     env->exception_payload = 0;
     env->nmi_injected = false;
+    env->triple_fault_pending = false;
 #if !defined(CONFIG_USER_ONLY)
     /* We hard-wire the BSP to the first CPU. */
     apic_designate_bsp(cpu->apic_state, s->cpu_index == 0);
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 982c532353..a2a9423747 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -1701,6 +1701,7 @@ typedef struct CPUArchState {
     uint8_t has_error_code;
     uint8_t exception_has_payload;
     uint64_t exception_payload;
+    bool triple_fault_pending;
     uint32_t ins_len;
     uint32_t sipi_vector;
     bool tsc_valid;
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index 9cf8e03669..bd44a02f51 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -4099,7 +4099,9 @@ static int kvm_put_vcpu_events(X86CPU *cpu, int level)
     }
 
     if (level >= KVM_PUT_RESET_STATE) {
-        events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING;
+        events.flags |= KVM_VCPUEVENT_VALID_NMI_PENDING |
+                        KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
+        events.triple_fault_pending = env->triple_fault_pending;
         if (env->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
             events.flags |= KVM_VCPUEVENT_VALID_SIPI_VECTOR;
         }
@@ -4174,6 +4176,10 @@ static int kvm_get_vcpu_events(X86CPU *cpu)
         }
     }
 
+    if (events.flags & KVM_VCPUEVENT_VALID_TRIPLE_FAULT) {
+        env->triple_fault_pending = events.triple_fault_pending;
+    }
+
     env->sipi_vector = events.sipi_vector;
 
     return 0;
-- 
2.17.1

[PATCH v3 3/3] i386: Add notify VM exit support

[Chenyi Qiang]

There are cases that malicious virtual machine can cause CPU stuck (due
to event windows don't open up), e.g., infinite loop in microcode when
nested #AC (CVE-2015-5307). No event window means no event (NMI, SMI and
IRQ) can be delivered. It leads the CPU to be unavailable to host or
other VMs. Notify VM exit is introduced to mitigate such kind of
attacks, which will generate a VM exit if no event window occurs in VM
non-root mode for a specified amount of time (notify window).

A new KVM capability KVM_CAP_X86_NOTIFY_VMEXIT is exposed to user space
so that the user can query the capability and set the expected notify
window when creating VMs. The format of the argument when enabling this
capability is as follows:
  Bit 63:32 - notify window specified in qemu command
  Bit 31:0  - some flags (e.g. KVM_X86_NOTIFY_VMEXIT_ENABLED is set to
              enable the feature.)

Because there are some concerns, e.g. a notify VM exit may happen with
VM_CONTEXT_INVALID set in exit qualification (no cases are anticipated
that would set this bit), which means VM context is corrupted. To avoid
the false positive and a well-behaved guest gets killed, make this
feature disabled by default. Users can enable the feature by a new
machine property:
    qemu -machine notify_vmexit=on,notify_window=0 ...

A new KVM exit reason KVM_EXIT_NOTIFY is defined for notify VM exit. If
it happens with VM_INVALID_CONTEXT, hypervisor exits to user space to
inform the fatal case. Then user space can inject a SHUTDOWN event to
the target vcpu. This is implemented by injecting a sythesized triple
fault event.

Signed-off-by: Chenyi Qiang <chenyi.qiang@intel.com>
---
 hw/i386/x86.c         | 45 +++++++++++++++++++++++++++++++
 include/hw/i386/x86.h |  5 ++++
 target/i386/kvm/kvm.c | 62 +++++++++++++++++++++++++++++--------------
 3 files changed, 92 insertions(+), 20 deletions(-)

diff --git a/hw/i386/x86.c b/hw/i386/x86.c
index 4cf107baea..a82f959cb9 100644
--- a/hw/i386/x86.c
+++ b/hw/i386/x86.c
@@ -1296,6 +1296,37 @@ static void machine_set_sgx_epc(Object *obj, Visitor *v, const char *name,
     qapi_free_SgxEPCList(list);
 }
 
