[v5,2/2] KVM: VMX: Cleanup VMX misc information defines and usages
Commit Message
Define VMX misc information fields with BIT_ULL()/GENMASK_ULL(), and move
VMX misc field macros to vmx.h if used in multiple files or where they are
used only once.
Signed-off-by: Xin Li <xin3.li@intel.com>
---
arch/x86/include/asm/msr-index.h | 5 -----
arch/x86/include/asm/vmx.h | 12 +++++------
arch/x86/kvm/vmx/capabilities.h | 4 ++--
arch/x86/kvm/vmx/nested.c | 34 ++++++++++++++++++++++++--------
arch/x86/kvm/vmx/nested.h | 2 +-
arch/x86/kvm/vmx/vmx.c | 8 +++-----
6 files changed, 37 insertions(+), 28 deletions(-)
Comments
On Tue, Feb 06, 2024, Xin Li wrote:
> Define VMX misc information fields with BIT_ULL()/GENMASK_ULL(), and move
> VMX misc field macros to vmx.h if used in multiple files or where they are
> used only once.
Yeah, no. This changelog doesn't even begin to cover what all is going on here,
and as with the first patch, this obviously needs to be split into multiple
patches.
> diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
> index 80fea1875948..a9dfda2cbca3 100644
> --- a/arch/x86/kvm/vmx/nested.c
> +++ b/arch/x86/kvm/vmx/nested.c
> @@ -917,6 +917,8 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
> return 0;
> }
>
> +#define VMX_MISC_MSR_LIST_MULTIPLIER 512
> +
> static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
> {
> struct vcpu_vmx *vmx = to_vmx(vcpu);
> @@ -1315,18 +1317,34 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
> return 0;
> }
>
> +#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5)
> +#define VMX_MISC_ACTIVITY_STATE_BITMAP GENMASK_ULL(8, 6)
> +#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6)
> +#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8)
> +#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15)
> +#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28)
Gah, my bad. I misread a comment in v1, and gave nonsensical feedback. I thought
the comment was saying that #defines for the *reserved* bits should be in vmx.h
but you were talking about moving existing defines from msr-index.h to vmx.h.
Defining feature bits in nested.c, and thus splitting the VMX_MISC feature bit
definitions across multiple locations, doesn't make any sense. Sorry for the
confusion.
: > Probably should also move VMX MSR field defs from msr-index.h to
: > a vmx header file.
:
: Why bother putting them in a header? As above, it's extremely unlikely anything
: besides vmx_restore_vmx_basic() will ever care about exactly which bits are
: reserved.
> +#define VMX_MISC_FEATURES_MASK \
> + (VMX_MISC_SAVE_EFER_LMA | \
> + VMX_MISC_ACTIVITY_STATE_BITMAP | \
> + VMX_MISC_INTEL_PT | \
> + VMX_MISC_RDMSR_IN_SMM | \
> + VMX_MISC_VMXOFF_BLOCK_SMI | \
> + VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | \
> + VMX_MISC_ZERO_LEN_INS)
> +
> +#define VMX_MISC_RESERVED_BITS \
> + (BIT_ULL(31) | GENMASK_ULL(13, 9))
> +
> static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
> diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
> index dc163a580f98..96f0d65dea45 100644
> --- a/arch/x86/kvm/vmx/vmx.c
> +++ b/arch/x86/kvm/vmx/vmx.c
> @@ -2570,7 +2570,6 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
> u32 _vmexit_control = 0;
> u32 _vmentry_control = 0;
> u64 basic_msr;
> - u64 misc_msr;
> int i;
>
> /*
> @@ -2704,8 +2703,6 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
> if (vmx_basic_vmcs_mem_type(basic_msr) != MEM_TYPE_WB)
> return -EIO;
>
> - rdmsrl(MSR_IA32_VMX_MISC, misc_msr);
> -
> vmcs_conf->basic = basic_msr;
> vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
> vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
> @@ -2713,7 +2710,8 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
> vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control;
> vmcs_conf->vmexit_ctrl = _vmexit_control;
> vmcs_conf->vmentry_ctrl = _vmentry_control;
> - vmcs_conf->misc = misc_msr;
> +
> + rdmsrl(MSR_IA32_VMX_MISC, vmcs_conf->misc);
No, keep the local variable. It's unlikely KVM will require a feature that is
enumerated in VMX_MISC, but it's not impossible, at which point we'd have to revert
this change.
