summaryrefslogtreecommitdiff
path: root/arch/x86/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kvm')
-rw-r--r--arch/x86/kvm/Kconfig1
-rw-r--r--arch/x86/kvm/ioapic.c36
-rw-r--r--arch/x86/kvm/kvm_onhyperv.h5
-rw-r--r--arch/x86/kvm/svm/avic.c37
-rw-r--r--arch/x86/kvm/svm/sev.c27
-rw-r--r--arch/x86/kvm/svm/svm.c37
-rw-r--r--arch/x86/kvm/svm/svm_onhyperv.h15
-rw-r--r--arch/x86/kvm/vmx/nested.c25
-rw-r--r--arch/x86/kvm/vmx/vmenter.S4
-rw-r--r--arch/x86/kvm/vmx/vmx.c12
-rw-r--r--arch/x86/kvm/x86.c14
11 files changed, 165 insertions, 48 deletions
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 8e578311ca9d..89ca7f4c1464 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -46,7 +46,6 @@ config KVM
select KVM_XFER_TO_GUEST_WORK
select KVM_GENERIC_DIRTYLOG_READ_PROTECT
select KVM_VFIO
- select SRCU
select INTERVAL_TREE
select HAVE_KVM_PM_NOTIFIER if PM
select KVM_GENERIC_HARDWARE_ENABLING
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 042dee556125..995eb5054360 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -368,9 +368,39 @@ static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
mask_after = e->fields.mask;
if (mask_before != mask_after)
kvm_fire_mask_notifiers(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index, mask_after);
- if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG
- && ioapic->irr & (1 << index))
- ioapic_service(ioapic, index, false);
+ if (e->fields.trig_mode == IOAPIC_LEVEL_TRIG &&
+ ioapic->irr & (1 << index) && !e->fields.mask && !e->fields.remote_irr) {
+ /*
+ * Pending status in irr may be outdated: the IRQ line may have
+ * already been deasserted by a device while the IRQ was masked.
+ * This occurs, for instance, if the interrupt is handled in a
+ * Linux guest as a oneshot interrupt (IRQF_ONESHOT). In this
+ * case the guest acknowledges the interrupt to the device in
+ * its threaded irq handler, i.e. after the EOI but before
+ * unmasking, so at the time of unmasking the IRQ line is
+ * already down but our pending irr bit is still set. In such
+ * cases, injecting this pending interrupt to the guest is
+ * buggy: the guest will receive an extra unwanted interrupt.
+ *
+ * So we need to check here if the IRQ is actually still pending.
+ * As we are generally not able to probe the IRQ line status
+ * directly, we do it through irqfd resampler. Namely, we clear
+ * the pending status and notify the resampler that this interrupt
+ * is done, without actually injecting it into the guest. If the
+ * IRQ line is actually already deasserted, we are done. If it is
+ * still asserted, a new interrupt will be shortly triggered
+ * through irqfd and injected into the guest.
+ *
+ * If, however, it's not possible to resample (no irqfd resampler
+ * registered for this irq), then unconditionally inject this
+ * pending interrupt into the guest, so the guest will not miss
+ * an interrupt, although may get an extra unwanted interrupt.
+ */
+ if (kvm_notify_irqfd_resampler(ioapic->kvm, KVM_IRQCHIP_IOAPIC, index))
+ ioapic->irr &= ~(1 << index);
+ else
+ ioapic_service(ioapic, index, false);
+ }
if (e->fields.delivery_mode == APIC_DM_FIXED) {
struct kvm_lapic_irq irq;
diff --git a/arch/x86/kvm/kvm_onhyperv.h b/arch/x86/kvm/kvm_onhyperv.h
index 287e98ef9df3..6272dabec02d 100644
--- a/arch/x86/kvm/kvm_onhyperv.h
+++ b/arch/x86/kvm/kvm_onhyperv.h
@@ -12,6 +12,11 @@ int hv_remote_flush_tlb_with_range(struct kvm *kvm,
int hv_remote_flush_tlb(struct kvm *kvm);
void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp);
#else /* !CONFIG_HYPERV */
+static inline int hv_remote_flush_tlb(struct kvm *kvm)
+{
+ return -EOPNOTSUPP;
+}
+
static inline void hv_track_root_tdp(struct kvm_vcpu *vcpu, hpa_t root_tdp)
{
}
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index ca684979e90d..cfc8ab773025 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -27,19 +27,38 @@
#include "irq.h"
#include "svm.h"
-/* AVIC GATAG is encoded using VM and VCPU IDs */
-#define AVIC_VCPU_ID_BITS 8
-#define AVIC_VCPU_ID_MASK ((1 << AVIC_VCPU_ID_BITS) - 1)
+/*
+ * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID,
+ * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry
+ * if an interrupt can't be delivered, e.g. because the vCPU isn't running.
