#define KVM_VMX_TSC_MULTIPLIER_MAX 0xffffffffffffffffULL
+/* Guest_tsc -> host_tsc conversion requires 64-bit division. */
+static int __read_mostly cpu_preemption_timer_multi;
+static bool __read_mostly enable_preemption_timer = 1;
+#ifdef CONFIG_X86_64
+module_param_named(preemption_timer, enable_preemption_timer, bool, S_IRUGO);
+#endif
+
#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
#define KVM_VM_CR0_ALWAYS_ON \
struct pi_desc *pi_desc;
bool pi_pending;
u16 posted_intr_nv;
- u64 msr_ia32_feature_control;
struct hrtimer preemption_timer;
bool preemption_timer_expired;
#define PML_ENTITY_NUM 512
struct page *pml_pg;
+ /* apic deadline value in host tsc */
+ u64 hv_deadline_tsc;
+
u64 current_tsc_ratio;
bool guest_pkru_valid;
u32 guest_pkru;
u32 host_pkru;
+
+ /*
+ * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
+ * msr_ia32_feature_control. FEATURE_CONTROL_LOCKED is always included
+ * in msr_ia32_feature_control_valid_bits.
+ */
+ u64 msr_ia32_feature_control;
+ u64 msr_ia32_feature_control_valid_bits;
};
enum segment_cache_field {
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY;
}
+/*
+ * Comment's format: document - errata name - stepping - processor name.
+ * Refer from
+ * https://www.virtualbox.org/svn/vbox/trunk/src/VBox/VMM/VMMR0/HMR0.cpp
+ */
+static u32 vmx_preemption_cpu_tfms[] = {
+/* 323344.pdf - BA86 - D0 - Xeon 7500 Series */
+0x000206E6,
+/* 323056.pdf - AAX65 - C2 - Xeon L3406 */
+/* 322814.pdf - AAT59 - C2 - i7-600, i5-500, i5-400 and i3-300 Mobile */
+/* 322911.pdf - AAU65 - C2 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020652,
+/* 322911.pdf - AAU65 - K0 - i5-600, i3-500 Desktop and Pentium G6950 */
+0x00020655,
+/* 322373.pdf - AAO95 - B1 - Xeon 3400 Series */
+/* 322166.pdf - AAN92 - B1 - i7-800 and i5-700 Desktop */
+/*
+ * 320767.pdf - AAP86 - B1 -
+ * i7-900 Mobile Extreme, i7-800 and i7-700 Mobile
+ */
+0x000106E5,
+/* 321333.pdf - AAM126 - C0 - Xeon 3500 */
+0x000106A0,
+/* 321333.pdf - AAM126 - C1 - Xeon 3500 */
+0x000106A1,
+/* 320836.pdf - AAJ124 - C0 - i7-900 Desktop Extreme and i7-900 Desktop */
+0x000106A4,
+ /* 321333.pdf - AAM126 - D0 - Xeon 3500 */
+ /* 321324.pdf - AAK139 - D0 - Xeon 5500 */
+ /* 320836.pdf - AAJ124 - D0 - i7-900 Extreme and i7-900 Desktop */
+0x000106A5,
+};
+
+static inline bool cpu_has_broken_vmx_preemption_timer(void)
+{
+ u32 eax = cpuid_eax(0x00000001), i;
+
+ /* Clear the reserved bits */
+ eax &= ~(0x3U << 14 | 0xfU << 28);
+ for (i = 0; i < sizeof(vmx_preemption_cpu_tfms)/sizeof(u32); i++)
+ if (eax == vmx_preemption_cpu_tfms[i])
+ return true;
+
+ return false;
+}
+
+static inline bool cpu_has_vmx_preemption_timer(void)
+{
+ if (cpu_has_broken_vmx_preemption_timer())
+ return false;
+
+ return vmcs_config.pin_based_exec_ctrl &
+ PIN_BASED_VMX_PREEMPTION_TIMER;
+}
+
static inline bool cpu_has_vmx_posted_intr(void)
{
return IS_ENABLED(CONFIG_X86_LOCAL_APIC) &&
if (is_guest_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_nested;
- else if (vcpu->arch.apic_base & X2APIC_ENABLE) {
+ else if (cpu_has_secondary_exec_ctrls() &&
+ (vmcs_read32(SECONDARY_VM_EXEC_CONTROL) &
+ SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE)) {
if (is_long_mode(vcpu))
msr_bitmap = vmx_msr_bitmap_longmode_x2apic;
else
return 0;
}
+static inline bool vmx_feature_control_msr_valid(struct kvm_vcpu *vcpu,
+ uint64_t val)
+{
+ uint64_t valid_bits = to_vmx(vcpu)->msr_ia32_feature_control_valid_bits;
+
+ return !(val & ~valid_bits);
+}
+
/*
* Reads an msr value (of 'msr_index') into 'pdata'.
