Update Linux to v5.10.109
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.109.tar.xz
Change-Id: I19bca9fc6762d4e63bcf3e4cba88bbe560d9c76c
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 3041015..0c2389d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1,6 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/frame.h>
+#include <linux/objtool.h>
#include <linux/percpu.h>
#include <asm/debugreg.h>
@@ -10,6 +10,7 @@
#include "hyperv.h"
#include "mmu.h"
#include "nested.h"
+#include "pmu.h"
#include "trace.h"
#include "x86.h"
@@ -170,15 +171,6 @@
static int nested_vmx_failValid(struct kvm_vcpu *vcpu,
u32 vm_instruction_error)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- /*
- * failValid writes the error number to the current VMCS, which
- * can't be done if there isn't a current VMCS.
- */
- if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
- return nested_vmx_failInvalid(vcpu);
-
vmx_set_rflags(vcpu, (vmx_get_rflags(vcpu)
& ~(X86_EFLAGS_CF | X86_EFLAGS_PF | X86_EFLAGS_AF |
X86_EFLAGS_SF | X86_EFLAGS_OF))
@@ -191,6 +183,20 @@
return kvm_skip_emulated_instruction(vcpu);
}
+static int nested_vmx_fail(struct kvm_vcpu *vcpu, u32 vm_instruction_error)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * failValid writes the error number to the current VMCS, which
+ * can't be done if there isn't a current VMCS.
+ */
+ if (vmx->nested.current_vmptr == -1ull && !vmx->nested.hv_evmcs)
+ return nested_vmx_failInvalid(vcpu);
+
+ return nested_vmx_failValid(vcpu, vm_instruction_error);
+}
+
static void nested_vmx_abort(struct kvm_vcpu *vcpu, u32 indicator)
{
/* TODO: not to reset guest simply here. */
@@ -227,50 +233,6 @@
vmx->nested.hv_evmcs = NULL;
}
-/*
- * Free whatever needs to be freed from vmx->nested when L1 goes down, or
- * just stops using VMX.
- */
-static void free_nested(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(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);
- vmx->nested.posted_intr_nv = -1;
- vmx->nested.current_vmptr = -1ull;
- if (enable_shadow_vmcs) {
- vmx_disable_shadow_vmcs(vmx);
- vmcs_clear(vmx->vmcs01.shadow_vmcs);
- free_vmcs(vmx->vmcs01.shadow_vmcs);
- 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);
- vmx->nested.apic_access_page = NULL;
- }
- kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
- kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
- vmx->nested.pi_desc = NULL;
-
- kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
-
- nested_release_evmcs(vcpu);
-
- free_loaded_vmcs(&vmx->nested.vmcs02);
-}
-
static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
struct loaded_vmcs *prev)
{
@@ -296,7 +258,7 @@
struct loaded_vmcs *prev;
int cpu;
- if (vmx->loaded_vmcs == vmcs)
+ if (WARN_ON_ONCE(vmx->loaded_vmcs == vmcs))
return;
cpu = get_cpu();
@@ -306,7 +268,54 @@
vmx_sync_vmcs_host_state(vmx, prev);
put_cpu();
- vmx_segment_cache_clear(vmx);
+ vmx_register_cache_reset(vcpu);
+}
+
+/*
+ * Free whatever needs to be freed from vmx->nested when L1 goes down, or
+ * just stops using VMX.
+ */
+static void free_nested(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ if (WARN_ON_ONCE(vmx->loaded_vmcs != &vmx->vmcs01))
+ vmx_switch_vmcs(vcpu, &vmx->vmcs01);
+
+ if (!vmx->nested.vmxon && !vmx->nested.smm.vmxon)
+ return;
+
+ kvm_clear_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
+
+ vmx->nested.vmxon = false;
+ vmx->nested.smm.vmxon = false;
+ free_vpid(vmx->nested.vpid02);
+ vmx->nested.posted_intr_nv = -1;
+ vmx->nested.current_vmptr = -1ull;
+ if (enable_shadow_vmcs) {
+ vmx_disable_shadow_vmcs(vmx);
+ vmcs_clear(vmx->vmcs01.shadow_vmcs);
+ free_vmcs(vmx->vmcs01.shadow_vmcs);
+ 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_clean(vmx->nested.apic_access_page);
+ vmx->nested.apic_access_page = NULL;
+ }
+ kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
+ kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
+ vmx->nested.pi_desc = NULL;
+
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.guest_mmu, KVM_MMU_ROOTS_ALL);
+
+ nested_release_evmcs(vcpu);
+
+ free_loaded_vmcs(&vmx->nested.vmcs02);
}
/*
@@ -317,8 +326,6 @@
{
vcpu_load(vcpu);
vmx_leave_nested(vcpu);
- vmx_switch_vmcs(vcpu, &to_vmx(vcpu)->vmcs01);
- free_nested(vcpu);
vcpu_put(vcpu);
}
@@ -327,19 +334,19 @@
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 exit_reason;
+ u32 vm_exit_reason;
unsigned long exit_qualification = vcpu->arch.exit_qualification;
if (vmx->nested.pml_full) {
- exit_reason = EXIT_REASON_PML_FULL;
+ vm_exit_reason = EXIT_REASON_PML_FULL;
vmx->nested.pml_full = false;
exit_qualification &= INTR_INFO_UNBLOCK_NMI;
} else if (fault->error_code & PFERR_RSVD_MASK)
- exit_reason = EXIT_REASON_EPT_MISCONFIG;
+ vm_exit_reason = EXIT_REASON_EPT_MISCONFIG;
else
- exit_reason = EXIT_REASON_EPT_VIOLATION;
+ vm_exit_reason = EXIT_REASON_EPT_VIOLATION;
- nested_vmx_vmexit(vcpu, exit_reason, 0, exit_qualification);
+ nested_vmx_vmexit(vcpu, vm_exit_reason, 0, exit_qualification);
vmcs12->guest_physical_address = fault->address;
}
@@ -352,9 +359,8 @@
to_vmx(vcpu)->nested.msrs.ept_caps &
VMX_EPT_EXECUTE_ONLY_BIT,
nested_ept_ad_enabled(vcpu),
- nested_ept_get_cr3(vcpu));
- vcpu->arch.mmu->set_cr3 = vmx_set_cr3;
- vcpu->arch.mmu->get_cr3 = nested_ept_get_cr3;
+ nested_ept_get_eptp(vcpu));
+ vcpu->arch.mmu->get_guest_pgd = nested_ept_get_eptp;
vcpu->arch.mmu->inject_page_fault = nested_ept_inject_page_fault;
vcpu->arch.mmu->get_pdptr = kvm_pdptr_read;
@@ -437,11 +443,6 @@
}
}
-static bool page_address_valid(struct kvm_vcpu *vcpu, gpa_t gpa)
-{
- return PAGE_ALIGNED(gpa) && !(gpa >> cpuid_maxphyaddr(vcpu));
-}
-
static int nested_vmx_check_io_bitmap_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
@@ -543,7 +544,8 @@
}
}
-static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap) {
+static inline void enable_x2apic_msr_intercepts(unsigned long *msr_bitmap)
+{
int msr;
for (msr = 0x800; msr <= 0x8ff; msr += BITS_PER_LONG) {
@@ -616,6 +618,7 @@
}
/* KVM unconditionally exposes the FS/GS base MSRs to L1. */
+#ifdef CONFIG_X86_64
nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
MSR_FS_BASE, MSR_TYPE_RW);
@@ -624,6 +627,7 @@
nested_vmx_disable_intercept_for_msr(msr_bitmap_l1, msr_bitmap_l0,
MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+#endif
/*
* Checking the L0->L1 bitmap is trying to verify two things:
@@ -697,11 +701,6 @@
VM_EXIT_ACK_INTR_ON_EXIT;
}
-static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu)
-{
- return nested_cpu_has_nmi_exiting(get_vmcs12(vcpu));
-}
-
static int nested_vmx_check_apic_access_controls(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
@@ -926,9 +925,61 @@
}
return 0;
fail:
+ /* Note, max_msr_list_size is at most 4096, i.e. this can't wrap. */
return i + 1;
}
+static bool nested_vmx_get_vmexit_msr_value(struct kvm_vcpu *vcpu,
+ u32 msr_index,
+ u64 *data)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * If the L0 hypervisor stored a more accurate value for the TSC that
+ * does not include the time taken for emulation of the L2->L1
+ * VM-exit in L0, use the more accurate value.
+ */
+ if (msr_index == MSR_IA32_TSC) {
+ int i = vmx_find_loadstore_msr_slot(&vmx->msr_autostore.guest,
+ MSR_IA32_TSC);
+
+ if (i >= 0) {
+ u64 val = vmx->msr_autostore.guest.val[i].value;
+
+ *data = kvm_read_l1_tsc(vcpu, val);
+ return true;
+ }
+ }
+
+ if (kvm_get_msr(vcpu, msr_index, data)) {
+ pr_debug_ratelimited("%s cannot read MSR (0x%x)\n", __func__,
+ msr_index);
+ return false;
+ }
+ return true;
+}
+
+static bool read_and_check_msr_entry(struct kvm_vcpu *vcpu, u64 gpa, int i,
+ struct vmx_msr_entry *e)
+{
+ if (kvm_vcpu_read_guest(vcpu,
+ gpa + i * sizeof(*e),
+ e, 2 * sizeof(u32))) {
+ pr_debug_ratelimited(
+ "%s cannot read MSR entry (%u, 0x%08llx)\n",
+ __func__, i, gpa + i * sizeof(*e));
+ return false;
+ }
+ if (nested_vmx_store_msr_check(vcpu, e)) {
+ pr_debug_ratelimited(
+ "%s check failed (%u, 0x%x, 0x%x)\n",
+ __func__, i, e->index, e->reserved);
+ return false;
+ }
+ return true;
+}
+
static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
{
u64 data;
@@ -940,26 +991,12 @@
if (unlikely(i >= max_msr_list_size))
return -EINVAL;
- if (kvm_vcpu_read_guest(vcpu,
- gpa + i * sizeof(e),
- &e, 2 * sizeof(u32))) {
- pr_debug_ratelimited(
- "%s cannot read MSR entry (%u, 0x%08llx)\n",
- __func__, i, gpa + i * sizeof(e));
+ if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
return -EINVAL;
- }
- if (nested_vmx_store_msr_check(vcpu, &e)) {
- pr_debug_ratelimited(
- "%s check failed (%u, 0x%x, 0x%x)\n",
- __func__, i, e.index, e.reserved);
+
+ if (!nested_vmx_get_vmexit_msr_value(vcpu, e.index, &data))
return -EINVAL;
- }
- if (kvm_get_msr(vcpu, e.index, &data)) {
- pr_debug_ratelimited(
- "%s cannot read MSR (%u, 0x%x)\n",
- __func__, i, e.index);
- return -EINVAL;
- }
+
if (kvm_vcpu_write_guest(vcpu,
gpa + i * sizeof(e) +
offsetof(struct vmx_msr_entry, value),
@@ -973,6 +1010,60 @@
return 0;
}
+static bool nested_msr_store_list_has_msr(struct kvm_vcpu *vcpu, u32 msr_index)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ u32 count = vmcs12->vm_exit_msr_store_count;
+ u64 gpa = vmcs12->vm_exit_msr_store_addr;
+ struct vmx_msr_entry e;
+ u32 i;
+
+ for (i = 0; i < count; i++) {
+ if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
+ return false;
+
+ if (e.index == msr_index)
+ return true;
+ }
+ return false;
+}
+
+static void prepare_vmx_msr_autostore_list(struct kvm_vcpu *vcpu,
+ u32 msr_index)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmx_msrs *autostore = &vmx->msr_autostore.guest;
+ bool in_vmcs12_store_list;
+ int msr_autostore_slot;
+ bool in_autostore_list;
+ int last;
+
+ msr_autostore_slot = vmx_find_loadstore_msr_slot(autostore, msr_index);
+ in_autostore_list = msr_autostore_slot >= 0;
+ in_vmcs12_store_list = nested_msr_store_list_has_msr(vcpu, msr_index);
+
+ if (in_vmcs12_store_list && !in_autostore_list) {
+ if (autostore->nr == MAX_NR_LOADSTORE_MSRS) {
+ /*
+ * Emulated VMEntry does not fail here. Instead a less
+ * accurate value will be returned by
+ * nested_vmx_get_vmexit_msr_value() using kvm_get_msr()
+ * instead of reading the value from the vmcs02 VMExit
+ * MSR-store area.