+ *
+ * For the vCPU ID, use however many bits are currently allowed for the max
+ * guest physical APIC ID (limited by the size of the physical ID table), and
+ * use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the
+ * size of the GATag is defined by hardware (32 bits), but is an opaque value
+ * as far as hardware is concerned.
+ */
+#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK
-#define AVIC_VM_ID_BITS 24
-#define AVIC_VM_ID_NR (1 << AVIC_VM_ID_BITS)
-#define AVIC_VM_ID_MASK ((1 << AVIC_VM_ID_BITS) - 1)
+#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK)
+#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)
-#define AVIC_GATAG(x, y) (((x & AVIC_VM_ID_MASK) << AVIC_VCPU_ID_BITS) | \
- (y & AVIC_VCPU_ID_MASK))
-#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VCPU_ID_BITS) & AVIC_VM_ID_MASK)
+#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK)
#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)
+#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
+ ((vcpu_id) & AVIC_VCPU_ID_MASK))
+#define AVIC_GATAG(vm_id, vcpu_id) \
+({ \
+ u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \
+ \
+ WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \
+ WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \
+ ga_tag; \
+})
+
+static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u);
+
static bool force_avic;
module_param_unsafe(force_avic, bool, 0444);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index c25aeb550cd9..69ae5e1b3120 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -12,6 +12,7 @@
#include <linux/kvm_host.h>
#include <linux/kernel.h>
#include <linux/highmem.h>
+#include <linux/psp.h>
#include <linux/psp-sev.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
@@ -1767,18 +1768,20 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
{
struct kvm_sev_info *dst_sev = &to_kvm_svm(kvm)->sev_info;
struct kvm_sev_info *src_sev, *cg_cleanup_sev;
- struct file *source_kvm_file;
+ struct fd f = fdget(source_fd);
struct kvm *source_kvm;
bool charged = false;
int ret;
- source_kvm_file = fget(source_fd);
- if (!file_is_kvm(source_kvm_file)) {
+ if (!f.file)
+ return -EBADF;
+
+ if (!file_is_kvm(f.file)) {
ret = -EBADF;
goto out_fput;
}
- source_kvm = source_kvm_file->private_data;
+ source_kvm = f.file->private_data;
ret = sev_lock_two_vms(kvm, source_kvm);
if (ret)
goto out_fput;
@@ -1828,8 +1831,7 @@ out_dst_cgroup:
out_unlock:
sev_unlock_two_vms(kvm, source_kvm);
out_fput:
- if (source_kvm_file)
- fput(source_kvm_file);
+ fdput(f);
return ret;
}
@@ -2046,18 +2048,20 @@ failed:
int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
{
- struct file *source_kvm_file;
+ struct fd f = fdget(source_fd);
struct kvm *source_kvm;
struct kvm_sev_info *source_sev, *mirror_sev;
int ret;
- source_kvm_file = fget(source_fd);
- if (!file_is_kvm(source_kvm_file)) {
+ if (!f.file)
+ return -EBADF;
+
+ if (!file_is_kvm(f.file)) {
ret = -EBADF;
goto e_source_fput;
}
- source_kvm = source_kvm_file->private_data;
+ source_kvm = f.file->private_data;
ret = sev_lock_two_vms(kvm, source_kvm);
if (ret)
goto e_source_fput;
@@ -2103,8 +2107,7 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
e_unlock:
sev_unlock_two_vms(kvm, source_kvm);
e_source_fput:
- if (source_kvm_file)
- fput(source_kvm_file);
+ fdput(f);
return ret;
}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 252e7f37e4e2..f25bc3cbb250 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3729,7 +3729,7 @@ static void svm_enable_nmi_window(struct kvm_vcpu *vcpu)
svm->vmcb->save.rflags |= (X86_EFLAGS_TF | X86_EFLAGS_RF);
}
-static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
+static void svm_flush_tlb_asid(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -3753,6 +3753,37 @@ static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
svm->current_vmcb->asid_generation--;
}
+static void svm_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+ hpa_t root_tdp = vcpu->arch.mmu->root.hpa;
+
+ /*
+ * When running on Hyper-V with EnlightenedNptTlb enabled, explicitly
+ * flush the NPT mappings via hypercall as flushing the ASID only
+ * affects virtual to physical mappings, it does not invalidate guest
+ * physical to host physical mappings.
