summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/debugfs.c46
-rw-r--r--arch/x86/kvm/hyperv.c5
-rw-r--r--arch/x86/kvm/lapic.c13
-rw-r--r--arch/x86/kvm/mmu.c35
-rw-r--r--arch/x86/kvm/svm.c28
-rw-r--r--arch/x86/kvm/vmx/nested.c4
-rw-r--r--arch/x86/kvm/vmx/vmx.c20
-rw-r--r--arch/x86/kvm/x86.c41
8 files changed, 97 insertions, 95 deletions
diff --git a/arch/x86/kvm/debugfs.c b/arch/x86/kvm/debugfs.c
index 329361b69d5e..018aebce33ff 100644
--- a/arch/x86/kvm/debugfs.c
+++ b/arch/x86/kvm/debugfs.c
@@ -8,11 +8,6 @@
#include <linux/debugfs.h>
#include "lapic.h"
-bool kvm_arch_has_vcpu_debugfs(void)
-{
- return true;
-}
-
static int vcpu_get_timer_advance_ns(void *data, u64 *val)
{
struct kvm_vcpu *vcpu = (struct kvm_vcpu *) data;
@@ -48,37 +43,22 @@ static int vcpu_get_tsc_scaling_frac_bits(void *data, u64 *val)
DEFINE_SIMPLE_ATTRIBUTE(vcpu_tsc_scaling_frac_fops, vcpu_get_tsc_scaling_frac_bits, NULL, "%llu\n");
-int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
+void kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
- struct dentry *ret;
-
- ret = debugfs_create_file("tsc-offset", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_offset_fops);
- if (!ret)
- return -ENOMEM;
+ debugfs_create_file("tsc-offset", 0444, vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_offset_fops);
- if (lapic_in_kernel(vcpu)) {
- ret = debugfs_create_file("lapic_timer_advance_ns", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_timer_advance_ns_fops);
- if (!ret)
- return -ENOMEM;
- }
+ if (lapic_in_kernel(vcpu))
+ debugfs_create_file("lapic_timer_advance_ns", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_timer_advance_ns_fops);
if (kvm_has_tsc_control) {
- ret = debugfs_create_file("tsc-scaling-ratio", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_scaling_fops);
- if (!ret)
- return -ENOMEM;
- ret = debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
- vcpu->debugfs_dentry,
- vcpu, &vcpu_tsc_scaling_frac_fops);
- if (!ret)
- return -ENOMEM;
-
+ debugfs_create_file("tsc-scaling-ratio", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_scaling_fops);
+ debugfs_create_file("tsc-scaling-ratio-frac-bits", 0444,
+ vcpu->debugfs_dentry, vcpu,
+ &vcpu_tsc_scaling_frac_fops);
}
-
- return 0;
}
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index c10a8b10b203..fff790a3f4ee 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -1781,7 +1781,7 @@ int kvm_vm_ioctl_hv_eventfd(struct kvm *kvm, struct kvm_hyperv_eventfd *args)
int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries)
{
- uint16_t evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+ uint16_t evmcs_ver = 0;
struct kvm_cpuid_entry2 cpuid_entries[] = {
{ .function = HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS },
{ .function = HYPERV_CPUID_INTERFACE },
@@ -1793,6 +1793,9 @@ int kvm_vcpu_ioctl_get_hv_cpuid(struct kvm_vcpu *vcpu, struct kvm_cpuid2 *cpuid,
};
int i, nent = ARRAY_SIZE(cpuid_entries);
+ if (kvm_x86_ops->nested_get_evmcs_version)
+ evmcs_ver = kvm_x86_ops->nested_get_evmcs_version(vcpu);
+
/* Skip NESTED_FEATURES if eVMCS is not supported */
if (!evmcs_ver)
--nent;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 0aa158657f20..e904ff06a83d 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -216,6 +216,9 @@ static void recalculate_apic_map(struct kvm *kvm)
if (!apic_x2apic_mode(apic) && !new->phys_map[xapic_id])
new->phys_map[xapic_id] = apic;
+ if (!kvm_apic_sw_enabled(apic))
+ continue;
+
ldr = kvm_lapic_get_reg(apic, APIC_LDR);
if (apic_x2apic_mode(apic)) {
@@ -258,6 +261,8 @@ static inline void apic_set_spiv(struct kvm_lapic *apic, u32 val)
static_key_slow_dec_deferred(&apic_sw_disabled);
else
static_key_slow_inc(&apic_sw_disabled.key);
+
+ recalculate_apic_map(apic->vcpu->kvm);
}
}
@@ -1548,7 +1553,6 @@ static void kvm_apic_inject_pending_timer_irqs(struct kvm_lapic *apic)
static void apic_timer_expired(struct kvm_lapic *apic)
{
struct kvm_vcpu *vcpu = apic->vcpu;
- struct swait_queue_head *q = &vcpu->wq;
struct kvm_timer *ktimer = &apic->lapic_timer;
if (atomic_read(&apic->lapic_timer.pending))
@@ -1566,13 +1570,6 @@ static void apic_timer_expired(struct kvm_lapic *apic)
atomic_inc(&apic->lapic_timer.pending);
kvm_set_pending_timer(vcpu);
-
- /*
- * For x86, the atomic_inc() is serialized, thus
- * using swait_active() is safe.