+ */
+ pr_warn_ratelimited(
+ "Not enough msr entries in msr_autostore. Can't add msr %x\n",
+ msr_index);
+ return;
+ }
+ last = autostore->nr++;
+ autostore->val[last].index = msr_index;
+ } else if (!in_vmcs12_store_list && in_autostore_list) {
+ last = --autostore->nr;
+ autostore->val[msr_autostore_slot] = autostore->val[last];
+ }
+}
+
static bool nested_cr3_valid(struct kvm_vcpu *vcpu, unsigned long val)
{
unsigned long invalid_mask;
@@ -982,37 +1073,91 @@
}
/*
- * Load guest's/host's cr3 at nested entry/exit. nested_ept is true if we are
- * emulating VM entry into a guest with EPT enabled.
- * Returns 0 on success, 1 on failure. Invalid state exit qualification code
- * is assigned to entry_failure_code on failure.
+ * Returns true if the MMU needs to be sync'd on nested VM-Enter/VM-Exit.
+ * tl;dr: the MMU needs a sync if L0 is using shadow paging and L1 didn't
+ * enable VPID for L2 (implying it expects a TLB flush on VMX transitions).
+ * Here's why.
+ *
+ * If EPT is enabled by L0 a sync is never needed:
+ * - if it is disabled by L1, then L0 is not shadowing L1 or L2 PTEs, there
+ * cannot be unsync'd SPTEs for either L1 or L2.
+ *
+ * - if it is also enabled by L1, then L0 doesn't need to sync on VM-Enter
+ * VM-Enter as VM-Enter isn't required to invalidate guest-physical mappings
+ * (irrespective of VPID), i.e. L1 can't rely on the (virtual) CPU to flush
+ * stale guest-physical mappings for L2 from the TLB. And as above, L0 isn't
+ * shadowing L1 PTEs so there are no unsync'd SPTEs to sync on VM-Exit.
+ *
+ * If EPT is disabled by L0:
+ * - if VPID is enabled by L1 (for L2), the situation is similar to when L1
+ * enables EPT: L0 doesn't need to sync as VM-Enter and VM-Exit aren't
+ * required to invalidate linear mappings (EPT is disabled so there are
+ * no combined or guest-physical mappings), i.e. L1 can't rely on the
+ * (virtual) CPU to flush stale linear mappings for either L2 or itself (L1).
+ *
+ * - however if VPID is disabled by L1, then a sync is needed as L1 expects all
+ * linear mappings (EPT is disabled so there are no combined or guest-physical
+ * mappings) to be invalidated on both VM-Enter and VM-Exit.
+ *
+ * Note, this logic is subtly different than nested_has_guest_tlb_tag(), which
+ * additionally checks that L2 has been assigned a VPID (when EPT is disabled).
+ * Whether or not L2 has been assigned a VPID by L0 is irrelevant with respect
+ * to L1's expectations, e.g. L0 needs to invalidate hardware TLB entries if L2
+ * doesn't have a unique VPID to prevent reusing L1's entries (assuming L1 has
+ * been assigned a VPID), but L0 doesn't need to do a MMU sync because L1
+ * doesn't expect stale (virtual) TLB entries to be flushed, i.e. L1 doesn't
+ * know that L0 will flush the TLB and so L1 will do INVVPID as needed to flush
+ * stale TLB entries, at which point L0 will sync L2's MMU.
+ */
+static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu)
+{
+ return !enable_ept && !nested_cpu_has_vpid(get_vmcs12(vcpu));
+}
+
+/*
+ * Load guest's/host's cr3 at nested entry/exit. @nested_ept is true if we are
+ * emulating VM-Entry into a guest with EPT enabled. On failure, the expected
+ * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to
+ * @entry_failure_code.
*/
static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
- u32 *entry_failure_code)
+ enum vm_entry_failure_code *entry_failure_code)
{
- if (cr3 != kvm_read_cr3(vcpu) || (!nested_ept && pdptrs_changed(vcpu))) {
- if (CC(!nested_cr3_valid(vcpu, cr3))) {
- *entry_failure_code = ENTRY_FAIL_DEFAULT;
- return -EINVAL;
- }
+ if (CC(!nested_cr3_valid(vcpu, cr3))) {
+ *entry_failure_code = ENTRY_FAIL_DEFAULT;
+ return -EINVAL;
+ }
- /*
- * If PAE paging and EPT are both on, CR3 is not used by the CPU and
- * must not be dereferenced.
- */
- if (is_pae_paging(vcpu) && !nested_ept) {
- if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
- *entry_failure_code = ENTRY_FAIL_PDPTE;
- return -EINVAL;
- }
+ /*
+ * If PAE paging and EPT are both on, CR3 is not used by the CPU and
+ * must not be dereferenced.
+ */
+ if (!nested_ept && is_pae_paging(vcpu) &&
+ (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) {
+ if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
+ *entry_failure_code = ENTRY_FAIL_PDPTE;
+ return -EINVAL;
}
}
- if (!nested_ept)
- kvm_mmu_new_cr3(vcpu, cr3, false);
+ /*
+ * Unconditionally skip the TLB flush on fast CR3 switch, all TLB
+ * flushes are handled by nested_vmx_transition_tlb_flush().
+ */
+ if (!nested_ept) {
+ kvm_mmu_new_pgd(vcpu, cr3, true, true);
+
+ /*
+ * A TLB flush on VM-Enter/VM-Exit flushes all linear mappings
+ * across all PCIDs, i.e. all PGDs need to be synchronized.
+ * See nested_vmx_transition_mmu_sync() for more details.
+ */
+ if (nested_vmx_transition_mmu_sync(vcpu))
+ kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+ }
vcpu->arch.cr3 = cr3;
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
kvm_init_mmu(vcpu, false);
@@ -1024,7 +1169,9 @@
* populated by L2 differently than TLB entries populated
* by L1.
*
- * If L1 uses EPT, then TLB entries are tagged with different EPTP.
+ * If L0 uses EPT, L1 and L2 run with different EPTP because
+ * guest_mode is part of kvm_mmu_page_role. Thus, TLB entries
+ * are tagged with different EPTP.
*
* If L1 uses VPID and we allocated a vpid02, TLB entries are tagged
* with different VPID (L1 entries are tagged with vmx->vpid
@@ -1034,15 +1181,52 @@
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
- return nested_cpu_has_ept(vmcs12) ||
+ return enable_ept ||
(nested_cpu_has_vpid(vmcs12) && to_vmx(vcpu)->nested.vpid02);
}
-static u16 nested_get_vpid02(struct kvm_vcpu *vcpu)
+static void nested_vmx_transition_tlb_flush(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12,
+ bool is_vmenter)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- return vmx->nested.vpid02 ? vmx->nested.vpid02 : vmx->vpid;
+ /*
+ * If VPID is disabled, linear and combined mappings are flushed on
+ * VM-Enter/VM-Exit, and guest-physical mappings are valid only for
+ * their associated EPTP.
+ */
+ if (!enable_vpid)
+ return;
+
+ /*
+ * If vmcs12 doesn't use VPID, L1 expects linear and combined mappings
+ * for *all* contexts to be flushed on VM-Enter/VM-Exit.
+ *
+ * If VPID is enabled and used by vmc12, but L2 does not have a unique
+ * TLB tag (ASID), i.e. EPT is disabled and KVM was unable to allocate
+ * a VPID for L2, flush the current context as the effective ASID is
+ * common to both L1 and L2.
+ *
+ * Defer the flush so that it runs after vmcs02.EPTP has been set by
+ * KVM_REQ_LOAD_MMU_PGD (if nested EPT is enabled) and to avoid
+ * redundant flushes further down the nested pipeline.
+ *
+ * If a TLB flush isn't required due to any of the above, and vpid12 is
+ * changing then the new "virtual" VPID (vpid12) will reuse the same
+ * "real" VPID (vpid02), and so needs to be sync'd. There is no direct
+ * mapping between vpid02 and vpid12, vpid02 is per-vCPU and reused for
+ * all nested vCPUs.
+ */
+ if (!nested_cpu_has_vpid(vmcs12)) {
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
+ } else if (!nested_has_guest_tlb_tag(vcpu)) {
+ kvm_make_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu);
+ } else if (is_vmenter &&
+ vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
+ vmx->nested.last_vpid = vmcs12->virtual_processor_id;
+ vpid_sync_context(nested_get_vpid02(vcpu));
+ }
}
static bool is_bitwise_subset(u64 superset, u64 subset, u64 mask)
@@ -1606,10 +1790,6 @@
* vmcs12->vm_exit_msr_store_addr = evmcs->vm_exit_msr_store_addr;
* vmcs12->vm_exit_msr_load_addr = evmcs->vm_exit_msr_load_addr;
* vmcs12->vm_entry_msr_load_addr = evmcs->vm_entry_msr_load_addr;
- * vmcs12->cr3_target_value0 = evmcs->cr3_target_value0;
- * vmcs12->cr3_target_value1 = evmcs->cr3_target_value1;
- * vmcs12->cr3_target_value2 = evmcs->cr3_target_value2;
- * vmcs12->cr3_target_value3 = evmcs->cr3_target_value3;
* vmcs12->page_fault_error_code_mask =
* evmcs->page_fault_error_code_mask;
* vmcs12->page_fault_error_code_match =
@@ -1683,10 +1863,6 @@
* evmcs->vm_exit_msr_store_addr = vmcs12->vm_exit_msr_store_addr;
* evmcs->vm_exit_msr_load_addr = vmcs12->vm_exit_msr_load_addr;
* evmcs->vm_entry_msr_load_addr = vmcs12->vm_entry_msr_load_addr;
- * evmcs->cr3_target_value0 = vmcs12->cr3_target_value0;
- * evmcs->cr3_target_value1 = vmcs12->cr3_target_value1;
- * evmcs->cr3_target_value2 = vmcs12->cr3_target_value2;
- * evmcs->cr3_target_value3 = vmcs12->cr3_target_value3;
* evmcs->tpr_threshold = vmcs12->tpr_threshold;
* evmcs->virtual_processor_id = vmcs12->virtual_processor_id;
* evmcs->exception_bitmap = vmcs12->exception_bitmap;
@@ -1815,18 +1991,18 @@
* This is an equivalent of the nested hypervisor executing the vmptrld
* instruction.
