KVM: nVMX: Tweak handling of failure code for nested VM-Enter failure

Use an enum for passing around the failure code for a failed VM-Enter
that results in VM-Exit to provide a level of indirection from the final
resting place of the failure code, vmcs.EXIT_QUALIFICATION.  The exit
qualification field is an unsigned long, e.g. passing around
'u32 exit_qual' throws up red flags as it suggests KVM may be dropping
bits when reporting errors to L1.  This is a red herring because the
only defined failure codes are 0, 2, 3, and 4, i.e. don't come remotely
close to overflowing a u32.

Setting vmcs.EXIT_QUALIFICATION on entry failure is further complicated
by the MSR load list, which returns the (1-based) entry that failed, and
the number of MSRs to load is a 32-bit VMCS field.  At first blush, it
would appear that overflowing a u32 is possible, but the number of MSRs
that can be loaded is hardcapped at 4096 (limited by MSR_IA32_VMX_MISC).

In other words, there are two completely disparate types of data that
eventually get stuffed into vmcs.EXIT_QUALIFICATION, neither of which is
an 'unsigned long' in nature.  This was presumably the reasoning for
switching to 'u32' when the related code was refactored in commit
ca0bde28f2 ("kvm: nVMX: Split VMCS checks from nested_vmx_run()").

Using an enum for the failure code addresses the technically-possible-
but-will-never-happen scenario where Intel defines a failure code that
doesn't fit in a 32-bit integer.  The enum variables and values will
either be automatically sized (gcc 5.4 behavior) or be subjected to some
combination of truncation.  The former case will simply work, while the
latter will trigger a compile-time warning unless the compiler is being
particularly unhelpful.

Separating the failure code from the failed MSR entry allows for
disassociating both from vmcs.EXIT_QUALIFICATION, which avoids the
conundrum where KVM has to choose between 'u32 exit_qual' and tracking
values as 'unsigned long' that have no business being tracked as such.
To cement the split, set vmcs12->exit_qualification directly from the
entry error code or failed MSR index instead of bouncing through a local
variable.

Opportunistically rename the variables in load_vmcs12_host_state() and
vmx_set_nested_state() to call out that they're ignored, set exit_reason
on demand on nested VM-Enter failure, and add a comment in
nested_vmx_load_msr() to call out that returning 'i + 1' can't wrap.

No functional change intended.

Reported-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jim Mattson <jmattson@google.com>
Signed-off-by: Sean Christopherson <sean.j.christopherson@intel.com>
Message-Id: <20200511220529.11402-1-sean.j.christopherson@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Sean Christopherson 2020-05-11 15:05:29 -07:00 committed by Paolo Bonzini
parent e93fd3b3e8
commit 68cda40d9f
2 changed files with 34 additions and 23 deletions

View File

@ -527,10 +527,12 @@ struct vmx_msr_entry {
/* /*
* Exit Qualifications for entry failure during or after loading guest state * Exit Qualifications for entry failure during or after loading guest state
*/ */
#define ENTRY_FAIL_DEFAULT 0 enum vm_entry_failure_code {
#define ENTRY_FAIL_PDPTE 2 ENTRY_FAIL_DEFAULT = 0,
#define ENTRY_FAIL_NMI 3 ENTRY_FAIL_PDPTE = 2,
#define ENTRY_FAIL_VMCS_LINK_PTR 4 ENTRY_FAIL_NMI = 3,
ENTRY_FAIL_VMCS_LINK_PTR = 4,
};
/* /*
* Exit Qualifications for EPT Violations * Exit Qualifications for EPT Violations