- */
- if (swait_active(q))
- swake_up_one(q);
}
static void start_sw_tscdeadline(struct kvm_lapic *apic)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 8f72526e2f68..218b277bfda3 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3466,7 +3466,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level,
/*
* Currently, fast page fault only works for direct mapping
* since the gfn is not stable for indirect shadow page. See
- * Documentation/virtual/kvm/locking.txt to get more detail.
+ * Documentation/virt/kvm/locking.txt to get more detail.
*/
fault_handled = fast_pf_fix_direct_spte(vcpu, sp,
iterator.sptep, spte,
@@ -5653,38 +5653,7 @@ static void kvm_mmu_invalidate_zap_pages_in_memslot(struct kvm *kvm,
struct kvm_memory_slot *slot,
struct kvm_page_track_notifier_node *node)
{
- struct kvm_mmu_page *sp;
- LIST_HEAD(invalid_list);
- unsigned long i;
- bool flush;
- gfn_t gfn;
-
- spin_lock(&kvm->mmu_lock);
-
- if (list_empty(&kvm->arch.active_mmu_pages))
- goto out_unlock;
-
- flush = slot_handle_all_level(kvm, slot, kvm_zap_rmapp, false);
-
- for (i = 0; i < slot->npages; i++) {
- gfn = slot->base_gfn + i;
-
- for_each_valid_sp(kvm, sp, gfn) {
- if (sp->gfn != gfn)
- continue;
-
- kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
- }
- if (need_resched() || spin_needbreak(&kvm->mmu_lock)) {
- kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
- flush = false;
- cond_resched_lock(&kvm->mmu_lock);
- }
- }
- kvm_mmu_remote_flush_or_zap(kvm, &invalid_list, flush);
-
-out_unlock:
- spin_unlock(&kvm->mmu_lock);
+ kvm_mmu_zap_all(kvm);
}
void kvm_mmu_init_vm(struct kvm *kvm)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 19f69df96758..e0368076a1ef 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1714,7 +1714,6 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
if (!entry)
return -EINVAL;
- new_entry = READ_ONCE(*entry);
new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
@@ -2143,12 +2142,20 @@ static struct kvm_vcpu *svm_create_vcpu(struct kvm *kvm, unsigned int id)
goto out;
}
+ svm->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+ GFP_KERNEL_ACCOUNT);
+ if (!svm->vcpu.arch.user_fpu) {
+ printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+ err = -ENOMEM;
+ goto free_partial_svm;
+ }
+
svm->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
GFP_KERNEL_ACCOUNT);
if (!svm->vcpu.arch.guest_fpu) {
printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
err = -ENOMEM;
- goto free_partial_svm;
+ goto free_user_fpu;
}
err = kvm_vcpu_init(&svm->vcpu, kvm, id);
@@ -2211,6 +2218,8 @@ uninit:
kvm_vcpu_uninit(&svm->vcpu);
free_svm:
kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
+free_user_fpu:
+ kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
free_partial_svm:
kmem_cache_free(kvm_vcpu_cache, svm);
out:
@@ -2241,6 +2250,7 @@ static void svm_free_vcpu(struct kvm_vcpu *vcpu)
__free_page(virt_to_page(svm->nested.hsave));
__free_pages(virt_to_page(svm->nested.msrpm), MSRPM_ALLOC_ORDER);
kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.user_fpu);
kmem_cache_free(x86_fpu_cache, svm->vcpu.arch.guest_fpu);
kmem_cache_free(kvm_vcpu_cache, svm);
}
@@ -5179,6 +5189,11 @@ static void svm_deliver_avic_intr(struct kvm_vcpu *vcpu, int vec)
kvm_vcpu_wake_up(vcpu);
}
+static bool svm_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
{
unsigned long flags;
@@ -7113,12 +7128,6 @@ failed:
return ret;
}
-static uint16_t nested_get_evmcs_version(struct kvm_vcpu *vcpu)
-{