*/
-static int nested_vmx_handle_enlightened_vmptrld(struct kvm_vcpu *vcpu,
- bool from_launch)
+static enum nested_evmptrld_status nested_vmx_handle_enlightened_vmptrld(
+ struct kvm_vcpu *vcpu, bool from_launch)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool evmcs_gpa_changed = false;
u64 evmcs_gpa;
if (likely(!vmx->nested.enlightened_vmcs_enabled))
- return 1;
+ return EVMPTRLD_DISABLED;
if (!nested_enlightened_vmentry(vcpu, &evmcs_gpa))
- return 1;
+ return EVMPTRLD_DISABLED;
if (unlikely(!vmx->nested.hv_evmcs ||
evmcs_gpa != vmx->nested.hv_evmcs_vmptr)) {
@@ -1837,7 +2013,7 @@
if (kvm_vcpu_map(vcpu, gpa_to_gfn(evmcs_gpa),
&vmx->nested.hv_evmcs_map))
- return 0;
+ return EVMPTRLD_ERROR;
vmx->nested.hv_evmcs = vmx->nested.hv_evmcs_map.hva;
@@ -1866,7 +2042,7 @@
if ((vmx->nested.hv_evmcs->revision_id != KVM_EVMCS_VERSION) &&
(vmx->nested.hv_evmcs->revision_id != VMCS12_REVISION)) {
nested_release_evmcs(vcpu);
- return 0;
+ return EVMPTRLD_VMFAIL;
}
vmx->nested.dirty_vmcs12 = true;
@@ -1888,28 +2064,20 @@
}
/*
- * Clean fields data can't de used on VMLAUNCH and when we switch
+ * Clean fields data can't be used on VMLAUNCH and when we switch
* between different L2 guests as KVM keeps a single VMCS12 per L1.
*/
if (from_launch || evmcs_gpa_changed)
vmx->nested.hv_evmcs->hv_clean_fields &=
~HV_VMX_ENLIGHTENED_CLEAN_FIELD_ALL;
- return 1;
+ return EVMPTRLD_SUCCEEDED;
}
void nested_sync_vmcs12_to_shadow(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- /*
- * hv_evmcs may end up being not mapped after migration (when
- * L2 was running), map it here to make sure vmcs12 changes are
- * properly reflected.
- */
- if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs)
- nested_vmx_handle_enlightened_vmptrld(vcpu, false);
-
if (vmx->nested.hv_evmcs) {
copy_vmcs12_to_enlightened(vmx);
/* All fields are clean */
@@ -1934,9 +2102,25 @@
return HRTIMER_NORESTART;
}
-static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu)
+static u64 vmx_calc_preemption_timer_value(struct kvm_vcpu *vcpu)
{
- u64 preemption_timeout = get_vmcs12(vcpu)->vmx_preemption_timer_value;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ u64 l1_scaled_tsc = kvm_read_l1_tsc(vcpu, rdtsc()) >>
+ VMX_MISC_EMULATED_PREEMPTION_TIMER_RATE;
+
+ if (!vmx->nested.has_preemption_timer_deadline) {
+ vmx->nested.preemption_timer_deadline =
+ vmcs12->vmx_preemption_timer_value + l1_scaled_tsc;
+ vmx->nested.has_preemption_timer_deadline = true;
+ }
+ return vmx->nested.preemption_timer_deadline - l1_scaled_tsc;
+}
+
+static void vmx_start_preemption_timer(struct kvm_vcpu *vcpu,
+ u64 preemption_timeout)
+{
struct vcpu_vmx *vmx = to_vmx(vcpu);
/*
@@ -1955,7 +2139,8 @@
preemption_timeout *= 1000000;
do_div(preemption_timeout, vcpu->arch.virtual_tsc_khz);
hrtimer_start(&vmx->nested.preemption_timer,
- ns_to_ktime(preemption_timeout), HRTIMER_MODE_REL);
+ ktime_add_ns(ktime_get(), preemption_timeout),
+ HRTIMER_MODE_ABS_PINNED);
}
static u64 nested_vmx_calc_efer(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
@@ -1987,7 +2172,8 @@
* consistency checks.
*/
if (enable_ept && nested_early_check)
- vmcs_write64(EPT_POINTER, construct_eptp(&vmx->vcpu, 0));
+ vmcs_write64(EPT_POINTER,
+ construct_eptp(&vmx->vcpu, 0, PT64_ROOT_4LEVEL));
/* All VMFUNCs are currently emulated through L0 vmexits. */
if (cpu_has_vmx_vmfunc())
@@ -2019,7 +2205,7 @@
* addresses are constant (for vmcs02), the counts can change based
* on L2's behavior, e.g. switching to/from long mode.
*/
- vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmcs_write64(VM_EXIT_MSR_STORE_ADDR, __pa(vmx->msr_autostore.guest.val));
vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host.val));
vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest.val));
@@ -2068,11 +2254,12 @@
* EXEC CONTROLS
*/
exec_control = vmx_exec_control(vmx); /* L0's desires */
- exec_control &= ~CPU_BASED_VIRTUAL_INTR_PENDING;
- exec_control &= ~CPU_BASED_VIRTUAL_NMI_PENDING;
+ exec_control &= ~CPU_BASED_INTR_WINDOW_EXITING;
+ exec_control &= ~CPU_BASED_NMI_WINDOW_EXITING;
exec_control &= ~CPU_BASED_TPR_SHADOW;
exec_control |= vmcs12->cpu_based_vm_exec_control;
+ vmx->nested.l1_tpr_threshold = -1;
if (exec_control & CPU_BASED_TPR_SHADOW)
vmcs_write32(TPR_THRESHOLD, vmcs12->tpr_threshold);
#ifdef CONFIG_X86_64
@@ -2108,7 +2295,7 @@
/* Take the following fields only from vmcs12 */
exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
SECONDARY_EXEC_ENABLE_INVPCID |
- SECONDARY_EXEC_RDTSCP |
+ SECONDARY_EXEC_ENABLE_RDTSCP |
SECONDARY_EXEC_XSAVES |
SECONDARY_EXEC_ENABLE_USR_WAIT_PAUSE |
SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY |
@@ -2136,6 +2323,9 @@
vmcs_write16(GUEST_INTR_STATUS,
vmcs12->guest_intr_status);
+ if (!nested_cpu_has2(vmcs12, SECONDARY_EXEC_UNRESTRICTED_GUEST))
+ exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
+
secondary_exec_controls_set(vmx, exec_control);
}
@@ -2263,22 +2453,28 @@
/*
* Whether page-faults are trapped is determined by a combination of
- * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
- * If enable_ept, L0 doesn't care about page faults and we should
- * set all of these to L1's desires. However, if !enable_ept, L0 does
- * care about (at least some) page faults, and because it is not easy
- * (if at all possible?) to merge L0 and L1's desires, we simply ask
- * to exit on each and every L2 page fault. This is done by setting
- * MASK=MATCH=0 and (see below) EB.PF=1.
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF. If L0
+ * doesn't care about page faults then we should set all of these to
+ * L1's desires. However, if L0 does care about (some) page faults, it
+ * is not easy (if at all possible?) to merge L0 and L1's desires, we
+ * simply ask to exit on each and every L2 page fault. This is done by
+ * setting MASK=MATCH=0 and (see below) EB.PF=1.
* Note that below we don't need special code to set EB.PF beyond the
* "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
* vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
* !enable_ept, EB.PF is 1, so the "or" will always be 1.
*/
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
- enable_ept ? vmcs12->page_fault_error_code_mask : 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
- enable_ept ? vmcs12->page_fault_error_code_match : 0);
+ if (vmx_need_pf_intercept(&vmx->vcpu)) {
+ /*
+ * TODO: if both L0 and L1 need the same MASK and MATCH,
+ * go ahead and use it?
+ */
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, 0);
+ } else {
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK, vmcs12->page_fault_error_code_mask);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH, vmcs12->page_fault_error_code_match);
+ }
if (cpu_has_vmx_apicv()) {
vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
@@ -2287,6 +2483,13 @@
vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
}
+ /*
+ * Make sure the msr_autostore list is up to date before we set the
+ * count in the vmcs02.
+ */
+ prepare_vmx_msr_autostore_list(&vmx->vcpu, MSR_IA32_TSC);
+
+ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, vmx->msr_autostore.guest.nr);
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
@@ -2305,7 +2508,7 @@
* is assigned to entry_failure_code on failure.
*/
static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- u32 *entry_failure_code)
+ enum vm_entry_failure_code *entry_failure_code)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct hv_enlightened_vmcs *hv_evmcs = vmx->nested.hv_evmcs;
@@ -2354,38 +2557,10 @@
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
- if (enable_vpid) {
- /*
- * There is no direct mapping between vpid02 and vpid12, the
- * vpid02 is per-vCPU for L0 and reused while the value of
- * vpid12 is changed w/ one invvpid during nested vmentry.
- * The vpid12 is allocated by L1 for L2, so it will not
- * influence global bitmap(for vpid01 and vpid02 allocation)
- * even if spawn a lot of nested vCPUs.
- */
- if (nested_cpu_has_vpid(vmcs12) && nested_has_guest_tlb_tag(vcpu)) {
- if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
- vmx->nested.last_vpid = vmcs12->virtual_processor_id;
- __vmx_flush_tlb(vcpu, nested_get_vpid02(vcpu), false);
- }
- } else {
- /*
- * If L1 use EPT, then L0 needs to execute INVEPT on
- * EPTP02 instead of EPTP01. Therefore, delay TLB
- * flush until vmcs02->eptp is fully updated by
- * KVM_REQ_LOAD_CR3. Note that this assumes
- * KVM_REQ_TLB_FLUSH is evaluated after
- * KVM_REQ_LOAD_CR3 in vcpu_enter_guest().
- */
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- }
- }
+ nested_vmx_transition_tlb_flush(vcpu, vmcs12, true);
if (nested_cpu_has_ept(vmcs12))
nested_ept_init_mmu_context(vcpu);
- else if (nested_cpu_has2(vmcs12,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
- vmx_flush_tlb(vcpu, true);
/*
* This sets GUEST_CR0 to vmcs12->guest_cr0, possibly modifying those
@@ -2410,7 +2585,7 @@
* which means L1 attempted VMEntry to L2 with invalid state.
* Fail the VMEntry.
*/
- if (vmx->emulation_required) {
+ if (CC(!vmx_guest_state_valid(vcpu))) {
*entry_failure_code = ENTRY_FAIL_DEFAULT;
return -EINVAL;
}
@@ -2423,7 +2598,7 @@
/*
* Immediately write vmcs02.GUEST_CR3. It will be propagated to vmcs12
* on nested VM-Exit, which can occur without actually running L2 and
- * thus without hitting vmx_set_cr3(), e.g. if L1 is entering L2 with
+ * thus without hitting vmx_load_mmu_pgd(), e.g. if L1 is entering L2 with
* vmcs12.GUEST_ACTIVITYSTATE=HLT, in which case KVM will intercept the
* transition to HLT instead of running L2.
