KVM: fix bad user ABI for KVM_EXIT_SYSTEM_EVENT

When KVM_EXIT_SYSTEM_EVENT was introduced, it included a flags
member that at the time was unused.  Unfortunately this extensibility
mechanism has several issues:

- x86 is not writing the member, so it would not be possible to use it
  on x86 except for new events

- the member is not aligned to 64 bits, so the definition of the
  uAPI struct is incorrect for 32- on 64-bit userspace.  This is a
  problem for RISC-V, which supports CONFIG_KVM_COMPAT, but fortunately
  usage of flags was only introduced in 5.18.

Since padding has to be introduced, place a new field in there
that tells if the flags field is valid.  To allow further extensibility,
in fact, change flags to an array of 16 values, and store how many
of the values are valid.  The availability of the new ndata field
is tied to a system capability; all architectures are changed to
fill in the field.

To avoid breaking compilation of userspace that was using the flags
field, provide a userspace-only union to overlap flags with data[0].
The new field is placed at the same offset for both 32- and 64-bit
userspace.

Cc: Will Deacon <will@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Peter Gonda <pgonda@google.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Reported-by: kernel test robot <lkp@intel.com>
Message-Id: <20220422103013.34832-1-pbonzini@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virt/kvm/api.rst

@@ -5986,16 +5986,16 @@ should put the acknowledged interrupt vector into the 'epr' field.
   #define KVM_SYSTEM_EVENT_RESET          2
   #define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
-			__u64 flags;
+                        __u32 ndata;
+                        __u64 data[16];
 		} system_event;
 
 If exit_reason is KVM_EXIT_SYSTEM_EVENT then the vcpu has triggered
 a system-level event using some architecture specific mechanism (hypercall
 or some special instruction). In case of ARM64, this is triggered using
-HVC instruction based PSCI call from the vcpu. The 'type' field describes
-the system-level event type. The 'flags' field describes architecture
-specific flags for the system-level event.
+HVC instruction based PSCI call from the vcpu.
 
+The 'type' field describes the system-level event type.
 Valid values for 'type' are:
 
  - KVM_SYSTEM_EVENT_SHUTDOWN -- the guest has requested a shutdown of the
@@ -6010,10 +6010,20 @@ Valid values for 'type' are:
    to ignore the request, or to gather VM memory core dump and/or
    reset/shutdown of the VM.
 
-Valid flags are:
+If KVM_CAP_SYSTEM_EVENT_DATA is present, the 'data' field can contain
+architecture specific information for the system-level event.  Only
+the first `ndata` items (possibly zero) of the data array are valid.
+
+ - for arm64, data[0] is set to KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 if
+   the guest issued a SYSTEM_RESET2 call according to v1.1 of the PSCI
+   specification.
+
+ - for RISC-V, data[0] is set to the value of the second argument of the
+   ``sbi_system_reset`` call.
 
- - KVM_SYSTEM_EVENT_RESET_FLAG_PSCI_RESET2 (arm64 only) -- the guest issued
-   a SYSTEM_RESET2 call according to v1.1 of the PSCI specification.
+Previous versions of Linux defined a `flags` member in this struct.  The
+field is now aliased to `data[0]`.  Userspace can assume that it is only
+written if ndata is greater than 0.
 
 ::
 

arch/arm64/kvm/psci.c

@@ -181,7 +181,8 @@ static void kvm_prepare_system_event(struct kvm_vcpu *vcpu, u32 type, u64 flags)
 
 	memset(&vcpu->run->system_event, 0, sizeof(vcpu->run->system_event));
 	vcpu->run->system_event.type = type;
-	vcpu->run->system_event.flags = flags;
+	vcpu->run->system_event.ndata = 1;
+	vcpu->run->system_event.data[0] = flags;
 	vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }
 

arch/riscv/kvm/vcpu_sbi.c

@@ -83,7 +83,7 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
 
 void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 				     struct kvm_run *run,
-				     u32 type, u64 flags)
+				     u32 type, u64 reason)
 {
 	unsigned long i;
 	struct kvm_vcpu *tmp;
@@ -94,7 +94,8 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 
 	memset(&run->system_event, 0, sizeof(run->system_event));
 	run->system_event.type = type;
-	run->system_event.flags = flags;
+	run->system_event.ndata = 1;
+	run->system_event.data[0] = reason;
 	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }
 

arch/x86/kvm/x86.c

@@ -10015,12 +10015,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		if (kvm_check_request(KVM_REQ_HV_CRASH, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_CRASH;
+			vcpu->run->system_event.ndata = 0;
 			r = 0;
 			goto out;
 		}
 		if (kvm_check_request(KVM_REQ_HV_RESET, vcpu)) {
 			vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 			vcpu->run->system_event.type = KVM_SYSTEM_EVENT_RESET;
+			vcpu->run->system_event.ndata = 0;
 			r = 0;
 			goto out;
 		}

include/uapi/linux/kvm.h

@@ -445,7 +445,13 @@ struct kvm_run {
 #define KVM_SYSTEM_EVENT_RESET          2
 #define KVM_SYSTEM_EVENT_CRASH          3
 			__u32 type;
+			__u32 ndata;
+			union {
+#ifndef __KERNEL__
 				__u64 flags;
+#endif
+				__u64 data[16];
+			};
 		} system_event;
 		/* KVM_EXIT_S390_STSI */
 		struct {
@@ -1144,6 +1150,8 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_MEM_OP_EXTENSION 211
 #define KVM_CAP_PMU_CAPABILITY 212
 #define KVM_CAP_DISABLE_QUIRKS2 213
+/* #define KVM_CAP_VM_TSC_CONTROL 214 */
+#define KVM_CAP_SYSTEM_EVENT_DATA 215
 
 #ifdef KVM_CAP_IRQ_ROUTING
 

virt/kvm/kvm_main.c

@@ -4333,6 +4333,7 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg)
 		return 0;
 #endif
 	case KVM_CAP_BINARY_STATS_FD:
+	case KVM_CAP_SYSTEM_EVENT_DATA:
 		return 1;
 	default:
 		break;