* Returns 0 on success, non-0 otherwise.
return 1;
msr_info->data = vmcs_read64(GUEST_BNDCFGS);
break;
- case MSR_IA32_FEATURE_CONTROL:
- if (!nested_vmx_allowed(vcpu))
+ case MSR_IA32_MCG_EXT_CTL:
+ if (!msr_info->host_initiated &&
+ !(to_vmx(vcpu)->msr_ia32_feature_control &
+ FEATURE_CONTROL_LMCE))
return 1;
- msr_info->data = to_vmx(vcpu)->nested.msr_ia32_feature_control;
+ msr_info->data = vcpu->arch.mcg_ext_ctl;
+ break;
+ case MSR_IA32_FEATURE_CONTROL:
+ msr_info->data = to_vmx(vcpu)->msr_ia32_feature_control;
break;
case MSR_IA32_VMX_BASIC ... MSR_IA32_VMX_VMFUNC:
if (!nested_vmx_allowed(vcpu))
case MSR_IA32_TSC_ADJUST:
ret = kvm_set_msr_common(vcpu, msr_info);
break;
+ case MSR_IA32_MCG_EXT_CTL:
+ if ((!msr_info->host_initiated &&
+ !(to_vmx(vcpu)->msr_ia32_feature_control &
+ FEATURE_CONTROL_LMCE)) ||
+ (data & ~MCG_EXT_CTL_LMCE_EN))
+ return 1;
+ vcpu->arch.mcg_ext_ctl = data;
+ break;
case MSR_IA32_FEATURE_CONTROL:
- if (!nested_vmx_allowed(vcpu) ||
- (to_vmx(vcpu)->nested.msr_ia32_feature_control &
+ if (!vmx_feature_control_msr_valid(vcpu, data) ||
+ (to_vmx(vcpu)->msr_ia32_feature_control &
FEATURE_CONTROL_LOCKED && !msr_info->host_initiated))
return 1;
- vmx->nested.msr_ia32_feature_control = data;
+ vmx->msr_ia32_feature_control = data;
if (msr_info->host_initiated && data == 0)
vmx_leave_nested(vcpu);
break;
vmx_capability.ept, vmx_capability.vpid);
}
- min = VM_EXIT_SAVE_DEBUG_CONTROLS;
+ min = VM_EXIT_SAVE_DEBUG_CONTROLS | VM_EXIT_ACK_INTR_ON_EXIT;
#ifdef CONFIG_X86_64
min |= VM_EXIT_HOST_ADDR_SPACE_SIZE;
#endif
opt = VM_EXIT_SAVE_IA32_PAT | VM_EXIT_LOAD_IA32_PAT |
- VM_EXIT_ACK_INTR_ON_EXIT | VM_EXIT_CLEAR_BNDCFGS;
+ VM_EXIT_CLEAR_BNDCFGS;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_EXIT_CTLS,
&_vmexit_control) < 0)
return -EIO;
min = PIN_BASED_EXT_INTR_MASK | PIN_BASED_NMI_EXITING;
- opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR;
+ opt = PIN_BASED_VIRTUAL_NMIS | PIN_BASED_POSTED_INTR |
+ PIN_BASED_VMX_PREEMPTION_TIMER;
if (adjust_vmx_controls(min, opt, MSR_IA32_VMX_PINBASED_CTLS,
&_pin_based_exec_control) < 0)
return -EIO;
if (!(_cpu_based_2nd_exec_control &
- SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) ||
- !(_vmexit_control & VM_EXIT_ACK_INTR_ON_EXIT))
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY))
_pin_based_exec_control &= ~PIN_BASED_POSTED_INTR;
min = VM_ENTRY_LOAD_DEBUG_CONTROLS;
/*
* Some cpus support VM_ENTRY_(LOAD|SAVE)_IA32_PERF_GLOBAL_CTRL
- * but due to arrata below it can't be used. Workaround is to use
+ * but due to errata below it can't be used. Workaround is to use
* msr load mechanism to switch IA32_PERF_GLOBAL_CTRL.