*/
@@ -2442,6 +2617,13 @@
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;
+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+ WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+ vmcs12->guest_ia32_perf_global_ctrl))) {
+ *entry_failure_code = ENTRY_FAIL_DEFAULT;
+ return -EINVAL;
+ }
+
kvm_rsp_write(vcpu, vmcs12->guest_rsp);
kvm_rip_write(vcpu, vmcs12->guest_rip);
return 0;
@@ -2454,19 +2636,19 @@
return -EINVAL;
if (CC(!nested_cpu_has_virtual_nmis(vmcs12) &&
- nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING)))
+ nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING)))
return -EINVAL;
return 0;
}
-static bool valid_ept_address(struct kvm_vcpu *vcpu, u64 address)
+static bool nested_vmx_check_eptp(struct kvm_vcpu *vcpu, u64 new_eptp)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
int maxphyaddr = cpuid_maxphyaddr(vcpu);
/* Check for memory type validity */
- switch (address & VMX_EPTP_MT_MASK) {
+ switch (new_eptp & VMX_EPTP_MT_MASK) {
case VMX_EPTP_MT_UC:
if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPTP_UC_BIT)))
return false;
@@ -2479,16 +2661,26 @@
return false;
}
- /* only 4 levels page-walk length are valid */
- if (CC((address & VMX_EPTP_PWL_MASK) != VMX_EPTP_PWL_4))
+ /* Page-walk levels validity. */
+ switch (new_eptp & VMX_EPTP_PWL_MASK) {
+ case VMX_EPTP_PWL_5:
+ if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_5_BIT)))
+ return false;
+ break;
+ case VMX_EPTP_PWL_4:
+ if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_PAGE_WALK_4_BIT)))
+ return false;
+ break;
+ default:
return false;
+ }
/* Reserved bits should not be set */
- if (CC(address >> maxphyaddr || ((address >> 7) & 0x1f)))
+ if (CC(new_eptp >> maxphyaddr || ((new_eptp >> 7) & 0x1f)))
return false;
/* AD, if set, should be supported */
- if (address & VMX_EPTP_AD_ENABLE_BIT) {
+ if (new_eptp & VMX_EPTP_AD_ENABLE_BIT) {
if (CC(!(vmx->nested.msrs.ept_caps & VMX_EPT_AD_BIT)))
return false;
}
@@ -2537,7 +2729,7 @@
return -EINVAL;
if (nested_cpu_has_ept(vmcs12) &&
- CC(!valid_ept_address(vcpu, vmcs12->ept_pointer)))
+ CC(!nested_vmx_check_eptp(vcpu, vmcs12->ept_pointer)))
return -EINVAL;
if (nested_cpu_has_vmfunc(vmcs12)) {
@@ -2655,6 +2847,20 @@
nested_check_vm_entry_controls(vcpu, vmcs12))
return -EINVAL;
+ if (to_vmx(vcpu)->nested.enlightened_vmcs_enabled)
+ return nested_evmcs_check_controls(vmcs12);
+
+ return 0;
+}
+
+static int nested_vmx_check_address_space_size(struct kvm_vcpu *vcpu,
+ struct vmcs12 *vmcs12)
+{
+#ifdef CONFIG_X86_64
+ if (CC(!!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) !=
+ !!(vcpu->arch.efer & EFER_LMA)))
+ return -EINVAL;
+#endif
return 0;
}
@@ -2676,19 +2882,22 @@
CC(!kvm_pat_valid(vmcs12->host_ia32_pat)))
return -EINVAL;
+ if ((vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+ CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+ vmcs12->host_ia32_perf_global_ctrl)))
+ return -EINVAL;
+
#ifdef CONFIG_X86_64
- ia32e = !!(vcpu->arch.efer & EFER_LMA);
+ ia32e = !!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE);
#else
ia32e = false;
#endif
if (ia32e) {
- if (CC(!(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE)) ||
- CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
+ if (CC(!(vmcs12->host_cr4 & X86_CR4_PAE)))
return -EINVAL;
} else {
- if (CC(vmcs12->vm_exit_controls & VM_EXIT_HOST_ADDR_SPACE_SIZE) ||
- CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
+ if (CC(vmcs12->vm_entry_controls & VM_ENTRY_IA32E_MODE) ||
CC(vmcs12->host_cr4 & X86_CR4_PCIDE) ||
CC((vmcs12->host_rip) >> 32))
return -EINVAL;
@@ -2706,7 +2915,6 @@
CC(vmcs12->host_ss_selector == 0 && !ia32e))
return -EINVAL;
-#ifdef CONFIG_X86_64
if (CC(is_noncanonical_address(vmcs12->host_fs_base, vcpu)) ||
CC(is_noncanonical_address(vmcs12->host_gs_base, vcpu)) ||
CC(is_noncanonical_address(vmcs12->host_gdtr_base, vcpu)) ||
@@ -2714,7 +2922,6 @@
CC(is_noncanonical_address(vmcs12->host_tr_base, vcpu)) ||
CC(is_noncanonical_address(vmcs12->host_rip, vcpu)))
return -EINVAL;
-#endif
/*
* If the load IA32_EFER VM-exit control is 1, bits reserved in the
@@ -2772,25 +2979,34 @@
static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12,
- u32 *exit_qual)
+ enum vm_entry_failure_code *entry_failure_code)
{
bool ia32e;
- *exit_qual = ENTRY_FAIL_DEFAULT;
+ *entry_failure_code = ENTRY_FAIL_DEFAULT;
if (CC(!nested_guest_cr0_valid(vcpu, vmcs12->guest_cr0)) ||
CC(!nested_guest_cr4_valid(vcpu, vmcs12->guest_cr4)))
return -EINVAL;
+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
+ CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ return -EINVAL;
+
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
CC(!kvm_pat_valid(vmcs12->guest_ia32_pat)))
return -EINVAL;
if (nested_vmx_check_vmcs_link_ptr(vcpu, vmcs12)) {
- *exit_qual = ENTRY_FAIL_VMCS_LINK_PTR;
+ *entry_failure_code = ENTRY_FAIL_VMCS_LINK_PTR;
return -EINVAL;
}
+ if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL) &&
+ CC(!kvm_valid_perf_global_ctrl(vcpu_to_pmu(vcpu),
+ vmcs12->guest_ia32_perf_global_ctrl)))
+ 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:
@@ -2842,7 +3058,7 @@
/*
* Induce a consistency check VMExit by clearing bit 1 in GUEST_RFLAGS,
* which is reserved to '1' by hardware. GUEST_RFLAGS is guaranteed to
- * be written (by preparve_vmcs02()) before the "real" VMEnter, i.e.
+ * be written (by prepare_vmcs02()) before the "real" VMEnter, i.e.
* there is no need to preserve other bits or save/restore the field.
*/
vmcs_writel(GUEST_RFLAGS, 0);
@@ -2908,9 +3124,9 @@
/*
* VMExit clears RFLAGS.IF and DR7, even on a consistency check.
*/
- local_irq_enable();
if (hw_breakpoint_active())
set_debugreg(__this_cpu_read(cpu_dr7), 7);
+ local_irq_enable();
preempt_enable();
/*
@@ -2926,8 +3142,26 @@
return 0;
}
-static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12);
+static bool nested_get_evmcs_page(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+ /*
+ * hv_evmcs may end up being not mapped after migration (when
+ * L2 was running), map it here to make sure vmcs12 changes are
+ * properly reflected.
+ */
+ if (vmx->nested.enlightened_vmcs_enabled && !vmx->nested.hv_evmcs) {
+ enum nested_evmptrld_status evmptrld_status =
+ nested_vmx_handle_enlightened_vmptrld(vcpu, false);
+
+ if (evmptrld_status == EVMPTRLD_VMFAIL ||
+ evmptrld_status == EVMPTRLD_ERROR)
+ return false;
+ }
+
+ return true;
+}
static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
{
@@ -2945,7 +3179,7 @@
* to it so we can release it later.
*/
if (vmx->nested.apic_access_page) { /* shouldn't happen */
- kvm_release_page_dirty(vmx->nested.apic_access_page);
+ kvm_release_page_clean(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
}
page = kvm_vcpu_gpa_to_page(vcpu, vmcs12->apic_access_addr);
@@ -3005,9 +3239,66 @@
exec_controls_setbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
else
exec_controls_clearbit(vmx, CPU_BASED_USE_MSR_BITMAPS);
+
return true;
}
+static bool vmx_get_nested_state_pages(struct kvm_vcpu *vcpu)
+{
+ if (!nested_get_evmcs_page(vcpu)) {
+ pr_debug_ratelimited("%s: enlightened vmptrld failed\n",
+ __func__);
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror =
+ KVM_INTERNAL_ERROR_EMULATION;
+ vcpu->run->internal.ndata = 0;
+
+ return false;
+ }
+
+ if (is_guest_mode(vcpu) && !nested_get_vmcs12_pages(vcpu))
+ return false;
+
+ return true;
+}
+
+static int nested_vmx_write_pml_buffer(struct kvm_vcpu *vcpu, gpa_t gpa)
+{
+ struct vmcs12 *vmcs12;
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ gpa_t dst;
+
+ if (WARN_ON_ONCE(!is_guest_mode(vcpu)))
+ return 0;
+
+ if (WARN_ON_ONCE(vmx->nested.pml_full))
+ return 1;
+
+ /*
+ * Check if PML is enabled for the nested guest. Whether eptp bit 6 is
+ * set is already checked as part of A/D emulation.
+ */
+ vmcs12 = get_vmcs12(vcpu);
+ if (!nested_cpu_has_pml(vmcs12))
+ return 0;
+
+ if (vmcs12->guest_pml_index >= PML_ENTITY_NUM) {
+ vmx->nested.pml_full = true;
+ return 1;
+ }
+
+ gpa &= ~0xFFFull;
+ dst = vmcs12->pml_address + sizeof(u64) * vmcs12->guest_pml_index;
+
+ if (kvm_write_guest_page(vcpu->kvm, gpa_to_gfn(dst), &gpa,
+ offset_in_page(dst), sizeof(gpa)))
+ return 0;
+
+ vmcs12->guest_pml_index--;
+
+ return 0;
+}
+
/*
* Intel's VMX Instruction Reference specifies a common set of prerequisites
* for running VMX instructions (except VMXON, whose prerequisites are
@@ -3046,22 +3337,29 @@
* or KVM_SET_NESTED_STATE). Otherwise it's called from vmlaunch/vmresume.
*
* Returns:
- * NVMX_ENTRY_SUCCESS: Entered VMX non-root mode
- * NVMX_ENTRY_VMFAIL: Consistency check VMFail
- * NVMX_ENTRY_VMEXIT: Consistency check VMExit
- * NVMX_ENTRY_KVM_INTERNAL_ERROR: KVM internal error
+ * NVMX_VMENTRY_SUCCESS: Entered VMX non-root mode
+ * NVMX_VMENTRY_VMFAIL: Consistency check VMFail
+ * NVMX_VMENTRY_VMEXIT: Consistency check VMExit
+ * NVMX_VMENTRY_KVM_INTERNAL_ERROR: KVM internal error
*/
enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
bool from_vmentry)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ enum vm_entry_failure_code entry_failure_code;
bool evaluate_pending_interrupts;
- u32 exit_reason = EXIT_REASON_INVALID_STATE;
- u32 exit_qual;
+ union vmx_exit_reason exit_reason = {
+ .basic = EXIT_REASON_INVALID_STATE,
+ .failed_vmentry = 1,
+ };
+ u32 failed_index;
+
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+ kvm_vcpu_flush_tlb_current(vcpu);
evaluate_pending_interrupts = exec_controls_get(vmx) &
- (CPU_BASED_VIRTUAL_INTR_PENDING | CPU_BASED_VIRTUAL_NMI_PENDING);
+ (CPU_BASED_INTR_WINDOW_EXITING | CPU_BASED_NMI_WINDOW_EXITING);
if (likely(!evaluate_pending_interrupts) && kvm_vcpu_apicv_active(vcpu))
evaluate_pending_interrupts |= vmx_has_apicv_interrupt(vcpu);
@@ -3105,24 +3403,33 @@
return NVMX_VMENTRY_VMFAIL;
}
- if (nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
+ if (nested_vmx_check_guest_state(vcpu, vmcs12,
+ &entry_failure_code)) {
+ exit_reason.basic = EXIT_REASON_INVALID_STATE;
+ vmcs12->exit_qualification = entry_failure_code;
goto vmentry_fail_vmexit;
+ }
}
enter_guest_mode(vcpu);
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
vcpu->arch.tsc_offset += vmcs12->tsc_offset;
- if (prepare_vmcs02(vcpu, vmcs12, &exit_qual))
+ if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) {
+ exit_reason.basic = EXIT_REASON_INVALID_STATE;
+ vmcs12->exit_qualification = entry_failure_code;
goto vmentry_fail_vmexit_guest_mode;
+ }
if (from_vmentry) {
- exit_reason = EXIT_REASON_MSR_LOAD_FAIL;
- exit_qual = nested_vmx_load_msr(vcpu,
- vmcs12->vm_entry_msr_load_addr,
- vmcs12->vm_entry_msr_load_count);
- if (exit_qual)
+ failed_index = nested_vmx_load_msr(vcpu,
+ vmcs12->vm_entry_msr_load_addr,
+ vmcs12->vm_entry_msr_load_count);
+ if (failed_index) {
+ exit_reason.basic = EXIT_REASON_MSR_LOAD_FAIL;
+ vmcs12->exit_qualification = failed_index;
goto vmentry_fail_vmexit_guest_mode;
+ }
} else {
/*
* The MMU is not initialized to point at the right entities yet and
@@ -3131,7 +3438,7 @@
* to nested_get_vmcs12_pages before the next VM-entry. The MSRs
* have already been set at vmentry time and should not be reset.