- /* Not supported */
- return 0;
-}
-
static int nested_enable_evmcs(struct kvm_vcpu *vcpu,
uint16_t *vmcs_version)
{
@@ -7303,6 +7312,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.pmu_ops = &amd_pmu_ops,
.deliver_posted_interrupt = svm_deliver_avic_intr,
+ .dy_apicv_has_pending_interrupt = svm_dy_apicv_has_pending_interrupt,
.update_pi_irte = svm_update_pi_irte,
.setup_mce = svm_setup_mce,
@@ -7316,7 +7326,7 @@ static struct kvm_x86_ops svm_x86_ops __ro_after_init = {
.mem_enc_unreg_region = svm_unregister_enc_region,
.nested_enable_evmcs = nested_enable_evmcs,
- .nested_get_evmcs_version = nested_get_evmcs_version,
+ .nested_get_evmcs_version = NULL,
.need_emulation_on_page_fault = svm_need_emulation_on_page_fault,
};
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 0f1378789bd0..ced9fba32598 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -220,6 +220,8 @@ static void free_nested(struct kvm_vcpu *vcpu)
if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
return;
+ kvm_clear_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+
vmx->nested.vmxon = false;
vmx->nested.smm.vmxon = false;
free_vpid(vmx->nested.vpid02);
@@ -232,7 +234,9 @@ static void free_nested(struct kvm_vcpu *vcpu)
vmx->vmcs01.shadow_vmcs = NULL;
}
kfree(vmx->nested.cached_vmcs12);
+ vmx->nested.cached_vmcs12 = NULL;
kfree(vmx->nested.cached_shadow_vmcs12);
+ vmx->nested.cached_shadow_vmcs12 = NULL;
/* Unpin physical memory we referred to in the vmcs02 */
if (vmx->nested.apic_access_page) {
kvm_release_page_dirty(vmx->nested.apic_access_page);
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index a279447eb75b..c030c96fc81a 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -6117,6 +6117,11 @@ static int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
return max_irr;
}
+static bool vmx_dy_apicv_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+ return pi_test_on(vcpu_to_pi_desc(vcpu));
+}
+
static void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
{
if (!kvm_vcpu_apicv_active(vcpu))
@@ -6598,6 +6603,7 @@ static void vmx_free_vcpu(struct kvm_vcpu *vcpu)
free_loaded_vmcs(vmx->loaded_vmcs);
kfree(vmx->guest_msrs);
kvm_vcpu_uninit(vcpu);
+ kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
kmem_cache_free(kvm_vcpu_cache, vmx);
}
@@ -6613,12 +6619,20 @@ static struct kvm_vcpu *vmx_create_vcpu(struct kvm *kvm, unsigned int id)
if (!vmx)
return ERR_PTR(-ENOMEM);
+ vmx->vcpu.arch.user_fpu = kmem_cache_zalloc(x86_fpu_cache,
+ GFP_KERNEL_ACCOUNT);
+ if (!vmx->vcpu.arch.user_fpu) {
+ printk(KERN_ERR "kvm: failed to allocate kvm userspace's fpu\n");
+ err = -ENOMEM;
+ goto free_partial_vcpu;
+ }
+
vmx->vcpu.arch.guest_fpu = kmem_cache_zalloc(x86_fpu_cache,
GFP_KERNEL_ACCOUNT);
if (!vmx->vcpu.arch.guest_fpu) {
printk(KERN_ERR "kvm: failed to allocate vcpu's fpu\n");
err = -ENOMEM;
- goto free_partial_vcpu;
+ goto free_user_fpu;
}
vmx->vpid = allocate_vpid();
@@ -6721,6 +6735,8 @@ uninit_vcpu:
free_vcpu:
free_vpid(vmx->vpid);
kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.guest_fpu);
+free_user_fpu:
+ kmem_cache_free(x86_fpu_cache, vmx->vcpu.arch.user_fpu);
free_partial_vcpu:
kmem_cache_free(kvm_vcpu_cache, vmx);
return ERR_PTR(err);
@@ -7715,6 +7731,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
.sync_pir_to_irr = vmx_sync_pir_to_irr,
.deliver_posted_interrupt = vmx_deliver_posted_interrupt,
+ .dy_apicv_has_pending_interrupt = vmx_dy_apicv_has_pending_interrupt,
.set_tss_addr = vmx_set_tss_addr,