*
* VM Exit May Incorrectly Clear IA32_PERF_GLOBAL_CTRL [34:32]
}
}
- if (cpu_has_xsaves)
+ if (boot_cpu_has(X86_FEATURE_XSAVES))
rdmsrl(MSR_IA32_XSS, host_xss);
return 0;
if (!kvm_vcpu_apicv_active(&vmx->vcpu))
pin_based_exec_ctrl &= ~PIN_BASED_POSTED_INTR;
+ /* Enable the preemption timer dynamically */
+ pin_based_exec_ctrl &= ~PIN_BASED_VMX_PREEMPTION_TIMER;
return pin_based_exec_ctrl;
}
struct vcpu_vmx *vmx = to_vmx(vcpu);
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+ if (cpu_has_secondary_exec_ctrls()) {
+ if (kvm_vcpu_apicv_active(vcpu))
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_APIC_REGISTER_VIRT |
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+ else
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_APIC_REGISTER_VIRT |
+ SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY);
+ }
+
+ if (cpu_has_vmx_msr_bitmap())
+ vmx_set_msr_bitmap(vcpu);
}
static u32 vmx_exec_control(struct vcpu_vmx *vmx)
/* Control */
vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, vmx_pin_based_exec_ctrl(vmx));
+ vmx->hv_deadline_tsc = -1;
vmcs_write32(CPU_BASED_VM_EXEC_CONTROL, vmx_exec_control(vmx));
vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
- vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx->vcpu.arch.cr0 = cr0;
+ vmx_set_cr0(vcpu, cr0); /* enter rmode */
vmx_set_cr4(vcpu, 0);
vmx_set_efer(vcpu, 0);
vmx_fpu_activate(vcpu);
set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
- if (enable_apicv) {
- for (msr = 0x800; msr <= 0x8ff; msr++)
- vmx_disable_intercept_msr_read_x2apic(msr);
-
- /* According SDM, in x2apic mode, the whole id reg is used.