*/
- kvm_make_request(KVM_REQ_GET_VMCS12_PAGES, vcpu);
+ kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
}
/*
@@ -3157,8 +3464,10 @@
* the timer.
*/
vmx->nested.preemption_timer_expired = false;
- if (nested_cpu_has_preemption_timer(vmcs12))
- vmx_start_preemption_timer(vcpu);
+ if (nested_cpu_has_preemption_timer(vmcs12)) {
+ u64 timer_value = vmx_calc_preemption_timer_value(vcpu);
+ vmx_start_preemption_timer(vcpu, timer_value);
+ }
/*
* Note no nested_vmx_succeed or nested_vmx_fail here. At this point
@@ -3174,7 +3483,7 @@
* 26.7 "VM-entry failures during or after loading guest state".
*/
vmentry_fail_vmexit_guest_mode:
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
leave_guest_mode(vcpu);
@@ -3185,8 +3494,7 @@
return NVMX_VMENTRY_VMEXIT;
load_vmcs12_host_state(vcpu, vmcs12);
- vmcs12->vm_exit_reason = exit_reason | VMX_EXIT_REASONS_FAILED_VMENTRY;
- vmcs12->exit_qualification = exit_qual;
+ vmcs12->vm_exit_reason = exit_reason.full;
if (enable_shadow_vmcs || vmx->nested.hv_evmcs)
vmx->nested.need_vmcs12_to_shadow_sync = true;
return NVMX_VMENTRY_VMEXIT;
@@ -3202,14 +3510,20 @@
enum nvmx_vmentry_status status;
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 interrupt_shadow = vmx_get_interrupt_shadow(vcpu);
+ enum nested_evmptrld_status evmptrld_status;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (!nested_vmx_handle_enlightened_vmptrld(vcpu, launch))
+ evmptrld_status = nested_vmx_handle_enlightened_vmptrld(vcpu, launch);
+ if (evmptrld_status == EVMPTRLD_ERROR) {
+ kvm_queue_exception(vcpu, UD_VECTOR);
return 1;
+ } else if (CC(evmptrld_status == EVMPTRLD_VMFAIL)) {
+ return nested_vmx_failInvalid(vcpu);
+ }
- if (!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull)
+ if (CC(!vmx->nested.hv_evmcs && vmx->nested.current_vmptr == -1ull))
return nested_vmx_failInvalid(vcpu);
vmcs12 = get_vmcs12(vcpu);
@@ -3220,7 +3534,7 @@
* rather than RFLAGS.ZF, and no error number is stored to the
* VM-instruction error field.
*/
- if (vmcs12->hdr.shadow_vmcs)
+ if (CC(vmcs12->hdr.shadow_vmcs))
return nested_vmx_failInvalid(vcpu);
if (vmx->nested.hv_evmcs) {
@@ -3241,30 +3555,41 @@
* for misconfigurations which will anyway be caught by the processor
* when using the merged vmcs02.
*/
- if (interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS)
- return nested_vmx_failValid(vcpu,
- VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
+ if (CC(interrupt_shadow & KVM_X86_SHADOW_INT_MOV_SS))
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_EVENTS_BLOCKED_BY_MOV_SS);
- if (vmcs12->launch_state == launch)
- return nested_vmx_failValid(vcpu,
+ if (CC(vmcs12->launch_state == launch))
+ return nested_vmx_fail(vcpu,
launch ? VMXERR_VMLAUNCH_NONCLEAR_VMCS
: VMXERR_VMRESUME_NONLAUNCHED_VMCS);
if (nested_vmx_check_controls(vcpu, vmcs12))
- return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+
+ if (nested_vmx_check_address_space_size(vcpu, vmcs12))
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
if (nested_vmx_check_host_state(vcpu, vmcs12))
- return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_HOST_STATE_FIELD);
/*
* We're finally done with prerequisite checking, and can start with
* the nested entry.
*/
vmx->nested.nested_run_pending = 1;
+ vmx->nested.has_preemption_timer_deadline = false;
status = nested_vmx_enter_non_root_mode(vcpu, true);
if (unlikely(status != NVMX_VMENTRY_SUCCESS))
goto vmentry_failed;
+ /* Emulate processing of posted interrupts on VM-Enter. */
+ if (nested_cpu_has_posted_intr(vmcs12) &&
+ kvm_apic_has_interrupt(vcpu) == vmx->nested.posted_intr_nv) {
+ vmx->nested.pi_pending = true;
+ kvm_make_request(KVM_REQ_EVENT, vcpu);
+ kvm_apic_clear_irr(vcpu, vmx->nested.posted_intr_nv);
+ }
+
/* Hide L1D cache contents from the nested guest. */
vmx->vcpu.arch.l1tf_flush_l1d = true;
@@ -3287,8 +3612,8 @@
*/
if ((vmcs12->guest_activity_state == GUEST_ACTIVITY_HLT) &&
!(vmcs12->vm_entry_intr_info_field & INTR_INFO_VALID_MASK) &&
- !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_NMI_PENDING) &&
- !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_VIRTUAL_INTR_PENDING) &&
+ !(vmcs12->cpu_based_vm_exec_control & CPU_BASED_NMI_WINDOW_EXITING) &&
+ !((vmcs12->cpu_based_vm_exec_control & CPU_BASED_INTR_WINDOW_EXITING) &&
(vmcs12->guest_rflags & X86_EFLAGS_IF))) {
vmx->nested.nested_run_pending = 0;
return kvm_vcpu_halt(vcpu);
@@ -3302,12 +3627,12 @@
if (status == NVMX_VMENTRY_VMEXIT)
return 1;
WARN_ON_ONCE(status != NVMX_VMENTRY_VMFAIL);
- return nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ return nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
}
/*
* On a nested exit from L2 to L1, vmcs12.guest_cr0 might not be up-to-date
- * because L2 may have changed some cr0 bits directly (CRO_GUEST_HOST_MASK).
+ * because L2 may have changed some cr0 bits directly (CR0_GUEST_HOST_MASK).
* This function returns the new value we should put in vmcs12.guest_cr0.
* It's not enough to just return the vmcs02 GUEST_CR0. Rather,
* 1. Bits that neither L0 nor L1 trapped, were set directly by L2 and are now
@@ -3385,7 +3710,7 @@
}
-static void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
+void nested_mark_vmcs12_pages_dirty(struct kvm_vcpu *vcpu)
{
struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
gfn_t gfn;
@@ -3463,41 +3788,113 @@
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI, intr_info, exit_qual);
}
+/*
+ * Returns true if a debug trap is pending delivery.
+ *
+ * In KVM, debug traps bear an exception payload. As such, the class of a #DB
+ * exception may be inferred from the presence of an exception payload.
+ */
+static inline bool vmx_pending_dbg_trap(struct kvm_vcpu *vcpu)
+{
+ return vcpu->arch.exception.pending &&
+ vcpu->arch.exception.nr == DB_VECTOR &&
+ vcpu->arch.exception.payload;
+}
+
+/*
+ * Certain VM-exits set the 'pending debug exceptions' field to indicate a
+ * recognized #DB (data or single-step) that has yet to be delivered. Since KVM
+ * represents these debug traps with a payload that is said to be compatible
+ * with the 'pending debug exceptions' field, write the payload to the VMCS
+ * field if a VM-exit is delivered before the debug trap.
+ */
+static void nested_vmx_update_pending_dbg(struct kvm_vcpu *vcpu)
+{
+ if (vmx_pending_dbg_trap(vcpu))
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vcpu->arch.exception.payload);
+}
+
+static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
+{
+ return nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
+ to_vmx(vcpu)->nested.preemption_timer_expired;
+}
+
static int vmx_check_nested_events(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long exit_qual;
bool block_nested_events =
vmx->nested.nested_run_pending || kvm_event_needs_reinjection(vcpu);
+ bool mtf_pending = vmx->nested.mtf_pending;
struct kvm_lapic *apic = vcpu->arch.apic;
+ /*
+ * Clear the MTF state. If a higher priority VM-exit is delivered first,
+ * this state is discarded.
+ */
+ if (!block_nested_events)
+ vmx->nested.mtf_pending = false;
+
if (lapic_in_kernel(vcpu) &&
test_bit(KVM_APIC_INIT, &apic->pending_events)) {
if (block_nested_events)
return -EBUSY;
+ nested_vmx_update_pending_dbg(vcpu);
+ clear_bit(KVM_APIC_INIT, &apic->pending_events);
nested_vmx_vmexit(vcpu, EXIT_REASON_INIT_SIGNAL, 0, 0);
return 0;
}
- if (vcpu->arch.exception.pending &&
- nested_vmx_check_exception(vcpu, &exit_qual)) {
+ /*
+ * Process any exceptions that are not debug traps before MTF.
