summaryrefslogtreecommitdiffstats
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/mmu.c25
-rw-r--r--arch/x86/kvm/svm.c129
-rw-r--r--arch/x86/kvm/vmx.c11
-rw-r--r--arch/x86/kvm/x86.c6
4 files changed, 44 insertions, 127 deletions
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1ba509..ff606f507913 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@ walk_shadow_page_get_mmio_spte(struct kvm_vcpu *vcpu, u64 addr, u64 *sptep)
break;
reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
- leaf);
+ iterator.level);
}
walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@ static void
__reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
struct rsvd_bits_validate *rsvd_check,
int maxphyaddr, int level, bool nx, bool gbpages,
- bool pse)
+ bool pse, bool amd)
{
u64 exb_bit_rsvd = 0;
u64 gbpages_bit_rsvd = 0;
@@ -3631,7 +3631,7 @@ __reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
* Non-leaf PML4Es and PDPEs reserve bit 8 (which would be the G bit for
* leaf entries) on AMD CPUs only.
*/
- if (guest_cpuid_is_amd(vcpu))
+ if (amd)
nonleaf_bit8_rsvd = rsvd_bits(8, 8);
switch (level) {
@@ -3699,7 +3699,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu,
__reset_rsvds_bits_mask(vcpu, &context->guest_rsvd_check,
cpuid_maxphyaddr(vcpu), context->root_level,
context->nx, guest_cpuid_has_gbpages(vcpu),
- is_pse(vcpu));
+ is_pse(vcpu), guest_cpuid_is_amd(vcpu));
}
static void
@@ -3749,13 +3749,24 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
void
reset_shadow_zero_bits_mask(struct kvm_vcpu *vcpu, struct kvm_mmu *context)
{
+ /*
+ * Passing "true" to the last argument is okay; it adds a check
+ * on bit 8 of the SPTEs which KVM doesn't use anyway.
+ */
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, context->nx,
- guest_cpuid_has_gbpages(vcpu), is_pse(vcpu));
+ guest_cpuid_has_gbpages(vcpu), is_pse(vcpu),
+ true);
}
EXPORT_SYMBOL_GPL(reset_shadow_zero_bits_mask);
+static inline bool boot_cpu_is_amd(void)
+{
+ WARN_ON_ONCE(!tdp_enabled);
+ return shadow_x_mask == 0;
+}
+
/*
* the direct page table on host, use as much mmu features as
* possible, however, kvm currently does not do execution-protection.
@@ -3764,11 +3775,11 @@ static void
reset_tdp_shadow_zero_bits_mask(struct kvm_vcpu *vcpu,
struct kvm_mmu *context)
{
- if (guest_cpuid_is_amd(vcpu))
+ if (boot_cpu_is_amd())
__reset_rsvds_bits_mask(vcpu, &context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
context->shadow_root_level, false,
- cpu_has_gbpages, true);
+ cpu_has_gbpages, true, true);
else
__reset_rsvds_bits_mask_ept(&context->shadow_zero_check,
boot_cpu_data.x86_phys_bits,
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index fdb8cb63a6c0..2f9ed1ff0632 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@ module_param(npt, int, S_IRUGO);
static int nested = true;
module_param(nested, int, S_IRUGO);
+static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
static void svm_flush_tlb(struct kvm_vcpu *vcpu);
static void svm_complete_interrupts(struct vcpu_svm *svm);
@@ -513,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
if (svm->vmcb->control.next_rip != 0) {
- WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+ WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
svm->next_rip = svm->vmcb->control.next_rip;
}
@@ -865,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
}
-#define MTRR_TYPE_UC_MINUS 7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
- /*
- * WT and WP aren't always available in the host PAT. Treat
- * them as UC and UC- respectively. Everything else should be
- * there.
- */
- switch (mtrr)
- {
- case MTRR_TYPE_WRTHROUGH:
- return MTRR_TYPE_UNCACHABLE;
- case MTRR_TYPE_WRPROT:
- return MTRR_TYPE_UC_MINUS;
- default:
- BUG();
- }
-}
-
-static void build_mtrr2protval(void)
-{
- int i;
- u64 pat;
-
- for (i = 0; i < 8; i++)
- mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
- /* Ignore the invalid MTRR types. */
- mtrr2protval[2] = 0;
- mtrr2protval[3] = 0;
-
- /*
- * Use host PAT value to figure out the mapping from guest MTRR
- * values to nested page table PAT/PCD/PWT values. We do not
- * want to change the host PAT value every time we enter the
- * guest.