View File

@ -922,6 +922,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
} }
return 0; return 0;
fail: fail:
/* Note, max_msr_list_size is at most 4096, i.e. this can't wrap. */
return i + 1; return i + 1;
} }
@ -1117,7 +1118,7 @@ static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu)
* @entry_failure_code. * @entry_failure_code.
*/ */
static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept, static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
u32 *entry_failure_code) enum vm_entry_failure_code *entry_failure_code)
{ {
if (CC(!nested_cr3_valid(vcpu, cr3))) { if (CC(!nested_cr3_valid(vcpu, cr3))) {
*entry_failure_code = ENTRY_FAIL_DEFAULT; *entry_failure_code = ENTRY_FAIL_DEFAULT;
@ -2469,7 +2470,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
* is assigned to entry_failure_code on failure. * is assigned to entry_failure_code on failure.
*/ */
static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12, static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
u32 *entry_failure_code) enum vm_entry_failure_code *entry_failure_code)
{ {
struct vcpu_vmx *vmx = to_vmx(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu);
struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs; struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
@ -2929,11 +2930,11 @@ static int nested_check_guest_non_reg_state(struct vmcs12 *vmcs12)
static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu, static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12, struct vmcs12 *vmcs12,
u32 *exit_qual) enum vm_entry_failure_code *entry_failure_code)
{ {
bool ia32e; bool ia32e;
*exit_qual = ENTRY_FAIL_DEFAULT; *entry_failure_code = ENTRY_FAIL_DEFAULT;
if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) || if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) ||
CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4))) CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)))
@ -2948,7 +2949,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL; return -EINVAL;
if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) { if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
*exit_qual = ENTRY_FAIL_VMCS_LINK_PTR; *entry_failure_code = ENTRY_FAIL_VMCS_LINK_PTR;
return -EINVAL; return -EINVAL;
} }
@ -3240,9 +3241,9 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
{ {
struct vcpu_vmx *vmx = to_vmx(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu); struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
enum vm_entry_failure_code entry_failure_code;
bool evaluate_pending_interrupts; bool evaluate_pending_interrupts;
u32 exit_reason = EXIT_REASON_INVALID_STATE; u32 exit_reason, failed_index;
u32 exit_qual;
if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu)) if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
kvm_vcpu_flush_tlb_current(vcpu); kvm_vcpu_flush_tlb_current(vcpu);
@ -3290,24 +3291,33 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
return NVMX_VMENTRY_VMFAIL; return NVMX_VMENTRY_VMFAIL;
} }
if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) if (nested_vmx_check_guest_state(vcpu, vmcs12,
&entry_failure_code)) {
exit_reason = EXIT_REASON_INVALID_STATE;
vmcs12->exit_qualification = entry_failure_code;
goto vmentry_fail_vmexit; goto vmentry_fail_vmexit;
}
} }
enter_guest_mode(vcpu); enter_guest_mode(vcpu);
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING) if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
vcpu->arch.tsc_offset += vmcs12->tsc_offset; vcpu->arch.tsc_offset += vmcs12->tsc_offset;
if (prepare_vmcs02(vcpu, vmcs12, &exit_qual)) if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) {
exit_reason = EXIT_REASON_INVALID_STATE;
vmcs12->exit_qualification = entry_failure_code;
goto vmentry_fail_vmexit_guest_mode; goto vmentry_fail_vmexit_guest_mode;
}
if (from_vmentry) { if (from_vmentry) {
exit_reason = EXIT_REASON_MSR_LOAD_FAIL; failed_index = nested_vmx_load_msr(vcpu,
exit_qual = nested_vmx_load_msr(vcpu, vmcs12->vm_entry_msr_load_addr,
vmcs12->vm_entry_msr_load_addr, vmcs12->vm_entry_msr_load_count);
vmcs12->vm_entry_msr_load_count); if (failed_index) {
if (exit_qual) exit_reason = EXIT_REASON_MSR_LOAD_FAIL;
vmcs12->exit_qualification = failed_index;
goto vmentry_fail_vmexit_guest_mode; goto vmentry_fail_vmexit_guest_mode;
}
} else { } else {
/* /*
* The MMU is not initialized to point at the right entities yet and * The MMU is not initialized to point at the right entities yet and
@ -3371,7 +3381,6 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
load_vmcs12_host_state(vcpu, vmcs12); load_vmcs12_host_state(vcpu, vmcs12);
vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY; vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
vmcs12->exit_qualification = exit_qual;
if (enable_shadow_vmcs || vmx->nested.hv_evmcs) if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
vmx->nested.need_vmcs12_to_shadow_sync = true; vmx->nested.need_vmcs12_to_shadow_sync = true;
return NVMX_VMENTRY_VMEXIT; return NVMX_VMENTRY_VMEXIT;
@ -4065,8 +4074,8 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12) struct vmcs12 *vmcs12)
{ {
enum vm_entry_failure_code ignored;
struct kvm_segment seg; struct kvm_segment seg;
u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER) if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer; vcpu->arch.efer = vmcs12->host_ia32_efer;
@ -4101,7 +4110,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
* Only PDPTE load can fail as the value of cr3 was checked on entry and * Only PDPTE load can fail as the value of cr3 was checked on entry and
* couldn't have changed. * couldn't have changed.
*/ */
if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code)) if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored))
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL); nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
if (!enable_ept) if (!enable_ept)
@ -6001,7 +6010,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
{ {
struct vcpu_vmx *vmx = to_vmx(vcpu); struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12; struct vmcs12 *vmcs12;
u32 exit_qual; enum vm_entry_failure_code ignored;
struct kvm_vmx_nested_state_data __user *user_vmx_nested_state = struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
&user_kvm_nested_state->data.vmx[0]; &user_kvm_nested_state->data.vmx[0];
int ret; int ret;
@ -6142,7 +6151,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
if (nested_vmx_check_controls(vcpu, vmcs12) || if (nested_vmx_check_controls(vcpu, vmcs12) ||
nested_vmx_check_host_state(vcpu, vmcs12) || nested_vmx_check_host_state(vcpu, vmcs12) ||
nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual)) nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
goto error_guest_mode; goto error_guest_mode;
vmx->nested.dirty_vmcs12 = true; vmx->nested.dirty_vmcs12 = true;