+ */
+ if (vcpu->arch.exception.pending && !vmx_pending_dbg_trap(vcpu)) {
if (block_nested_events)
return -EBUSY;
+ if (!nested_vmx_check_exception(vcpu, &exit_qual))
+ goto no_vmexit;
nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
return 0;
}
- if (nested_cpu_has_preemption_timer(get_vmcs12(vcpu)) &&
- vmx->nested.preemption_timer_expired) {
+ if (mtf_pending) {
+ if (block_nested_events)
+ return -EBUSY;
+ nested_vmx_update_pending_dbg(vcpu);
+ nested_vmx_vmexit(vcpu, EXIT_REASON_MONITOR_TRAP_FLAG, 0, 0);
+ return 0;
+ }
+
+ if (vcpu->arch.exception.pending) {
+ if (block_nested_events)
+ return -EBUSY;
+ if (!nested_vmx_check_exception(vcpu, &exit_qual))
+ goto no_vmexit;
+ nested_vmx_inject_exception_vmexit(vcpu, exit_qual);
+ return 0;
+ }
+
+ if (nested_vmx_preemption_timer_pending(vcpu)) {
if (block_nested_events)
return -EBUSY;
nested_vmx_vmexit(vcpu, EXIT_REASON_PREEMPTION_TIMER, 0, 0);
return 0;
}
- if (vcpu->arch.nmi_pending && nested_exit_on_nmi(vcpu)) {
+ if (vcpu->arch.smi_pending && !is_smm(vcpu)) {
if (block_nested_events)
return -EBUSY;
+ goto no_vmexit;
+ }
+
+ if (vcpu->arch.nmi_pending && !vmx_nmi_blocked(vcpu)) {
+ if (block_nested_events)
+ return -EBUSY;
+ if (!nested_exit_on_nmi(vcpu))
+ goto no_vmexit;
+
nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
NMI_VECTOR | INTR_TYPE_NMI_INTR |
INTR_INFO_VALID_MASK, 0);
@@ -3510,13 +3907,16 @@
return 0;
}
- if (kvm_cpu_has_interrupt(vcpu) && nested_exit_on_intr(vcpu)) {
+ if (kvm_cpu_has_interrupt(vcpu) && !vmx_interrupt_blocked(vcpu)) {
if (block_nested_events)
return -EBUSY;
+ if (!nested_exit_on_intr(vcpu))
+ goto no_vmexit;
nested_vmx_vmexit(vcpu, EXIT_REASON_EXTERNAL_INTERRUPT, 0, 0);
return 0;
}
+no_vmexit:
vmx_complete_nested_posted_interrupt(vcpu);
return 0;
}
@@ -3643,12 +4043,12 @@
cpu = get_cpu();
vmx->loaded_vmcs = &vmx->nested.vmcs02;
- vmx_vcpu_load(&vmx->vcpu, cpu);
+ vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
vmx->loaded_vmcs = &vmx->vmcs01;
- vmx_vcpu_load(&vmx->vcpu, cpu);
+ vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
put_cpu();
}
@@ -3677,10 +4077,6 @@
vmcs12->guest_cs_ar_bytes = vmcs_read32(GUEST_CS_AR_BYTES);
vmcs12->guest_ss_ar_bytes = vmcs_read32(GUEST_SS_AR_BYTES);
- vmcs12->guest_sysenter_cs = vmcs_read32(GUEST_SYSENTER_CS);
- vmcs12->guest_sysenter_esp = vmcs_readl(GUEST_SYSENTER_ESP);
- vmcs12->guest_sysenter_eip = vmcs_readl(GUEST_SYSENTER_EIP);
-
vmcs12->guest_interruptibility_info =
vmcs_read32(GUEST_INTERRUPTIBILITY_INFO);
@@ -3690,9 +4086,10 @@
vmcs12->guest_activity_state = GUEST_ACTIVITY_ACTIVE;
if (nested_cpu_has_preemption_timer(vmcs12) &&
- vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER)
- vmcs12->vmx_preemption_timer_value =
- vmx_get_preemption_timer_value(vcpu);
+ vmcs12->vm_exit_controls & VM_EXIT_SAVE_VMX_PREEMPTION_TIMER &&
+ !vmx->nested.nested_run_pending)
+ vmcs12->vmx_preemption_timer_value =
+ vmx_get_preemption_timer_value(vcpu);
/*
* In some cases (usually, nested EPT), L2 is allowed to change its
@@ -3740,11 +4137,11 @@
* which already writes to vmcs12 directly.
*/
static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
- u32 exit_reason, u32 exit_intr_info,
+ u32 vm_exit_reason, u32 exit_intr_info,
unsigned long exit_qualification)
{
/* update exit information fields: */
- vmcs12->vm_exit_reason = exit_reason;
+ vmcs12->vm_exit_reason = vm_exit_reason;
vmcs12->exit_qualification = exit_qualification;
vmcs12->vm_exit_intr_info = exit_intr_info;
@@ -3799,8 +4196,8 @@
static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
+ enum vm_entry_failure_code ignored;
struct kvm_segment seg;
- u32 entry_failure_code;
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_EFER)
vcpu->arch.efer = vmcs12->host_ia32_efer;
@@ -3822,7 +4219,7 @@
* CR0_GUEST_HOST_MASK is already set in the original vmcs01
* (KVM doesn't change it);
*/
- vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
vmx_set_cr0(vcpu, vmcs12->host_cr0);
/* Same as above - no reason to call set_cr4_guest_host_mask(). */
@@ -3835,30 +4232,13 @@
* Only PDPTE load can fail as the value of cr3 was checked on entry and
* couldn't have changed.
*/
- if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &entry_failure_code))
+ if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored))
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = kvm_inject_page_fault;
- /*
- * If vmcs01 doesn't use VPID, CPU flushes TLB on every
- * VMEntry/VMExit. Thus, no need to flush TLB.
- *
- * If vmcs12 doesn't use VPID, L1 expects TLB to be
- * flushed on every VMEntry/VMExit.
- *
- * Otherwise, we can preserve TLB entries as long as we are
- * able to tag L1 TLB entries differently than L2 TLB entries.
- *
- * If vmcs12 uses EPT, we need to execute this flush on EPTP01
- * and therefore we request the TLB flush to happen only after VMCS EPTP
- * has been set by KVM_REQ_LOAD_CR3.
- */
- if (enable_vpid &&
- (!nested_cpu_has_vpid(vmcs12) || !nested_has_guest_tlb_tag(vcpu))) {
- kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
- }
+ nested_vmx_transition_tlb_flush(vcpu, vmcs12, false);
vmcs_write32(GUEST_SYSENTER_CS, vmcs12->host_ia32_sysenter_cs);
vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->host_ia32_sysenter_esp);
@@ -3877,8 +4257,8 @@
vcpu->arch.pat = vmcs12->host_ia32_pat;
}
if (vmcs12->vm_exit_controls & VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL)
- vmcs_write64(GUEST_IA32_PERF_GLOBAL_CTRL,
- vmcs12->host_ia32_perf_global_ctrl);
+ WARN_ON_ONCE(kvm_set_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL,
+ vmcs12->host_ia32_perf_global_ctrl));
/* Set L1 segment info according to Intel SDM
27.5.2 Loading Host Segment and Descriptor-Table Registers */
@@ -3939,7 +4319,7 @@
static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
{
- struct shared_msr_entry *efer_msr;
+ struct vmx_uret_msr *efer_msr;
unsigned int i;
if (vm_entry_controls_get(vmx) & VM_ENTRY_LOAD_IA32_EFER)
@@ -3953,7 +4333,7 @@
return vmx->msr_autoload.guest.val[i].value;
}
- efer_msr = find_msr_entry(vmx, MSR_EFER);
+ efer_msr = vmx_find_uret_msr(vmx, MSR_EFER);
if (efer_msr)
return efer_msr->data;
@@ -3989,7 +4369,7 @@
*/
vmx_set_efer(vcpu, nested_vmx_get_vmcs01_guest_efer(vmx));
- vcpu->arch.cr0_guest_owned_bits = X86_CR0_TS;
+ vcpu->arch.cr0_guest_owned_bits = KVM_POSSIBLE_CR0_GUEST_BITS;
vmx_set_cr0(vcpu, vmcs_readl(CR0_READ_SHADOW));
vcpu->arch.cr4_guest_owned_bits = ~vmcs_readl(CR4_GUEST_HOST_MASK);
@@ -3997,7 +4377,7 @@
nested_ept_uninit_mmu_context(vcpu);
vcpu->arch.cr3 = vmcs_readl(GUEST_CR3);
- __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail);
+ kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);
/*
* Use ept_save_pdptrs(vcpu) to load the MMU's cached PDPTRs
@@ -4005,7 +4385,7 @@
* VMFail, like everything else we just need to ensure our
* software model is up-to-date.
*/
- if (enable_ept)
+ if (enable_ept && is_pae_paging(vcpu))
ept_save_pdptrs(vcpu);
kvm_mmu_reset_context(vcpu);
@@ -4073,7 +4453,7 @@
* and modify vmcs12 to make it see what it would expect to see there if
* L2 was its real guest. Must only be called when in L2 (is_guest_mode())
*/
-void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason,
+void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
u32 exit_intr_info, unsigned long exit_qualification)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -4082,20 +4462,42 @@
/* trying to cancel vmlaunch/vmresume is a bug */
WARN_ON_ONCE(vmx->nested.nested_run_pending);
+ if (kvm_check_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu)) {
+ /*
+ * KVM_REQ_GET_NESTED_STATE_PAGES is also used to map
+ * Enlightened VMCS after migration and we still need to
+ * do that when something is forcing L2->L1 exit prior to
+ * the first L2 run.
+ */
+ (void)nested_get_evmcs_page(vcpu);
+ }
+
+ /* Service the TLB flush request for L2 before switching to L1. */
+ if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
+ kvm_vcpu_flush_tlb_current(vcpu);
+
+ /*
+ * VCPU_EXREG_PDPTR will be clobbered in arch/x86/kvm/vmx/vmx.h between
+ * now and the new vmentry. Ensure that the VMCS02 PDPTR fields are
+ * up-to-date before switching to L1.
+ */
+ if (enable_ept && is_pae_paging(vcpu))
+ vmx_ept_load_pdptrs(vcpu);
+
leave_guest_mode(vcpu);
if (nested_cpu_has_preemption_timer(vmcs12))
hrtimer_cancel(&to_vmx(vcpu)->nested.preemption_timer);
- if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
+ if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
vcpu->arch.tsc_offset -= vmcs12->tsc_offset;
if (likely(!vmx->fail)) {
sync_vmcs02_to_vmcs12(vcpu, vmcs12);
- if (exit_reason != -1)
- prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info,
- exit_qualification);
+ if (vm_exit_reason != -1)
+ prepare_vmcs12(vcpu, vmcs12, vm_exit_reason,
+ exit_intr_info, exit_qualification);
/*
* Must happen outside of sync_vmcs02_to_vmcs12() as it will
@@ -4125,6 +4527,8 @@
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.guest.nr);
vmcs_write64(TSC_OFFSET, vcpu->arch.tsc_offset);
+ if (vmx->nested.l1_tpr_threshold != -1)
+ vmcs_write32(TPR_THRESHOLD, vmx->nested.l1_tpr_threshold);
if (kvm_has_tsc_control)
decache_tsc_multiplier(vmx);
@@ -4132,35 +4536,31 @@
if (vmx->nested.change_vmcs01_virtual_apic_mode) {
vmx->nested.change_vmcs01_virtual_apic_mode = false;
vmx_set_virtual_apic_mode(vcpu);
- } else if (!nested_cpu_has_ept(vmcs12) &&
- nested_cpu_has2(vmcs12,
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
- vmx_flush_tlb(vcpu, true);
}
/* Unpin physical memory we referred to in vmcs02 */
if (vmx->nested.apic_access_page) {
- kvm_release_page_dirty(vmx->nested.apic_access_page);
+ kvm_release_page_clean(vmx->nested.apic_access_page);
vmx->nested.apic_access_page = NULL;
}
kvm_vcpu_unmap(vcpu, &vmx->nested.virtual_apic_map, true);
kvm_vcpu_unmap(vcpu, &vmx->nested.pi_desc_map, true);
vmx->nested.pi_desc = NULL;
- /*
- * We are now running in L2, mmu_notifier will force to reload the
- * page's hpa for L2 vmcs. Need to reload it for L1 before entering L1.
- */
- kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
+ if (vmx->nested.reload_vmcs01_apic_access_page) {
+ vmx->nested.reload_vmcs01_apic_access_page = false;
+ kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
+ }
- if ((exit_reason != -1) && (enable_shadow_vmcs || vmx->nested.hv_evmcs))
+ if ((vm_exit_reason != -1) &&
+ (enable_shadow_vmcs || vmx->nested.hv_evmcs))
vmx->nested.need_vmcs12_to_shadow_sync = true;
/* in case we halted in L2 */
vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
if (likely(!vmx->fail)) {
- if (exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
+ if ((u16)vm_exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT &&
nested_exit_intr_ack_set(vcpu)) {
int irq = kvm_cpu_get_interrupt(vcpu);
WARN_ON(irq < 0);
@@ -4168,7 +4568,7 @@
INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR;
}
- if (exit_reason != -1)
+ if (vm_exit_reason != -1)
trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason,
vmcs12->exit_qualification,
vmcs12->idt_vectoring_info_field,
@@ -4188,7 +4588,7 @@
* flag and the VM-instruction error field of the VMCS
* accordingly, and skip the emulated instruction.
*/
- (void)nested_vmx_failValid(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
+ (void)nested_vmx_fail(vcpu, VMXERR_ENTRY_INVALID_CONTROL_FIELD);
/*
* Restore L1's host state to KVM's software model. We're here
@@ -4205,7 +4605,7 @@
* Decode the memory-address operand of a vmx instruction, as recorded on an
* exit caused by such an instruction (run by a guest hypervisor).