.set_identity_map_addr = vmx_set_identity_map_addr,
@@ -7780,6 +7797,7 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
.set_nested_state = NULL,
.get_vmcs12_pages = NULL,
.nested_enable_evmcs = NULL,
+ .nested_get_evmcs_version = NULL,
.need_emulation_on_page_fault = vmx_need_emulation_on_page_fault,
};
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 58305cf81182..290c3c3efb87 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3306,6 +3306,10 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
kvm_x86_ops->vcpu_load(vcpu, cpu);
+ fpregs_assert_state_consistent();
+ if (test_thread_flag(TIF_NEED_FPU_LOAD))
+ switch_fpu_return();
+
/* Apply any externally detected TSC adjustments (due to suspend) */
if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
@@ -6590,12 +6594,13 @@ restart:
unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
toggle_interruptibility(vcpu, ctxt->interruptibility);
vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
- kvm_rip_write(vcpu, ctxt->eip);
- if (r == EMULATE_DONE && ctxt->tf)
- kvm_vcpu_do_singlestep(vcpu, &r);
if (!ctxt->have_exception ||
- exception_type(ctxt->exception.vector) == EXCPT_TRAP)
+ exception_type(ctxt->exception.vector) == EXCPT_TRAP) {
+ kvm_rip_write(vcpu, ctxt->eip);
+ if (r == EMULATE_DONE && ctxt->tf)
+ kvm_vcpu_do_singlestep(vcpu, &r);
__kvm_set_rflags(vcpu, ctxt->eflags);
+ }
/*
* For STI, interrupts are shadowed; so KVM_REQ_EVENT will
@@ -7202,7 +7207,7 @@ static void kvm_sched_yield(struct kvm *kvm, unsigned long dest_id)
rcu_read_unlock();
- if (target)
+ if (target && READ_ONCE(target->ready))
kvm_vcpu_yield_to(target);
}
@@ -7242,6 +7247,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
break;
case KVM_HC_KICK_CPU:
kvm_pv_kick_cpu_op(vcpu->kvm, a0, a1);
+ kvm_sched_yield(vcpu->kvm, a1);
ret = 0;
break;
#ifdef CONFIG_X86_64
@@ -7990,9 +7996,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
trace_kvm_entry(vcpu->vcpu_id);
guest_enter_irqoff();
- fpregs_assert_state_consistent();
- if (test_thread_flag(TIF_NEED_FPU_LOAD))
- switch_fpu_return();
+ /* The preempt notifier should have taken care of the FPU already. */
+ WARN_ON_ONCE(test_thread_flag(TIF_NEED_FPU_LOAD));
if (unlikely(vcpu->arch.switch_db_regs)) {
set_debugreg(0, 7);
@@ -8270,7 +8275,7 @@ static void kvm_load_guest_fpu(struct kvm_vcpu *vcpu)
{
fpregs_lock();
- copy_fpregs_to_fpstate(&current->thread.fpu);
+ copy_fpregs_to_fpstate(vcpu->arch.user_fpu);
/* PKRU is separately restored in kvm_x86_ops->run. */
__copy_kernel_to_fpregs(&vcpu->arch.guest_fpu->state,
~XFEATURE_MASK_PKRU);
@@ -8287,7 +8292,7 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
fpregs_lock();
copy_fpregs_to_fpstate(vcpu->arch.guest_fpu);
- copy_kernel_to_fpregs(&current->thread.fpu.state);
+ copy_kernel_to_fpregs(&vcpu->arch.user_fpu->state);
fpregs_mark_activate();
fpregs_unlock();
@@ -9694,6 +9699,22 @@ int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
}
+bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu)
+{
+ if (READ_ONCE(vcpu->arch.pv.pv_unhalted))
+ return true;
+
+ if (kvm_test_request(KVM_REQ_NMI, vcpu) ||
+ kvm_test_request(KVM_REQ_SMI, vcpu) ||
+ kvm_test_request(KVM_REQ_EVENT, vcpu))
+ return true;
+
+ if (vcpu->arch.apicv_active && kvm_x86_ops->dy_apicv_has_pending_interrupt(vcpu))
+ return true;
+
+ return false;
+}
+
bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu)
{
return vcpu->arch.preempted_in_kernel;
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-04 20:00:37 +0300