+static bool x86_machine_get_notify_vmexit(Object *obj, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+
+    return x86ms->notify_vmexit;
+}
+
+static void x86_machine_set_notify_vmexit(Object *obj, bool value, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+
+    x86ms->notify_vmexit = value;
+}
+
+static void x86_machine_get_notify_window(Object *obj, Visitor *v,
+                                const char *name, void *opaque, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+    uint32_t notify_window = x86ms->notify_window;
+
+    visit_type_uint32(v, name, &notify_window, errp);
+}
+
+static void x86_machine_set_notify_window(Object *obj, Visitor *v,
+                               const char *name, void *opaque, Error **errp)
+{
+    X86MachineState *x86ms = X86_MACHINE(obj);
+
+    visit_type_uint32(v, name, &x86ms->notify_window, errp);
+}
+
 static void x86_machine_initfn(Object *obj)
 {
     X86MachineState *x86ms = X86_MACHINE(obj);
@@ -1306,6 +1337,8 @@ static void x86_machine_initfn(Object *obj)
     x86ms->oem_id = g_strndup(ACPI_BUILD_APPNAME6, 6);
     x86ms->oem_table_id = g_strndup(ACPI_BUILD_APPNAME8, 8);
     x86ms->bus_lock_ratelimit = 0;
+    x86ms->notify_vmexit = false;
+    x86ms->notify_window = 0;
 }
 
 static void x86_machine_class_init(ObjectClass *oc, void *data)
@@ -1361,6 +1394,18 @@ static void x86_machine_class_init(ObjectClass *oc, void *data)
         NULL, NULL);
     object_class_property_set_description(oc, "sgx-epc",
         "SGX EPC device");
+
+    object_class_property_add(oc, X86_MACHINE_NOTIFY_WINDOW, "uint32_t",
+                              x86_machine_get_notify_window,
+                              x86_machine_set_notify_window, NULL, NULL);
+    object_class_property_set_description(oc, X86_MACHINE_NOTIFY_WINDOW,
+            "Set the notify window required by notify VM exit");
+
+    object_class_property_add_bool(oc, X86_MACHINE_NOTIFY_VMEXIT,
+                                   x86_machine_get_notify_vmexit,
+                                   x86_machine_set_notify_vmexit);
+    object_class_property_set_description(oc, X86_MACHINE_NOTIFY_VMEXIT,
+            "Enable notify VM exit");
 }
 
 static const TypeInfo x86_machine_info = {
diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h
index 916cc325ee..571ee8b667 100644
--- a/include/hw/i386/x86.h
+++ b/include/hw/i386/x86.h
@@ -80,6 +80,9 @@ struct X86MachineState {
      * which means no limitation on the guest's bus locks.
      */
     uint64_t bus_lock_ratelimit;
+
+    bool notify_vmexit;
+    uint32_t notify_window;
 };
 
 #define X86_MACHINE_SMM              "smm"
@@ -87,6 +90,8 @@ struct X86MachineState {
 #define X86_MACHINE_OEM_ID           "x-oem-id"
 #define X86_MACHINE_OEM_TABLE_ID     "x-oem-table-id"
 #define X86_MACHINE_BUS_LOCK_RATELIMIT  "bus-lock-ratelimit"
+#define X86_MACHINE_NOTIFY_VMEXIT     "notify-vmexit"
+#define X86_MACHINE_NOTIFY_WINDOW     "notify-window"
 
 #define TYPE_X86_MACHINE   MACHINE_TYPE_NAME("x86")
 OBJECT_DECLARE_TYPE(X86MachineState, X86MachineClass, X86_MACHINE)
diff --git a/target/i386/kvm/kvm.c b/target/i386/kvm/kvm.c
index bd44a02f51..01dbdef8b2 100644
--- a/target/i386/kvm/kvm.c
+++ b/target/i386/kvm/kvm.c
@@ -2344,6 +2344,10 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
     int ret;
     struct utsname utsname;
     Error *local_err = NULL;
+    X86MachineState *x86ms;
+
+    assert(object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE));
+    x86ms = X86_MACHINE(ms);
 