And more importantly, if we messed up and forgot to revert this change, it's
slightly more like that the compiler will fail to detect an "uninitialized" access,
e.g. if vmcs_conf->misc were read before it was filled by rdmsrl().
Uninitialized in quotes because the usage from hardware_setup() isn't truly
uninitialized, i.e. it will be zeros. If we had a bug as above, we'd be relying
on the compiler to see that vmx_check_processor_compat()'s vmx_cap can get used
uninitialized, whereas the current code should be easily flagged if misc_msr is
used before it's written.
@@ -1118,11 +1118,6 @@
#define MSR_IA32_SMBA_BW_BASE 0xc0000280
#define MSR_IA32_EVT_CFG_BASE 0xc0000400
-/* MSR_IA32_VMX_MISC bits */
-#define MSR_IA32_VMX_MISC_INTEL_PT (1ULL << 14)
-#define MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS (1ULL << 29)
-#define MSR_IA32_VMX_MISC_PREEMPTION_TIMER_SCALE 0x1F
-
/* AMD-V MSRs */
#define MSR_VM_CR 0xc0010114
#define MSR_VM_IGNNE 0xc0010115
@@ -131,12 +131,10 @@
#define VMX_BASIC_TRUE_CTLS BIT_ULL(55)
-#define VMX_MISC_PREEMPTION_TIMER_RATE_MASK 0x0000001f
-#define VMX_MISC_SAVE_EFER_LMA 0x00000020
-#define VMX_MISC_ACTIVITY_HLT 0x00000040
-#define VMX_MISC_ACTIVITY_WAIT_SIPI 0x00000100
-#define VMX_MISC_ZERO_LEN_INS 0x40000000
-#define VMX_MISC_MSR_LIST_MULTIPLIER 512
+/* VMX_MISC bits and bitmasks */
+#define VMX_MISC_INTEL_PT BIT_ULL(14)
+#define VMX_MISC_VMWRITE_SHADOW_RO_FIELDS BIT_ULL(29)
+#define VMX_MISC_ZERO_LEN_INS BIT_ULL(30)
/* VMFUNC functions */
#define VMFUNC_CONTROL_BIT(x) BIT((VMX_FEATURE_##x & 0x1f) - 28)
@@ -161,7 +159,7 @@ static inline u32 vmx_basic_vmcs_mem_type(u64 vmx_basic)
static inline int vmx_misc_preemption_timer_rate(u64 vmx_misc)
{
- return vmx_misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+ return vmx_misc & GENMASK_ULL(4, 0);
}
static inline int vmx_misc_cr3_count(u64 vmx_misc)
@@ -223,7 +223,7 @@ static inline bool cpu_has_vmx_vmfunc(void)
static inline bool cpu_has_vmx_shadow_vmcs(void)
{
/* check if the cpu supports writing r/o exit information fields */
- if (!(vmcs_config.misc & MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
+ if (!(vmcs_config.misc & VMX_MISC_VMWRITE_SHADOW_RO_FIELDS))
return false;
return vmcs_config.cpu_based_2nd_exec_ctrl &
@@ -365,7 +365,7 @@ static inline bool cpu_has_vmx_invvpid_global(void)
static inline bool cpu_has_vmx_intel_pt(void)
{
- return (vmcs_config.misc & MSR_IA32_VMX_MISC_INTEL_PT) &&
+ return (vmcs_config.misc & VMX_MISC_INTEL_PT) &&
(vmcs_config.cpu_based_2nd_exec_ctrl & SECONDARY_EXEC_PT_USE_GPA) &&
(vmcs_config.vmentry_ctrl & VM_ENTRY_LOAD_IA32_RTIT_CTL);
}
@@ -917,6 +917,8 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
return 0;
}
+#define VMX_MISC_MSR_LIST_MULTIPLIER 512
+
static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -1315,18 +1317,34 @@ vmx_restore_control_msr(struct vcpu_vmx *vmx, u32 msr_index, u64 data)
return 0;
}
+#define VMX_MISC_SAVE_EFER_LMA BIT_ULL(5)
+#define VMX_MISC_ACTIVITY_STATE_BITMAP GENMASK_ULL(8, 6)
+#define VMX_MISC_ACTIVITY_HLT BIT_ULL(6)