+ */
+ if (svm_hv_is_enlightened_tlb_enabled(vcpu) && VALID_PAGE(root_tdp))
+ hyperv_flush_guest_mapping(root_tdp);
+
+ svm_flush_tlb_asid(vcpu);
+}
+
+static void svm_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+ /*
+ * When running on Hyper-V with EnlightenedNptTlb enabled, remote TLB
+ * flushes should be routed to hv_remote_flush_tlb() without requesting
+ * a "regular" remote flush. Reaching this point means either there's
+ * a KVM bug or a prior hv_remote_flush_tlb() call failed, both of
+ * which might be fatal to the guest. Yell, but try to recover.
+ */
+ if (WARN_ON_ONCE(svm_hv_is_enlightened_tlb_enabled(vcpu)))
+ hv_remote_flush_tlb(vcpu->kvm);
+
+ svm_flush_tlb_asid(vcpu);
+}
+
static void svm_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t gva)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -4745,10 +4776,10 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.set_rflags = svm_set_rflags,
.get_if_flag = svm_get_if_flag,
- .flush_tlb_all = svm_flush_tlb_current,
+ .flush_tlb_all = svm_flush_tlb_all,
.flush_tlb_current = svm_flush_tlb_current,
.flush_tlb_gva = svm_flush_tlb_gva,
- .flush_tlb_guest = svm_flush_tlb_current,
+ .flush_tlb_guest = svm_flush_tlb_asid,
.vcpu_pre_run = svm_vcpu_pre_run,
.vcpu_run = svm_vcpu_run,
diff --git a/arch/x86/kvm/svm/svm_onhyperv.h b/arch/x86/kvm/svm/svm_onhyperv.h
index cff838f15db5..786d46d73a8e 100644
--- a/arch/x86/kvm/svm/svm_onhyperv.h
+++ b/arch/x86/kvm/svm/svm_onhyperv.h
@@ -6,6 +6,8 @@
#ifndef __ARCH_X86_KVM_SVM_ONHYPERV_H__
#define __ARCH_X86_KVM_SVM_ONHYPERV_H__
+#include <asm/mshyperv.h>
+
#if IS_ENABLED(CONFIG_HYPERV)
#include "kvm_onhyperv.h"
@@ -15,6 +17,14 @@ static struct kvm_x86_ops svm_x86_ops;
int svm_hv_enable_l2_tlb_flush(struct kvm_vcpu *vcpu);
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+ struct hv_vmcb_enlightenments *hve = &to_svm(vcpu)->vmcb->control.hv_enlightenments;
+
+ return ms_hyperv.nested_features & HV_X64_NESTED_ENLIGHTENED_TLB &&
+ !!hve->hv_enlightenments_control.enlightened_npt_tlb;
+}
+
static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
{
struct hv_vmcb_enlightenments *hve = &vmcb->control.hv_enlightenments;
@@ -80,6 +90,11 @@ static inline void svm_hv_update_vp_id(struct vmcb *vmcb, struct kvm_vcpu *vcpu)
}
#else
+static inline bool svm_hv_is_enlightened_tlb_enabled(struct kvm_vcpu *vcpu)
+{
+ return false;
+}
+
static inline void svm_hv_init_vmcb(struct vmcb *vmcb)
{
}
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 7c4f5ca405c7..768487611db7 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -2903,7 +2903,7 @@ static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- bool ia32e;
+ bool ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
if (CC(!nested_host_cr0_valid(vcpu, vmcs12->host_cr0)) ||
CC(!nested_host_cr4_valid(vcpu, vmcs12->host_cr4)) ||
@@ -2923,12 +2923,6 @@ static int nested_vmx_check_host_state(struct kvm_vcpu *vcpu,
vmcs12->host_ia32_perf_global_ctrl)))
return -EINVAL;
-#ifdef CONFIG_X86_64
- ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
-#else
- ia32e = false;
-#endif
-
if (ia32e) {
if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
return -EINVAL;
@@ -3022,7 +3016,7 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12,
enum vm_entry_failure_code *entry_failure_code)
{
- bool ia32e;
+ bool ia32e = !!(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE);
*entry_failure_code = ENTRY_FAIL_DEFAULT;
@@ -3048,6 +3042,13 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
vmcs12->guest_ia32_perf_global_ctrl)))
return -EINVAL;
+ if (CC((vmcs12->guest_cr0 & (X86_CR0_PG | X86_CR0_PE)) == X86_CR0_PG))
+ return -EINVAL;
+
+ if (CC(ia32e && !(vmcs12->guest_cr4 & X86_CR4_PAE)) ||
+ CC(ia32e && !(vmcs12->guest_cr0 & X86_CR0_PG)))
+ return -EINVAL;
+
/*
* If the load IA32_EFER VM-entry control is 1, the following checks
* are performed on the field for the IA32_EFER MSR:
@@ -3059,7 +3060,6 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
*/
if (to_vmx(vcpu)->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_EFER)) {
- ia32e = (vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) != 0;
if (CC(!kvm_valid_efer(vcpu, vmcs12->guest_ia32_efer)) ||
CC(ia32e != !!(vmcs12->guest_ia32_efer & EFER_LMA)) ||
CC(((vmcs12->guest_cr0 & X86_CR0_PG) &&
@@ -3868,7 +3868,12 @@ static void nested_vmx_inject_exception_vmexit(struct kvm_vcpu *vcpu)
exit_qual = 0;
}
- if (ex->has_error_code) {
+ /*
+ * Unlike AMD's Paged Real Mode, which reports an error code on #PF
+ * VM-Exits even if the CPU is in Real Mode, Intel VMX never sets the
+ * "has error code" flags on VM-Exit if the CPU is in Real Mode.
