UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity

KVM: x86: Prepare MSR bitmaps for userspace tracked MSRs 

Prepare vmx and svm for a subsequent change that ensures the MSR permission
bitmap is set to allow an MSR that userspace is tracking to force a vmx_vmexit
in the guest.

Signed-off-by: Aaron Lewis <aaronlewis@google.com>
Reviewed-by: Oliver Upton <oupton@google.com>
[agraf: rebase, adapt SVM scheme to nested changes that came in between]
Signed-off-by: Alexander Graf <graf@amazon.com>
Message-Id: <20200925143422.21718-5-graf@amazon.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
Aaron Lewis 2020-09-25 16:34:18 +02:00 committed by Paolo Bonzini
parent 51de8151bd
commit 476c9bd8e9
4 changed files with 77 additions and 70 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

60
arch/x86/kvm/svm/svm.c
View File

@ -564,7 +564,7 @@ static bool valid_msr_intercept(u32 index)
return false;
}
static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
{
u8 bit_write;
unsigned long tmp;
@ -583,7 +583,7 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, unsigned msr)
return !!test_bit(bit_write, &tmp);
}
static void set_msr_interception(u32 *msrpm, unsigned msr,
static void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
int read, int write)
{
u8 bit_read, bit_write;
@ -609,11 +609,10 @@ static void set_msr_interception(u32 *msrpm, unsigned msr,
msrpm[offset] = tmp;
}
static u32 *svm_vcpu_init_msrpm(void)
static u32 *svm_vcpu_alloc_msrpm(void)
{
int i;
u32 *msrpm;
struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, MSRPM_ALLOC_ORDER);
u32 *msrpm;
if (!pages)
return NULL;
@ -621,12 +620,18 @@ static u32 *svm_vcpu_init_msrpm(void)
msrpm = page_address(pages);
memset(msrpm, 0xff, PAGE_SIZE * (1 << MSRPM_ALLOC_ORDER));
return msrpm;
}
static void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
{
int i;
for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
if (!direct_access_msrs[i].always)
continue;
set_msr_interception(msrpm, direct_access_msrs[i].index, 1, 1);
set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
}
return msrpm;
}
static void svm_vcpu_free_msrpm(u32 *msrpm)
@ -677,26 +682,26 @@ static void init_msrpm_offsets(void)
}
}
static void svm_enable_lbrv(struct vcpu_svm *svm)
static void svm_enable_lbrv(struct kvm_vcpu *vcpu)
{
u32 *msrpm = svm->msrpm;
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
}
static void svm_disable_lbrv(struct vcpu_svm *svm)
static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
{
u32 *msrpm = svm->msrpm;
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
void disable_nmi_singlestep(struct vcpu_svm *svm)
@ -1230,14 +1235,19 @@ static int svm_create_vcpu(struct kvm_vcpu *vcpu)
svm->nested.hsave = page_address(hsave_page);
svm->msrpm = svm_vcpu_init_msrpm();
svm->msrpm = svm_vcpu_alloc_msrpm();
if (!svm->msrpm)
goto error_free_hsave_page;
svm->nested.msrpm = svm_vcpu_init_msrpm();
svm_vcpu_init_msrpm(vcpu, svm->msrpm);
svm->nested.msrpm = svm_vcpu_alloc_msrpm();
if (!svm->nested.msrpm)
goto error_free_msrpm;
/* We only need the L1 pass-through MSR state, so leave vcpu as NULL */
svm_vcpu_init_msrpm(vcpu, svm->nested.msrpm);
svm->vmcb = page_address(vmcb_page);
svm->vmcb_pa = __sme_set(page_to_pfn(vmcb_page) << PAGE_SHIFT);
svm->asid_generation = 0;
@ -2574,7 +2584,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
* We update the L1 MSR bit as well since it will end up
* touching the MSR anyway now.
*/
set_msr_interception(svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
break;
case MSR_IA32_PRED_CMD:
if (!msr->host_initiated &&
@ -2589,7 +2599,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
break;
wrmsrl(MSR_IA32_PRED_CMD, PRED_CMD_IBPB);
set_msr_interception(svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0, 1);
break;
case MSR_AMD64_VIRT_SPEC_CTRL:
if (!msr->host_initiated &&
@ -2653,9 +2663,9 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
svm->vmcb->save.dbgctl = data;
vmcb_mark_dirty(svm->vmcb, VMCB_LBR);
if (data & (1ULL<<0))
svm_enable_lbrv(svm);
svm_enable_lbrv(vcpu);
else
svm_disable_lbrv(svm);
svm_disable_lbrv(vcpu);
break;
case MSR_VM_HSAVE_PA:
svm->nested.hsave_msr = data;

2
arch/x86/kvm/vmx/nested.c
View File

@ -4776,7 +4776,7 @@ static int enter_vmx_operation(struct kvm_vcpu *vcpu)
if (vmx_pt_mode_is_host_guest()) {
vmx->pt_desc.guest.ctl = 0;
pt_update_intercept_for_msr(vmx);
pt_update_intercept_for_msr(vcpu);
}
return 0;