+#define VMX_MISC_ACTIVITY_WAIT_SIPI BIT_ULL(8)
+#define VMX_MISC_RDMSR_IN_SMM BIT_ULL(15)
+#define VMX_MISC_VMXOFF_BLOCK_SMI BIT_ULL(28)
+
+#define VMX_MISC_FEATURES_MASK \
+ (VMX_MISC_SAVE_EFER_LMA | \
+ VMX_MISC_ACTIVITY_STATE_BITMAP | \
+ VMX_MISC_INTEL_PT | \
+ VMX_MISC_RDMSR_IN_SMM | \
+ VMX_MISC_VMXOFF_BLOCK_SMI | \
+ VMX_MISC_VMWRITE_SHADOW_RO_FIELDS | \
+ VMX_MISC_ZERO_LEN_INS)
+
+#define VMX_MISC_RESERVED_BITS \
+ (BIT_ULL(31) | GENMASK_ULL(13, 9))
+
static int vmx_restore_vmx_misc(struct vcpu_vmx *vmx, u64 data)
{
- const u64 feature_and_reserved_bits =
- /* feature */
- BIT_ULL(5) | GENMASK_ULL(8, 6) | BIT_ULL(14) | BIT_ULL(15) |
- BIT_ULL(28) | BIT_ULL(29) | BIT_ULL(30) |
- /* reserved */
- GENMASK_ULL(13, 9) | BIT_ULL(31);
u64 vmx_misc = vmx_control_msr(vmcs_config.nested.misc_low,
vmcs_config.nested.misc_high);
- if (!is_bitwise_subset(vmx_misc, data, feature_and_reserved_bits))
+ static_assert(!(VMX_MISC_FEATURES_MASK & VMX_MISC_RESERVED_BITS));
+
+ if (!is_bitwise_subset(vmx_misc, data,
+ VMX_MISC_FEATURES_MASK | VMX_MISC_RESERVED_BITS))
return -EINVAL;
if ((vmx->nested.msrs.pinbased_ctls_high &
@@ -6993,7 +7011,7 @@ static void nested_vmx_setup_misc_data(struct vmcs_config *vmcs_conf,
{
msrs->misc_low = (u32)vmcs_conf->misc & VMX_MISC_SAVE_EFER_LMA;
msrs->misc_low |=
- MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
+ VMX_MISC_VMWRITE_SHADOW_RO_FIELDS |
VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE |
VMX_MISC_ACTIVITY_HLT |
VMX_MISC_ACTIVITY_WAIT_SIPI;
@@ -109,7 +109,7 @@ static inline unsigned nested_cpu_vmx_misc_cr3_count(struct kvm_vcpu *vcpu)
static inline bool nested_cpu_has_vmwrite_any_field(struct kvm_vcpu *vcpu)
{
return to_vmx(vcpu)->nested.msrs.misc_low &
- MSR_IA32_VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
+ VMX_MISC_VMWRITE_SHADOW_RO_FIELDS;
}
static inline bool nested_cpu_has_zero_length_injection(struct kvm_vcpu *vcpu)
@@ -2570,7 +2570,6 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
u32 _vmexit_control = 0;
u32 _vmentry_control = 0;
u64 basic_msr;
- u64 misc_msr;
int i;
/*
@@ -2704,8 +2703,6 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
if (vmx_basic_vmcs_mem_type(basic_msr) != MEM_TYPE_WB)
return -EIO;
- rdmsrl(MSR_IA32_VMX_MISC, misc_msr);
-
vmcs_conf->basic = basic_msr;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
vmcs_conf->cpu_based_exec_ctrl = _cpu_based_exec_control;
@@ -2713,7 +2710,8 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
vmcs_conf->cpu_based_3rd_exec_ctrl = _cpu_based_3rd_exec_control;
vmcs_conf->vmexit_ctrl = _vmexit_control;
vmcs_conf->vmentry_ctrl = _vmentry_control;
- vmcs_conf->misc = misc_msr;
+
+ rdmsrl(MSR_IA32_VMX_MISC, vmcs_conf->misc);
#if IS_ENABLED(CONFIG_HYPERV)
if (enlightened_vmcs)
@@ -8597,7 +8595,7 @@ static __init int hardware_setup(void)
u64 use_timer_freq = 5000ULL * 1000 * 1000;
cpu_preemption_timer_multi =
- vmcs_config.misc & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+ vmx_misc_preemption_timer_rate(vmcs_config.misc);
if (tsc_khz)
use_timer_freq = (u64)tsc_khz * 1000;