* On success, returns 0. When the operand is invalid, returns 1 and throws
- * #UD or #GP.
+ * #UD, #GP, or #SS.
*/
int get_vmx_mem_address(struct kvm_vcpu *vcpu, unsigned long exit_qualification,
u32 vmx_instruction_info, bool wr, int len, gva_t *ret)
@@ -4244,9 +4644,9 @@
else if (addr_size == 0)
off = (gva_t)sign_extend64(off, 15);
if (base_is_valid)
- off += kvm_register_read(vcpu, base_reg);
+ off += kvm_register_readl(vcpu, base_reg);
if (index_is_valid)
- off += kvm_register_read(vcpu, index_reg)<<scaling;
+ off += kvm_register_readl(vcpu, index_reg) << scaling;
vmx_get_segment(vcpu, &s, seg_reg);
/*
@@ -4331,19 +4731,45 @@
return 0;
}
-static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer)
+void nested_vmx_pmu_entry_exit_ctls_update(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx;
+
+ if (!nested_vmx_allowed(vcpu))
+ return;
+
+ vmx = to_vmx(vcpu);
+ if (kvm_x86_ops.pmu_ops->is_valid_msr(vcpu, MSR_CORE_PERF_GLOBAL_CTRL)) {
+ vmx->nested.msrs.entry_ctls_high |=
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmx->nested.msrs.exit_ctls_high |=
+ VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ } else {
+ vmx->nested.msrs.entry_ctls_high &=
+ ~VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
+ vmx->nested.msrs.exit_ctls_high &=
+ ~VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
+ }
+}
+
+static int nested_vmx_get_vmptr(struct kvm_vcpu *vcpu, gpa_t *vmpointer,
+ int *ret)
{
gva_t gva;
struct x86_exception e;
+ int r;
- if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
vmcs_read32(VMX_INSTRUCTION_INFO), false,
- sizeof(*vmpointer), &gva))
- return 1;
+ sizeof(*vmpointer), &gva)) {
+ *ret = 1;
+ return -EINVAL;
+ }
- if (kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
+ r = kvm_read_guest_virt(vcpu, gva, vmpointer, sizeof(*vmpointer), &e);
+ if (r != X86EMUL_CONTINUE) {
+ *ret = kvm_handle_memory_failure(vcpu, r, &e);
+ return -EINVAL;
}
return 0;
@@ -4396,7 +4822,7 @@
goto out_shadow_vmcs;
hrtimer_init(&vmx->nested.preemption_timer, CLOCK_MONOTONIC,
- HRTIMER_MODE_REL_PINNED);
+ HRTIMER_MODE_ABS_PINNED);
vmx->nested.preemption_timer.function = vmx_preemption_timer_fn;
vmx->nested.vpid02 = allocate_vpid();
@@ -4404,9 +4830,9 @@
vmx->nested.vmcs02_initialized = false;
vmx->nested.vmxon = true;
- if (pt_mode == PT_MODE_HOST_GUEST) {
+ 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;
@@ -4438,8 +4864,8 @@
gpa_t vmptr;
uint32_t revision;
struct vcpu_vmx *vmx = to_vmx(vcpu);
- const u64 VMXON_NEEDED_FEATURES = FEATURE_CONTROL_LOCKED
- | FEATURE_CONTROL_VMXON_ENABLED_OUTSIDE_SMX;
+ const u64 VMXON_NEEDED_FEATURES = FEAT_CTL_LOCKED
+ | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX;
/*
* The Intel VMX Instruction Reference lists a bunch of bits that are
@@ -4462,8 +4888,7 @@
}
if (vmx->nested.vmxon)
- return nested_vmx_failValid(vcpu,
- VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
+ return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES)
!= VMXON_NEEDED_FEATURES) {
@@ -4471,8 +4896,8 @@
return 1;
}
- if (nested_vmx_get_vmptr(vcpu, &vmptr))
- return 1;
+ if (nested_vmx_get_vmptr(vcpu, &vmptr, &ret))
+ return ret;
/*
* SDM 3: 24.11.5
@@ -4545,20 +4970,19 @@
u32 zero = 0;
gpa_t vmptr;
u64 evmcs_gpa;
+ int r;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_get_vmptr(vcpu, &vmptr))
- return 1;
+ if (nested_vmx_get_vmptr(vcpu, &vmptr, &r))
+ return r;
if (!page_address_valid(vcpu, vmptr))
- return nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_INVALID_ADDRESS);
+ return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS);
if (vmptr == vmx->nested.vmxon_ptr)
- return nested_vmx_failValid(vcpu,
- VMXERR_VMCLEAR_VMXON_POINTER);
+ return nested_vmx_fail(vcpu, VMXERR_VMCLEAR_VMXON_POINTER);
/*
* When Enlightened VMEntry is enabled on the calling CPU we treat
@@ -4584,8 +5008,6 @@
return nested_vmx_succeed(vcpu);
}
-static int nested_vmx_run(struct kvm_vcpu *vcpu, bool launch);
-
/* Emulate the VMLAUNCH instruction */
static int handle_vmlaunch(struct kvm_vcpu *vcpu)
{
@@ -4601,17 +5023,17 @@
static int handle_vmread(struct kvm_vcpu *vcpu)
{
- unsigned long field;
- u64 field_value;
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
- int len;
- gva_t gva = 0;
struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
: get_vmcs12(vcpu);
+ unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
+ u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
struct x86_exception e;
+ unsigned long field;
+ u64 value;
+ gva_t gva = 0;
short offset;
+ int len, r;
if (!nested_vmx_check_permission(vcpu))
return 1;
@@ -4626,37 +5048,34 @@
return nested_vmx_failInvalid(vcpu);
/* Decode instruction info and find the field to read */
- field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+ field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf));
offset = vmcs_field_to_offset(field);
if (offset < 0)
- return nested_vmx_failValid(vcpu,
- VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+ return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
if (!is_guest_mode(vcpu) && is_vmcs12_ext_field(field))
copy_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
- /* Read the field, zero-extended to a u64 field_value */
- field_value = vmcs12_read_any(vmcs12, field, offset);
+ /* Read the field, zero-extended to a u64 value */
+ value = vmcs12_read_any(vmcs12, field, offset);
/*
* Now copy part of this value to register or memory, as requested.
* Note that the number of bits actually copied is 32 or 64 depending
* on the guest's mode (32 or 64 bit), not on the given field's length.
*/
- if (vmx_instruction_info & (1u << 10)) {
- kvm_register_writel(vcpu, (((vmx_instruction_info) >> 3) & 0xf),
- field_value);
+ if (instr_info & BIT(10)) {
+ kvm_register_writel(vcpu, (((instr_info) >> 3) & 0xf), value);
} else {
len = is_64_bit_mode(vcpu) ? 8 : 4;
if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, true, len, &gva))
+ instr_info, true, len, &gva))
return 1;
/* _system ok, nested_vmx_check_permission has verified cpl=0 */
- if (kvm_write_guest_virt_system(vcpu, gva, &field_value, len, &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
- }
+ r = kvm_write_guest_virt_system(vcpu, gva, &value, len, &e);
+ if (r != X86EMUL_CONTINUE)
+ return kvm_handle_memory_failure(vcpu, r, &e);
}
return nested_vmx_succeed(vcpu);
@@ -4688,24 +5107,25 @@
static int handle_vmwrite(struct kvm_vcpu *vcpu)
{
- unsigned long field;
- int len;
- gva_t gva;
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
- u32 vmx_instruction_info = vmcs_read32(VMX_INSTRUCTION_INFO);
-
- /* The value to write might be 32 or 64 bits, depending on L1's long
- * mode, and eventually we need to write that into a field of several
- * possible lengths. The code below first zero-extends the value to 64
- * bit (field_value), and then copies only the appropriate number of
- * bits into the vmcs12 field.
- */
- u64 field_value = 0;
- struct x86_exception e;
struct vmcs12 *vmcs12 = is_guest_mode(vcpu) ? get_shadow_vmcs12(vcpu)
: get_vmcs12(vcpu);
+ unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
+ u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct x86_exception e;
+ unsigned long field;
short offset;
+ gva_t gva;
+ int len, r;
+
+ /*
+ * The value to write might be 32 or 64 bits, depending on L1's long
+ * mode, and eventually we need to write that into a field of several
+ * possible lengths. The code below first zero-extends the value to 64
+ * bit (value), and then copies only the appropriate number of
+ * bits into the vmcs12 field.
+ */
+ u64 value = 0;
if (!nested_vmx_check_permission(vcpu))
return 1;
@@ -4719,27 +5139,23 @@
get_vmcs12(vcpu)->vmcs_link_pointer == -1ull))
return nested_vmx_failInvalid(vcpu);
- if (vmx_instruction_info & (1u << 10))
- field_value = kvm_register_readl(vcpu,
- (((vmx_instruction_info) >> 3) & 0xf));
+ if (instr_info & BIT(10))
+ value = kvm_register_readl(vcpu, (((instr_info) >> 3) & 0xf));
else {
len = is_64_bit_mode(vcpu) ? 8 : 4;
if (get_vmx_mem_address(vcpu, exit_qualification,
- vmx_instruction_info, false, len, &gva))
+ instr_info, false, len, &gva))
return 1;
- if (kvm_read_guest_virt(vcpu, gva, &field_value, len, &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
- }
+ r = kvm_read_guest_virt(vcpu, gva, &value, len, &e);
+ if (r != X86EMUL_CONTINUE)
+ return kvm_handle_memory_failure(vcpu, r, &e);
}
-
- field = kvm_register_readl(vcpu, (((vmx_instruction_info) >> 28) & 0xf));
+ field = kvm_register_readl(vcpu, (((instr_info) >> 28) & 0xf));
offset = vmcs_field_to_offset(field);
if (offset < 0)
- return nested_vmx_failValid(vcpu,
- VMXERR_UNSUPPORTED_VMCS_COMPONENT);
+ return nested_vmx_fail(vcpu, VMXERR_UNSUPPORTED_VMCS_COMPONENT);
/*
* If the vCPU supports "VMWRITE to any supported field in the
@@ -4747,8 +5163,7 @@
*/
if (vmcs_field_readonly(field) &&
!nested_cpu_has_vmwrite_any_field(vcpu))
- return nested_vmx_failValid(vcpu,
- VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
+ return nested_vmx_fail(vcpu, VMXERR_VMWRITE_READ_ONLY_VMCS_COMPONENT);
/*
* Ensure vmcs12 is up-to-date before any VMWRITE that dirties
@@ -4766,9 +5181,9 @@
* the stripped down value, L2 sees the full value as stored by KVM).
*/
if (field >= GUEST_ES_AR_BYTES && field <= GUEST_TR_AR_BYTES)
- field_value &= 0x1f0ff;
+ value &= 0x1f0ff;
- vmcs12_write_any(vmcs12, field, offset, field_value);
+ vmcs12_write_any(vmcs12, field, offset, value);
/*
* Do not track vmcs12 dirty-state if in guest-mode as we actually
@@ -4785,7 +5200,7 @@
preempt_disable();
vmcs_load(vmx->vmcs01.shadow_vmcs);
- __vmcs_writel(field, field_value);
+ __vmcs_writel(field, value);
vmcs_clear(vmx->vmcs01.shadow_vmcs);
vmcs_load(vmx->loaded_vmcs->vmcs);
@@ -4814,20 +5229,19 @@
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
gpa_t vmptr;
+ int r;
if (!nested_vmx_check_permission(vcpu))
return 1;
- if (nested_vmx_get_vmptr(vcpu, &vmptr))
- return 1;
+ if (nested_vmx_get_vmptr(vcpu, &vmptr, &r))
+ return r;
if (!page_address_valid(vcpu, vmptr))
- return nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_INVALID_ADDRESS);
+ return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS);
if (vmptr == vmx->nested.vmxon_ptr)
- return nested_vmx_failValid(vcpu,
- VMXERR_VMPTRLD_VMXON_POINTER);
+ return nested_vmx_fail(vcpu, VMXERR_VMPTRLD_VMXON_POINTER);
/* Forbid normal VMPTRLD if Enlightened version was used */
if (vmx->nested.hv_evmcs)
@@ -4844,7 +5258,7 @@
* given physical address won't match the required
* VMCS12_REVISION identifier.