- */
- rdmsrl(MSR_IA32_CR_PAT, pat);
- for (i = 0; i < 8; i++) {
- u8 mtrr = pat >> (8 * i);
-
- if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
- mtrr2protval[mtrr] = __cm_idx2pte(i);
- }
-
- for (i = 0; i < 8; i++) {
- if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
- u8 fallback = fallback_mtrr_type(i);
- mtrr2protval[i] = mtrr2protval[fallback];
- BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
- }
- }
-}
-
static __init int svm_hardware_setup(void)
{
int cpu;
@@ -989,7 +932,6 @@ static __init int svm_hardware_setup(void)
} else
kvm_disable_tdp();
- build_mtrr2protval();
return 0;
err:
@@ -1144,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
return target_tsc - tsc;
}
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
- struct kvm_vcpu *vcpu = &svm->vcpu;
-
- /* Unlike Intel, AMD takes the guest's CR0.CD into account.
- *
- * AMD does not have IPAT. To emulate it for the case of guests
- * with no assigned devices, just set everything to WB. If guests
- * have assigned devices, however, we cannot force WB for RAM
- * pages only, so use the guest PAT directly.
- */
- if (!kvm_arch_has_assigned_device(vcpu->kvm))
- *g_pat = 0x0606060606060606;
- else
- *g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
- u8 mtrr;
-
- /*
- * 1. MMIO: trust guest MTRR, so same as item 3.
- * 2. No passthrough: always map as WB, and force guest PAT to WB as well
- * 3. Passthrough: can't guarantee the result, try to trust guest.
- */
- if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
- return 0;
-
- if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
- kvm_read_cr0(vcpu) & X86_CR0_CD)
- return _PAGE_NOCACHE;
-
- mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
- return mtrr2protval[mtrr];
-}
-
static void init_vmcb(struct vcpu_svm *svm, bool init_event)
{
struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1263,7 +1168,8 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
* svm_set_cr0() sets PG and WP and clears NW and CD on save->cr0.
* It also updates the guest-visible cr0 value.
*/
- (void)kvm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+ svm_set_cr0(&svm->vcpu, X86_CR0_NW | X86_CR0_CD | X86_CR0_ET);
+ kvm_mmu_reset_context(&svm->vcpu);
save->cr4 = X86_CR4_PAE;
/* rdx = ?? */
@@ -1276,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
clr_cr_intercept(svm, INTERCEPT_CR3_READ);
clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
save->g_pat = svm->vcpu.arch.pat;
- svm_set_guest_pat(svm, &save->g_pat);
save->cr3 = 0;
save->cr4 = 0;
}
@@ -1671,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
if (!vcpu->fpu_active)
cr0 |= X86_CR0_TS;
-
- /* These are emulated via page tables. */
- cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+ /*
+ * re-enable caching here because the QEMU bios
+ * does not do it - this results in some delay at
+ * reboot
+ */
+ if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+ cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
svm->vmcb->save.cr0 = cr0;
mark_dirty(svm->vmcb, VMCB_CR);
update_cr0_intercept(svm);
@@ -3349,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
case MSR_VM_IGNNE:
vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
break;
- case MSR_IA32_CR_PAT:
- if (npt_enabled) {
- if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
- return 1;
- vcpu->arch.pat = data;
- svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
- mark_dirty(svm->vmcb, VMCB_NPT);
- break;
- }
- /* fall through */
default:
return kvm_set_msr_common(vcpu, msr);
}
@@ -4193,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void)
return true;
}
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+ return 0;
+}
+
static void svm_cpuid_update(struct kvm_vcpu *vcpu)
{
}
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64076740251e..06ef4908ba61 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8617,17 +8617,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
u64 ipat = 0;
/* For VT-d and EPT combination
- * 1. MMIO: guest may want to apply WC, trust it.
+ * 1. MMIO: always map as UC
* 2. EPT with VT-d:
* a. VT-d without snooping control feature: can't guarantee the
- * result, try to trust guest. So the same as item 1.
+ * result, try to trust guest.
* b. VT-d with snooping control feature: snooping control feature of
* VT-d engine can guarantee the cache correctness. Just set it
* to WB to keep consistent with host. So the same as item 3.
* 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
* consistent with host MTRR
*/
- if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+ if (is_mmio) {
+ cache = MTRR_TYPE_UNCACHABLE;
+ goto exit;
+ }
+
+ if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
ipat = VMX_EPT_IPAT_BIT;
cache = MTRR_TYPE_WRBACK;
goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6bbb0dfb99d0..92511d4b7236 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1708,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
vcpu->pvclock_set_guest_stopped_request = false;
}
- pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
/* If the host uses TSC clocksource, then it is stable */
if (use_master_clock)
pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -2007,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
&vcpu->requests);
ka->boot_vcpu_runs_old_kvmclock = tmp;
-
- ka->kvmclock_offset = -get_kernel_ns();
}
vcpu->arch.time = data;
@@ -2190,6 +2186,8 @@ int kvm_get_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
case MSR_IA32_LASTINTFROMIP:
case MSR_IA32_LASTINTTOIP:
case MSR_K8_SYSCFG:
+ case MSR_K8_TSEG_ADDR:
+ case MSR_K8_TSEG_MASK:
case MSR_K7_HWCR:
case MSR_VM_HSAVE_PA:
case MSR_K8_INT_PENDING_MSG:
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-06 13:50:52 +0100