Set injected-event data when injecting a #PF, #DB, or #NM caused
by extended feature disable using FRED event delivery, and save
original-event data for being used as injected-event data.
Unlike IDT using some extra CPU register as part of an event
context, e.g., %cr2 for #PF, FRED saves a complete event context
in its stack frame, e.g., FRED saves the faulting linear address
of a #PF into the event data field defined in its stack frame.
Thus a new VMX control field called injected-event data is added
to provide the event data that will be pushed into a FRED stack
frame for VM entries that inject an event using FRED event delivery.
In addition, a new VM exit information field called original-event
data is added to store the event data that would have saved into a
FRED stack frame for VM exits that occur during FRED event delivery.
After such a VM exit is handled to allow the original-event to be
delivered, the data in the original-event data VMCS field needs to
be set into the injected-event data VMCS field for the injection of
the original event.
Signed-off-by: Xin Li <xin3.li@xxxxxxxxx>
Tested-by: Shan Kang <shan.kang@xxxxxxxxx>
---
Change since v1:
* Document event data should be equal to CR2/DR6/IA32_XFD_ERR instead
of using WARN_ON() (Chao Gao).
* Zero event data if a #NM was not caused by extended feature disable
(Chao Gao).
---
arch/x86/include/asm/vmx.h | 4 ++
arch/x86/kvm/vmx/vmx.c | 109 ++++++++++++++++++++++++++++---------
arch/x86/kvm/vmx/vmx.h | 1 +
arch/x86/kvm/x86.c | 10 +++-
4 files changed, 95 insertions(+), 29 deletions(-)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 4889754415b5..6b796c5c9c2b 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -256,8 +256,12 @@ enum vmcs_field {
PID_POINTER_TABLE_HIGH = 0x00002043,
SECONDARY_VM_EXIT_CONTROLS = 0x00002044,
SECONDARY_VM_EXIT_CONTROLS_HIGH = 0x00002045,
+ INJECTED_EVENT_DATA = 0x00002052,
+ INJECTED_EVENT_DATA_HIGH = 0x00002053,
GUEST_PHYSICAL_ADDRESS = 0x00002400,
GUEST_PHYSICAL_ADDRESS_HIGH = 0x00002401,
+ ORIGINAL_EVENT_DATA = 0x00002404,
+ ORIGINAL_EVENT_DATA_HIGH = 0x00002405,
VMCS_LINK_POINTER = 0x00002800,
VMCS_LINK_POINTER_HIGH = 0x00002801,
GUEST_IA32_DEBUGCTL = 0x00002802,
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index ee61d2c25cb0..f622fb90a098 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1871,9 +1871,29 @@ static void vmx_inject_exception(struct kvm_vcpu *vcpu)
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
vmx->vcpu.arch.event_exit_inst_len);
intr_info |= INTR_TYPE_SOFT_EXCEPTION;
- } else
+ } else {
intr_info |= INTR_TYPE_HARD_EXCEPTION;
+ if (kvm_is_fred_enabled(vcpu)) {
+ u64 event_data = 0;
+
+ if (is_debug(intr_info))
+ /*
+ * Compared to DR6, FRED #DB event data saved on
+ * the stack frame have bits 4 ~ 11 and 16 ~ 31
+ * inverted, i.e.,
+ * fred_db_event_data = dr6 ^ 0xFFFF0FF0UL
+ */
+ event_data = vcpu->arch.dr6 ^ DR6_RESERVED;
+ else if (is_page_fault(intr_info))
+ event_data = vcpu->arch.cr2;
+ else if (is_nm_fault(intr_info))
+ event_data = to_vmx(vcpu)->fred_xfd_event_data;
+
+ vmcs_write64(INJECTED_EVENT_DATA, event_data);
+ }
+ }
+
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, intr_info);
vmx_clear_hlt(vcpu);
@@ -7082,8 +7102,11 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
*
* Queuing exception is done in vmx_handle_exit. See comment there.