83
arch/x86/kvm/vmx/vmx.c
View File

@ -338,7 +338,7 @@ static const struct kernel_param_ops vmentry_l1d_flush_ops = {
module_param_cb(vmentry_l1d_flush, &vmentry_l1d_flush_ops, NULL, 0644);
static u32 vmx_segment_access_rights(struct kvm_segment *var);
static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
u32 msr, int type);
void vmx_vmexit(void);
@ -1980,7 +1980,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
* in the merging. We update the vmcs01 here for L1 as well
* since it will end up touching the MSR anyway now.
*/
vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap,
vmx_disable_intercept_for_msr(vcpu,
MSR_IA32_SPEC_CTRL,
MSR_TYPE_RW);
break;
@ -2016,8 +2016,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
* vmcs02.msr_bitmap here since it gets completely overwritten
* in the merging.
*/
vmx_disable_intercept_for_msr(vmx->vmcs01.msr_bitmap, MSR_IA32_PRED_CMD,
MSR_TYPE_W);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W);
break;
case MSR_IA32_CR_PAT:
if (!kvm_pat_valid(data))
@ -2067,7 +2066,7 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
return 1;
vmcs_write64(GUEST_IA32_RTIT_CTL, data);
vmx->pt_desc.guest.ctl = data;
pt_update_intercept_for_msr(vmx);
pt_update_intercept_for_msr(vcpu);
break;
case MSR_IA32_RTIT_STATUS:
if (!pt_can_write_msr(vmx))
@ -3584,9 +3583,11 @@ void free_vpid(int vpid)
spin_unlock(&vmx_vpid_lock);
}
static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bitmap,
static __always_inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
u32 msr, int type)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
int f = sizeof(unsigned long);
if (!cpu_has_vmx_msr_bitmap())
@ -3622,9 +3623,11 @@ static __always_inline void vmx_disable_intercept_for_msr(unsigned long *msr_bit
}
}
static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitmap,
static __always_inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
u32 msr, int type)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
int f = sizeof(unsigned long);
if (!cpu_has_vmx_msr_bitmap())
@ -3660,13 +3663,13 @@ static __always_inline void vmx_enable_intercept_for_msr(unsigned long *msr_bitm
}
}
static __always_inline void vmx_set_intercept_for_msr(unsigned long *msr_bitmap,
u32 msr, int type, bool value)
static __always_inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu,
u32 msr, int type, bool value)
{
if (value)
vmx_enable_intercept_for_msr(msr_bitmap, msr, type);
vmx_enable_intercept_for_msr(vcpu, msr, type);
else
vmx_disable_intercept_for_msr(msr_bitmap, msr, type);
vmx_disable_intercept_for_msr(vcpu, msr, type);
}
static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
@ -3684,8 +3687,8 @@ static u8 vmx_msr_bitmap_mode(struct kvm_vcpu *vcpu)
return mode;
}
static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
u8 mode)
static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu,
unsigned long *msr_bitmap, u8 mode)
{
int msr;
@ -3700,11 +3703,11 @@ static void vmx_update_msr_bitmap_x2apic(unsigned long *msr_bitmap,
* TPR reads and writes can be virtualized even if virtual interrupt
* delivery is not in use.
*/
vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TASKPRI), MSR_TYPE_RW);
if (mode & MSR_BITMAP_MODE_X2APIC_APICV) {
vmx_enable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_R);
vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
vmx_disable_intercept_for_msr(msr_bitmap, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
vmx_enable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_TMCCT), MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_EOI), MSR_TYPE_W);
vmx_disable_intercept_for_msr(vcpu, X2APIC_MSR(APIC_SELF_IPI), MSR_TYPE_W);
}
}
}
@ -3720,30 +3723,24 @@ void vmx_update_msr_bitmap(struct kvm_vcpu *vcpu)
return;
if (changed & (MSR_BITMAP_MODE_X2APIC | MSR_BITMAP_MODE_X2APIC_APICV))
vmx_update_msr_bitmap_x2apic(msr_bitmap, mode);
vmx_update_msr_bitmap_x2apic(vcpu, msr_bitmap, mode);
vmx->msr_bitmap_mode = mode;
}
void pt_update_intercept_for_msr(struct vcpu_vmx *vmx)
void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
{
unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool flag = !(vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN);
u32 i;
vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_STATUS,
MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_BASE,
MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_OUTPUT_MASK,
MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(msr_bitmap, MSR_IA32_RTIT_CR3_MATCH,
MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_STATUS, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_BASE, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_OUTPUT_MASK, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_CR3_MATCH, MSR_TYPE_RW, flag);
for (i = 0; i < vmx->pt_desc.addr_range; i++) {
vmx_set_intercept_for_msr(msr_bitmap,
MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(msr_bitmap,
MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_A + i * 2, MSR_TYPE_RW, flag);
vmx_set_intercept_for_msr(vcpu, MSR_IA32_RTIT_ADDR0_B + i * 2, MSR_TYPE_RW, flag);
}
}
@ -6753,18 +6750,18 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
goto free_pml;
msr_bitmap = vmx->vmcs01.msr_bitmap;
vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_TSC, MSR_TYPE_R);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_FS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_GS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
if (kvm_cstate_in_guest(vcpu->kvm)) {
vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C1_RES, MSR_TYPE_R);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(msr_bitmap, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
}
vmx->msr_bitmap_mode = 0;

2
arch/x86/kvm/vmx/vmx.h
View File

@ -330,7 +330,7 @@ bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr);
void pt_update_intercept_for_msr(struct vcpu_vmx *vmx);
void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu);
void vmx_update_host_rsp(struct vcpu_vmx *vmx, unsigned long host_rsp);
int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);