- * But in KVM, it only use the highest eight bits. Need to
- * intercept it */
- vmx_enable_intercept_msr_read_x2apic(0x802);
- /* TMCCT */
- vmx_enable_intercept_msr_read_x2apic(0x839);
- /* TPR */
- vmx_disable_intercept_msr_write_x2apic(0x808);
- /* EOI */
- vmx_disable_intercept_msr_write_x2apic(0x80b);
- /* SELF-IPI */
- vmx_disable_intercept_msr_write_x2apic(0x83f);
- }
+ for (msr = 0x800; msr <= 0x8ff; msr++)
+ vmx_disable_intercept_msr_read_x2apic(msr);
+
+ /* According SDM, in x2apic mode, the whole id reg is used. But in
+ * KVM, it only use the highest eight bits. Need to intercept it */
+ vmx_enable_intercept_msr_read_x2apic(0x802);
+ /* TMCCT */
+ vmx_enable_intercept_msr_read_x2apic(0x839);
+ /* TPR */
+ vmx_disable_intercept_msr_write_x2apic(0x808);
+ /* EOI */
+ vmx_disable_intercept_msr_write_x2apic(0x80b);
+ /* SELF-IPI */
+ vmx_disable_intercept_msr_write_x2apic(0x83f);
if (enable_ept) {
kvm_mmu_set_mask_ptes(0ull,
kvm_x86_ops->enable_log_dirty_pt_masked = NULL;
}
+ if (cpu_has_vmx_preemption_timer() && enable_preemption_timer) {
+ u64 vmx_msr;
+
+ rdmsrl(MSR_IA32_VMX_MISC, vmx_msr);
+ cpu_preemption_timer_multi =
+ vmx_msr & VMX_MISC_PREEMPTION_TIMER_RATE_MASK;
+ } else {
+ kvm_x86_ops->set_hv_timer = NULL;
+ kvm_x86_ops->cancel_hv_timer = NULL;
+ }
+
kvm_set_posted_intr_wakeup_handler(wakeup_handler);
+ kvm_mce_cap_supported |= MCG_LMCE_P;
+
return alloc_kvm_area();
out8:
return 1;
}
- if ((vmx->nested.msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
+ if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
kvm_inject_gp(vcpu, 0);
return 1;
return 1;
}
+static int handle_preemption_timer(struct kvm_vcpu *vcpu)
+{
+ kvm_lapic_expired_hv_timer(vcpu);
+ return 1;
+}
+
/*
* The exit handlers return 1 if the exit was handled fully and guest execution
* may resume. Otherwise they set the kvm_run parameter to indicate what needs
[EXIT_REASON_XRSTORS] = handle_xrstors,
[EXIT_REASON_PML_FULL] = handle_pml_full,
[EXIT_REASON_PCOMMIT] = handle_pcommit,
+ [EXIT_REASON_PREEMPTION_TIMER] = handle_preemption_timer,
};
static const int kvm_vmx_max_exit_handlers =
vmcs_write64(APIC_ACCESS_ADDR, hpa);
}
-static void vmx_hwapic_isr_update(struct kvm *kvm, int isr)
+static void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
{
u16 status;
u8 old;
- if (isr == -1)
- isr = 0;
+ if (max_isr == -1)
+ max_isr = 0;
status = vmcs_read16(GUEST_INTR_STATUS);
old = status >> 8;
- if (isr != old) {
+ if (max_isr != old) {
status &= 0xff;
- status |= isr << 8;
+ status |= max_isr << 8;
vmcs_write16(GUEST_INTR_STATUS, status);
}
}
msrs[i].host);
}
+void vmx_arm_hv_timer(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 tscl;
+ u32 delta_tsc;
+
+ if (vmx->hv_deadline_tsc == -1)
+ return;
+
+ tscl = rdtsc();
+ if (vmx->hv_deadline_tsc > tscl)
+ /* sure to be 32 bit only because checked on set_hv_timer */
+ delta_tsc = (u32)((vmx->hv_deadline_tsc - tscl) >>
+ cpu_preemption_timer_multi);
+ else
+ delta_tsc = 0;
+
+ vmcs_write32(VMX_PREEMPTION_TIMER_VALUE, delta_tsc);
+}
+
static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
atomic_switch_perf_msrs(vmx);
debugctlmsr = get_debugctlmsr();
+ vmx_arm_hv_timer(vcpu);
+
vmx->__launched = vmx->loaded_vmcs->launched;
asm(
/* Store host registers */
goto free_vmcs;
}
+ vmx->msr_ia32_feature_control_valid_bits = FEATURE_CONTROL_LOCKED;
+
return &vmx->vcpu;
free_vmcs:
vmx->nested.nested_vmx_secondary_ctls_high &=