+ */
+ if (ex->has_error_code && is_protmode(vcpu)) {
/*
* Intel CPUs do not generate error codes with bits 31:16 set,
* and more importantly VMX disallows setting bits 31:16 in the
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index f550540ed54e..631fd7da2bc3 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -262,7 +262,7 @@ SYM_INNER_LABEL(vmx_vmexit, SYM_L_GLOBAL)
* eIBRS has its own protection against poisoned RSB, so it doesn't
* need the RSB filling sequence. But it does need to be enabled, and a
* single call to retire, before the first unbalanced RET.
- */
+ */
FILL_RETURN_BUFFER %_ASM_CX, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT,\
X86_FEATURE_RSB_VMEXIT_LITE
@@ -311,7 +311,7 @@ SYM_FUNC_END(vmx_do_nmi_irqoff)
* vmread_error_trampoline - Trampoline from inline asm to vmread_error()
* @field: VMCS field encoding that failed
* @fault: %true if the VMREAD faulted, %false if it failed
-
+ *
* Save and restore volatile registers across a call to vmread_error(). Note,
* all parameters are passed on the stack.
*/
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index bcac3efcde41..d2d6e1b6c788 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -874,7 +874,7 @@ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu)
*/
if (is_guest_mode(vcpu))
eb |= get_vmcs12(vcpu)->exception_bitmap;
- else {
+ else {
int mask = 0, match = 0;
if (enable_ept && (eb & (1u << PF_VECTOR))) {
@@ -1282,7 +1282,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
}
}
- if (vmx->nested.need_vmcs12_to_shadow_sync)
+ if (vmx->nested.need_vmcs12_to_shadow_sync)
nested_sync_vmcs12_to_shadow(vcpu);
if (vmx->guest_state_loaded)
@@ -5049,10 +5049,10 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
if (to_vmx(vcpu)->nested.nested_run_pending)
return -EBUSY;
- /*
- * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
- * e.g. if the IRQ arrived asynchronously after checking nested events.
- */
+ /*
+ * An IRQ must not be injected into L2 if it's supposed to VM-Exit,
+ * e.g. if the IRQ arrived asynchronously after checking nested events.
+ */
if (for_injection && is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
return -EBUSY;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7713420abab0..3d852ce84920 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4432,6 +4432,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_VAPIC:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_VM_DISABLE_NX_HUGE_PAGES:
+ case KVM_CAP_IRQFD_RESAMPLE:
r = 1;
break;
case KVM_CAP_EXIT_HYPERCALL:
@@ -8903,6 +8904,8 @@ restart:
}
if (ctxt->have_exception) {
+ WARN_ON_ONCE(vcpu->mmio_needed && !vcpu->mmio_is_write);
+ vcpu->mmio_needed = false;
r = 1;
inject_emulated_exception(vcpu);
} else if (vcpu->arch.pio.count) {
@@ -9906,13 +9909,20 @@ int kvm_check_nested_events(struct kvm_vcpu *vcpu)
static void kvm_inject_exception(struct kvm_vcpu *vcpu)
{
+ /*
+ * Suppress the error code if the vCPU is in Real Mode, as Real Mode
+ * exceptions don't report error codes. The presence of an error code
+ * is carried with the exception and only stripped when the exception
+ * is injected as intercepted #PF VM-Exits for AMD's Paged Real Mode do
+ * report an error code despite the CPU being in Real Mode.
+ */
+ vcpu->arch.exception.has_error_code &= is_protmode(vcpu);
+
trace_kvm_inj_exception(vcpu->arch.exception.vector,
vcpu->arch.exception.has_error_code,
vcpu->arch.exception.error_code,
vcpu->arch.exception.injected);
- if (vcpu->arch.exception.error_code && !is_protmode(vcpu))
- vcpu->arch.exception.error_code = false;
static_call(kvm_x86_inject_exception)(vcpu);
}
generated by cgit (git 2.34.1) at 2025-04-21 21:54:39 +0000