     /*
      * Initialize SEV context, if required
@@ -2439,8 +2443,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
     }
 
     if (kvm_check_extension(s, KVM_CAP_X86_SMM) &&
-        object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE) &&
-        x86_machine_is_smm_enabled(X86_MACHINE(ms))) {
+        x86_machine_is_smm_enabled(x86ms)) {
         smram_machine_done.notify = register_smram_listener;
         qemu_add_machine_init_done_notifier(&smram_machine_done);
     }
@@ -2468,25 +2471,34 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
         }
     }
 
-    if (object_dynamic_cast(OBJECT(ms), TYPE_X86_MACHINE)) {
-        X86MachineState *x86ms = X86_MACHINE(ms);
+    if (x86ms->bus_lock_ratelimit > 0) {
+        ret = kvm_check_extension(s, KVM_CAP_X86_BUS_LOCK_EXIT);
+        if (!(ret & KVM_BUS_LOCK_DETECTION_EXIT)) {
+            error_report("kvm: bus lock detection unsupported");
+            return -ENOTSUP;
+        }
+        ret = kvm_vm_enable_cap(s, KVM_CAP_X86_BUS_LOCK_EXIT, 0,
+                                KVM_BUS_LOCK_DETECTION_EXIT);
+        if (ret < 0) {
+            error_report("kvm: Failed to enable bus lock detection cap: %s",
+                         strerror(-ret));
+            return ret;
+        }
+        ratelimit_init(&bus_lock_ratelimit_ctrl);
+        ratelimit_set_speed(&bus_lock_ratelimit_ctrl,
+                            x86ms->bus_lock_ratelimit, BUS_LOCK_SLICE_TIME);
+    }
 
-        if (x86ms->bus_lock_ratelimit > 0) {
-            ret = kvm_check_extension(s, KVM_CAP_X86_BUS_LOCK_EXIT);
-            if (!(ret & KVM_BUS_LOCK_DETECTION_EXIT)) {
-                error_report("kvm: bus lock detection unsupported");
-                return -ENOTSUP;
-            }
-            ret = kvm_vm_enable_cap(s, KVM_CAP_X86_BUS_LOCK_EXIT, 0,
-                                    KVM_BUS_LOCK_DETECTION_EXIT);
-            if (ret < 0) {
-                error_report("kvm: Failed to enable bus lock detection cap: %s",
-                             strerror(-ret));
-                return ret;
-            }
-            ratelimit_init(&bus_lock_ratelimit_ctrl);
-            ratelimit_set_speed(&bus_lock_ratelimit_ctrl,
-                                x86ms->bus_lock_ratelimit, BUS_LOCK_SLICE_TIME);
+    if (x86ms->notify_vmexit && kvm_check_extension(s, KVM_CAP_X86_NOTIFY_VMEXIT)) {
+        uint64_t notify_window_flags = ((uint64_t)x86ms->notify_window << 32) |
+                                        KVM_X86_NOTIFY_VMEXIT_ENABLED |
+                                        KVM_X86_NOTIFY_VMEXIT_USER;
+        ret = kvm_vm_enable_cap(s, KVM_CAP_X86_NOTIFY_VMEXIT, 0,
+                                notify_window_flags);
+        if (ret < 0) {
+            error_report("kvm: Failed to enable notify vmexit cap: %s",
+                         strerror(-ret));
+            return ret;
         }
     }
 
@@ -4926,6 +4938,7 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
     X86CPU *cpu = X86_CPU(cs);
     uint64_t code;
     int ret;
+    struct kvm_vcpu_events events = {};
 
     switch (run->exit_reason) {
     case KVM_EXIT_HLT:
@@ -4981,6 +4994,15 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
         /* already handled in kvm_arch_post_run */
         ret = 0;
         break;
+    case KVM_EXIT_NOTIFY:
+        ret = 0;
+        if (run->notify.flags & KVM_NOTIFY_CONTEXT_INVALID) {
+            warn_report("KVM: invalid context due to notify vmexit");
+            events.flags |= KVM_VCPUEVENT_VALID_TRIPLE_FAULT;
+            events.triple_fault_pending = true;
+            ret = kvm_vcpu_ioctl(cs, KVM_SET_VCPU_EVENTS, &events);
+        }
+        break;
     default:
         fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
         ret = -1;
-- 
2.17.1