~SECONDARY_EXEC_PCOMMIT;
}
+
+ if (nested_vmx_allowed(vcpu))
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+ FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ else
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+ ~FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
}
static void vmx_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
return X86EMUL_CONTINUE;
}
+#ifdef CONFIG_X86_64
+/* (a << shift) / divisor, return 1 if overflow otherwise 0 */
+static inline int u64_shl_div_u64(u64 a, unsigned int shift,
+ u64 divisor, u64 *result)
+{
+ u64 low = a << shift, high = a >> (64 - shift);
+
+ /* To avoid the overflow on divq */
+ if (high >= divisor)
+ return 1;
+
+ /* Low hold the result, high hold rem which is discarded */
+ asm("divq %2\n\t" : "=a" (low), "=d" (high) :
+ "rm" (divisor), "0" (low), "1" (high));
+ *result = low;
+
+ return 0;
+}
+
+static int vmx_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 tscl = rdtsc(), delta_tsc;
+
+ delta_tsc = guest_deadline_tsc - kvm_read_l1_tsc(vcpu, tscl);
+
+ /* Convert to host delta tsc if tsc scaling is enabled */
+ if (vcpu->arch.tsc_scaling_ratio != kvm_default_tsc_scaling_ratio &&
+ u64_shl_div_u64(delta_tsc,
+ kvm_tsc_scaling_ratio_frac_bits,
+ vcpu->arch.tsc_scaling_ratio,
+ &delta_tsc))
+ return -ERANGE;
+
+ /*
+ * If the delta tsc can't fit in the 32 bit after the multi shift,
+ * we can't use the preemption timer.
+ * It's possible that it fits on later vmentries, but checking
+ * on every vmentry is costly so we just use an hrtimer.
+ */
+ if (delta_tsc >> (cpu_preemption_timer_multi + 32))
+ return -ERANGE;
+
+ vmx->hv_deadline_tsc = tscl + delta_tsc;
+ vmcs_set_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+ return 0;
+}
+
+static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ vmx->hv_deadline_tsc = -1;
+ vmcs_clear_bits(PIN_BASED_VM_EXEC_CONTROL,
+ PIN_BASED_VMX_PREEMPTION_TIMER);
+}
+#endif
+
static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
{
if (ple_gap)
* this case, return 1, otherwise, return 0.
*
*/
-static int vmx_pre_block(struct kvm_vcpu *vcpu)
+static int pi_pre_block(struct kvm_vcpu *vcpu)
{
unsigned long flags;
unsigned int dest;
return 0;
}
-static void vmx_post_block(struct kvm_vcpu *vcpu)
+static int vmx_pre_block(struct kvm_vcpu *vcpu)
+{
+ if (pi_pre_block(vcpu))
+ return 1;
+
+ if (kvm_lapic_hv_timer_in_use(vcpu))
+ kvm_lapic_switch_to_sw_timer(vcpu);
+
+ return 0;
+}
+
+static void pi_post_block(struct kvm_vcpu *vcpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
struct pi_desc old, new;
}
}
+static void vmx_post_block(struct kvm_vcpu *vcpu)
+{
+ if (kvm_x86_ops->set_hv_timer)
+ kvm_lapic_switch_to_hv_timer(vcpu);
+
+ pi_post_block(vcpu);
+}
+
/*
* vmx_update_pi_irte - set IRTE for Posted-Interrupts
*
return ret;
}
+static void vmx_setup_mce(struct kvm_vcpu *vcpu)
+{
+ if (vcpu->arch.mcg_cap & MCG_LMCE_P)
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits |=
+ FEATURE_CONTROL_LMCE;
+ else
+ to_vmx(vcpu)->msr_ia32_feature_control_valid_bits &=
+ ~FEATURE_CONTROL_LMCE;
+}
+
static struct kvm_x86_ops vmx_x86_ops = {
.cpu_has_kvm_support = cpu_has_kvm_support,
.disabled_by_bios = vmx_disabled_by_bios,
.pmu_ops = &intel_pmu_ops,
.update_pi_irte = vmx_update_pi_irte,
+
+#ifdef CONFIG_X86_64
+ .set_hv_timer = vmx_set_hv_timer,
+ .cancel_hv_timer = vmx_cancel_hv_timer,
+#endif
+
+ .setup_mce = vmx_setup_mce,
};
static int __init vmx_init(void)