*/
- if (vcpu->arch.guest_fpu.fpstate->xfd)
+ if (vcpu->arch.guest_fpu.fpstate->xfd) {
rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+ to_vmx(vcpu)->fred_xfd_event_data = vcpu->arch.cr0 & X86_CR0_TS
+ ? 0 : vcpu->arch.guest_fpu.xfd_err;
+ }
}
static void handle_exception_irqoff(struct vcpu_vmx *vmx)
@@ -7199,29 +7222,28 @@ static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
vmx->loaded_vmcs->entry_time));
}
-static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
- u32 idt_vectoring_info,
- int instr_len_field,
- int error_code_field)
+static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu, bool vectoring)
{
- u8 vector;
- int type;
- bool idtv_info_valid;
-
- idtv_info_valid = idt_vectoring_info & VECTORING_INFO_VALID_MASK;
+ u32 event_id = vectoring ? to_vmx(vcpu)->idt_vectoring_info
+ : vmcs_read32(VM_ENTRY_INTR_INFO_FIELD);
+ int instr_len_field = vectoring ? VM_EXIT_INSTRUCTION_LEN
+ : VM_ENTRY_INSTRUCTION_LEN;
+ int error_code_field = vectoring ? IDT_VECTORING_ERROR_CODE
+ : VM_ENTRY_EXCEPTION_ERROR_CODE;
+ int event_data_field = vectoring ? ORIGINAL_EVENT_DATA
+ : INJECTED_EVENT_DATA;
+ u8 vector = event_id & INTR_INFO_VECTOR_MASK;
+ int type = event_id & INTR_INFO_INTR_TYPE_MASK;
vcpu->arch.nmi_injected = false;
kvm_clear_exception_queue(vcpu);
kvm_clear_interrupt_queue(vcpu);
- if (!idtv_info_valid)
+ if (!(event_id & INTR_INFO_VALID_MASK))
return;
kvm_make_request(KVM_REQ_EVENT, vcpu);
- vector = idt_vectoring_info & VECTORING_INFO_VECTOR_MASK;
- type = idt_vectoring_info & VECTORING_INFO_TYPE_MASK;
-
switch (type) {
case INTR_TYPE_NMI_INTR:
vcpu->arch.nmi_injected = true;
@@ -7236,10 +7258,31 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
vcpu->arch.event_exit_inst_len = vmcs_read32(instr_len_field);
fallthrough;
case INTR_TYPE_HARD_EXCEPTION:
- if (idt_vectoring_info & VECTORING_INFO_DELIVER_CODE_MASK) {
- u32 err = vmcs_read32(error_code_field);
- kvm_requeue_exception_e(vcpu, vector, err);
- } else
+ if (kvm_is_fred_enabled(vcpu)) {
+ /* Save event data for being used as injected-event data */
+ u64 event_data = vmcs_read64(event_data_field);
+
+ switch (vector) {
+ case DB_VECTOR:
+ /* %dr6 should be equal to (event_data ^ DR6_RESERVED) */
+ vcpu->arch.dr6 = event_data ^ DR6_RESERVED;
+ break;
+ case NM_VECTOR:
+ to_vmx(vcpu)->fred_xfd_event_data = event_data;
+ break;
+ case PF_VECTOR:
+ /* %cr2 should be equal to event_data */
+ vcpu->arch.cr2 = event_data;
+ break;
+ default:
+ WARN_ON(event_data != 0);
+ break;
+ }
+ }
+
+ if (event_id & INTR_INFO_DELIVER_CODE_MASK)
+ kvm_requeue_exception_e(vcpu, vector, vmcs_read32(error_code_field));
+ else
kvm_requeue_exception(vcpu, vector);
break;
case INTR_TYPE_SOFT_INTR:
@@ -7255,18 +7298,12 @@ static void __vmx_complete_interrupts(struct kvm_vcpu *vcpu,
static void vmx_complete_interrupts(struct vcpu_vmx *vmx)
{
- __vmx_complete_interrupts(&vmx->vcpu, vmx->idt_vectoring_info,
- VM_EXIT_INSTRUCTION_LEN,
- IDT_VECTORING_ERROR_CODE);
+ __vmx_complete_interrupts(&vmx->vcpu, true);
}
static void vmx_cancel_injection(struct kvm_vcpu *vcpu)
{
- __vmx_complete_interrupts(vcpu,
- vmcs_read32(VM_ENTRY_INTR_INFO_FIELD),
- VM_ENTRY_INSTRUCTION_LEN,
- VM_ENTRY_EXCEPTION_ERROR_CODE);
-
+ __vmx_complete_interrupts(vcpu, false);
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
@@ -7382,6 +7419,24 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vmx_disable_fb_clear(vmx);
+ /*
+ * %cr2 needs to be saved after a VM exit and restored before a VM
+ * entry in case a VM exit happens immediately after delivery of a
+ * guest #PF but before guest reads %cr2.
+ *
+ * A FRED guest should read its #PF faulting linear address from
+ * the event data field in its FRED stack frame instead of %cr2.
+ * But the FRED 5.0 spec still requires a FRED CPU to update %cr2
+ * in the normal way, thus %cr2 is still updated even for a FRED
+ * guest.
+ *
+ * Note, an NMI could interrupt KVM:
+ * 1) after VM exit but before CR2 is saved.
+ * 2) after CR2 is restored but before VM entry.
+ * And a #PF could happen durng NMI handlng, which overwrites %cr2.
+ * Thus exc_nmi() should save and restore %cr2 upon entering and
+ * before leaving to make sure %cr2 not corrupted.
+ */
if (vcpu->arch.cr2 != native_read_cr2())
native_write_cr2(vcpu->arch.cr2);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 176ad39be406..d5738c5a4814 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -266,6 +266,7 @@ struct vcpu_vmx {
u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
+ u64 fred_xfd_event_data;
/*
* User return MSRs are always emulated when enabled in the guest, but
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4e8d60f248e3..00c0062726ae 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -680,8 +680,14 @@ static void kvm_multiple_exception(struct kvm_vcpu *vcpu,
vcpu->arch.exception.injected = true;
if (WARN_ON_ONCE(has_payload)) {
/*
- * A reinjected event has already
- * delivered its payload.
+ * For a reinjected event, KVM delivers its
+ * payload through:
+ * #PF: save %cr2 into arch.cr2 immediately
+ * after VM exits.
+ * #DB: save %dr6 into arch.dr6 later in
+ * sync_dirty_debug_regs().
+ *
+ * For FRED guest, see __vmx_complete_interrupts().
*/
has_payload = false;
payload = 0;
--
2.43.0