*/
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
}
@@ -4854,7 +5268,7 @@
(new_vmcs12->hdr.shadow_vmcs &&
!nested_cpu_has_vmx_shadow_vmcs(vcpu))) {
kvm_vcpu_unmap(vcpu, &map, false);
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_VMPTRLD_INCORRECT_VMCS_REVISION_ID);
}
@@ -4876,11 +5290,12 @@
/* Emulate the VMPTRST instruction */
static int handle_vmptrst(struct kvm_vcpu *vcpu)
{
- unsigned long exit_qual = vmcs_readl(EXIT_QUALIFICATION);
+ unsigned long exit_qual = vmx_get_exit_qual(vcpu);
u32 instr_info = vmcs_read32(VMX_INSTRUCTION_INFO);
gpa_t current_vmptr = to_vmx(vcpu)->nested.current_vmptr;
struct x86_exception e;
gva_t gva;
+ int r;
if (!nested_vmx_check_permission(vcpu))
return 1;
@@ -4892,25 +5307,35 @@
true, sizeof(gpa_t), &gva))
return 1;
/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
- if (kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr,
- sizeof(gpa_t), &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
- }
+ r = kvm_write_guest_virt_system(vcpu, gva, (void *)¤t_vmptr,
+ sizeof(gpa_t), &e);
+ if (r != X86EMUL_CONTINUE)
+ return kvm_handle_memory_failure(vcpu, r, &e);
+
return nested_vmx_succeed(vcpu);
}
+#define EPTP_PA_MASK GENMASK_ULL(51, 12)
+
+static bool nested_ept_root_matches(hpa_t root_hpa, u64 root_eptp, u64 eptp)
+{
+ return VALID_PAGE(root_hpa) &&
+ ((root_eptp & EPTP_PA_MASK) == (eptp & EPTP_PA_MASK));
+}
+
/* Emulate the INVEPT instruction */
static int handle_invept(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
u32 vmx_instruction_info, types;
- unsigned long type;
+ unsigned long type, roots_to_free;
+ struct kvm_mmu *mmu;
gva_t gva;
struct x86_exception e;
struct {
u64 eptp, gpa;
} operand;
+ int i, r;
if (!(vmx->nested.msrs.secondary_ctls_high &
SECONDARY_EXEC_ENABLE_EPT) ||
@@ -4928,33 +5353,53 @@
types = (vmx->nested.msrs.ept_caps >> VMX_EPT_EXTENT_SHIFT) & 6;
if (type >= 32 || !(types & (1 << type)))
- return nested_vmx_failValid(vcpu,
- VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+ return nested_vmx_fail(vcpu, VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
/* According to the Intel VMX instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
*/
- if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
vmx_instruction_info, false, sizeof(operand), &gva))
return 1;
- if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
- }
+ r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
+ if (r != X86EMUL_CONTINUE)
+ return kvm_handle_memory_failure(vcpu, r, &e);
+
+ /*
+ * Nested EPT roots are always held through guest_mmu,
+ * not root_mmu.
+ */
+ mmu = &vcpu->arch.guest_mmu;
switch (type) {
- case VMX_EPT_EXTENT_GLOBAL:
case VMX_EPT_EXTENT_CONTEXT:
- /*
- * TODO: Sync the necessary shadow EPT roots here, rather than
- * at the next emulated VM-entry.
- */
+ if (!nested_vmx_check_eptp(vcpu, operand.eptp))
+ return nested_vmx_fail(vcpu,
+ VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
+
+ roots_to_free = 0;
+ if (nested_ept_root_matches(mmu->root_hpa, mmu->root_pgd,
+ operand.eptp))
+ roots_to_free |= KVM_MMU_ROOT_CURRENT;
+
+ for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) {
+ if (nested_ept_root_matches(mmu->prev_roots[i].hpa,
+ mmu->prev_roots[i].pgd,
+ operand.eptp))
+ roots_to_free |= KVM_MMU_ROOT_PREVIOUS(i);
+ }
+ break;
+ case VMX_EPT_EXTENT_GLOBAL:
+ roots_to_free = KVM_MMU_ROOTS_ALL;
break;
default:
- BUG_ON(1);
+ BUG();
break;
}
+ if (roots_to_free)
+ kvm_mmu_free_roots(vcpu, mmu, roots_to_free);
+
return nested_vmx_succeed(vcpu);
}
@@ -4970,6 +5415,7 @@
u64 gla;
} operand;
u16 vpid02;
+ int r;
if (!(vmx->nested.msrs.secondary_ctls_high &
SECONDARY_EXEC_ENABLE_VPID) ||
@@ -4988,21 +5434,21 @@
VMX_VPID_EXTENT_SUPPORTED_MASK) >> 8;
if (type >= 32 || !(types & (1 << type)))
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
/* according to the intel vmx instruction reference, the memory
* operand is read even if it isn't needed (e.g., for type==global)
*/
- if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION),
+ if (get_vmx_mem_address(vcpu, vmx_get_exit_qual(vcpu),
vmx_instruction_info, false, sizeof(operand), &gva))
return 1;
- if (kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e)) {
- kvm_inject_page_fault(vcpu, &e);
- return 1;
- }
+ r = kvm_read_guest_virt(vcpu, gva, &operand, sizeof(operand), &e);
+ if (r != X86EMUL_CONTINUE)
+ return kvm_handle_memory_failure(vcpu, r, &e);
+
if (operand.vpid >> 16)
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
vpid02 = nested_get_vpid02(vcpu);
@@ -5010,29 +5456,39 @@
case VMX_VPID_EXTENT_INDIVIDUAL_ADDR:
if (!operand.vpid ||
is_noncanonical_address(operand.gla, vcpu))
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- if (cpu_has_vmx_invvpid_individual_addr()) {
- __invvpid(VMX_VPID_EXTENT_INDIVIDUAL_ADDR,
- vpid02, operand.gla);
- } else
- __vmx_flush_tlb(vcpu, vpid02, false);
+ vpid_sync_vcpu_addr(vpid02, operand.gla);
break;
case VMX_VPID_EXTENT_SINGLE_CONTEXT:
case VMX_VPID_EXTENT_SINGLE_NON_GLOBAL:
if (!operand.vpid)
- return nested_vmx_failValid(vcpu,
+ return nested_vmx_fail(vcpu,
VMXERR_INVALID_OPERAND_TO_INVEPT_INVVPID);
- __vmx_flush_tlb(vcpu, vpid02, false);
+ vpid_sync_context(vpid02);
break;
case VMX_VPID_EXTENT_ALL_CONTEXT:
- __vmx_flush_tlb(vcpu, vpid02, false);
+ vpid_sync_context(vpid02);
break;
default:
WARN_ON_ONCE(1);
return kvm_skip_emulated_instruction(vcpu);
}
+ /*
+ * Sync the shadow page tables if EPT is disabled, L1 is invalidating
+ * linear mappings for L2 (tagged with L2's VPID). Free all roots as
+ * VPIDs are not tracked in the MMU role.
+ *
+ * Note, this operates on root_mmu, not guest_mmu, as L1 and L2 share
+ * an MMU when EPT is disabled.
+ *
+ * TODO: sync only the affected SPTEs for INVDIVIDUAL_ADDR.
+ */
+ if (!enable_ept)
+ kvm_mmu_free_roots(vcpu, &vcpu->arch.root_mmu,
+ KVM_MMU_ROOTS_ALL);
+
return nested_vmx_succeed(vcpu);
}
@@ -5040,9 +5496,7 @@
struct vmcs12 *vmcs12)
{
u32 index = kvm_rcx_read(vcpu);
- u64 address;
- bool accessed_dirty;
- struct kvm_mmu *mmu = vcpu->arch.walk_mmu;
+ u64 new_eptp;
if (!nested_cpu_has_eptp_switching(vmcs12) ||
!nested_cpu_has_ept(vmcs12))
@@ -5051,31 +5505,21 @@
if (index >= VMFUNC_EPTP_ENTRIES)
return 1;
-
if (kvm_vcpu_read_guest_page(vcpu, vmcs12->eptp_list_address >> PAGE_SHIFT,
- &address, index * 8, 8))
+ &new_eptp, index * 8, 8))
return 1;
- accessed_dirty = !!(address & VMX_EPTP_AD_ENABLE_BIT);
-
/*
* If the (L2) guest does a vmfunc to the currently
* active ept pointer, we don't have to do anything else
*/
- if (vmcs12->ept_pointer != address) {
- if (!valid_ept_address(vcpu, address))
+ if (vmcs12->ept_pointer != new_eptp) {
+ if (!nested_vmx_check_eptp(vcpu, new_eptp))
return 1;
- kvm_mmu_unload(vcpu);
- mmu->ept_ad = accessed_dirty;
- mmu->mmu_role.base.ad_disabled = !accessed_dirty;
- vmcs12->ept_pointer = address;
- /*
- * TODO: Check what's the correct approach in case
- * mmu reload fails. Currently, we just let the next
- * reload potentially fail
- */
- kvm_mmu_reload(vcpu);
+ vmcs12->ept_pointer = new_eptp;
+
+ kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
}
return 0;
@@ -5112,9 +5556,14 @@
return kvm_skip_emulated_instruction(vcpu);
fail:
- nested_vmx_vmexit(vcpu, vmx->exit_reason,
- vmcs_read32(VM_EXIT_INTR_INFO),
- vmcs_readl(EXIT_QUALIFICATION));
+ /*
+ * This is effectively a reflected VM-Exit, as opposed to a synthesized
+ * nested VM-Exit. Pass the original exit reason, i.e. don't hardcode
+ * EXIT_REASON_VMFUNC as the exit reason.
+ */
+ nested_vmx_vmexit(vcpu, vmx->exit_reason.full,
+ vmx_get_intr_info(vcpu),
+ vmx_get_exit_qual(vcpu));
return 1;
}
@@ -5165,7 +5614,7 @@
if (!nested_cpu_has(vmcs12, CPU_BASED_USE_IO_BITMAPS))
return nested_cpu_has(vmcs12, CPU_BASED_UNCOND_IO_EXITING);
- exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+ exit_qualification = vmx_get_exit_qual(vcpu);
port = exit_qualification >> 16;
size = (exit_qualification & 7) + 1;
@@ -5174,13 +5623,14 @@
}
/*
- * Return 1 if we should exit from L2 to L1 to handle an MSR access access,
+ * Return 1 if we should exit from L2 to L1 to handle an MSR access,
* rather than handle it ourselves in L0. I.e., check whether L1 expressed
* disinterest in the current event (read or write a specific MSR) by using an
* MSR bitmap. This may be the case even when L0 doesn't use MSR bitmaps.
*/
static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
- struct vmcs12 *vmcs12, u32 exit_reason)
+ struct vmcs12 *vmcs12,
+ union vmx_exit_reason exit_reason)
{
u32 msr_index = kvm_rcx_read(vcpu);
gpa_t bitmap;
@@ -5194,7 +5644,7 @@
* First we need to figure out which of the four to use:
*/
bitmap = vmcs12->msr_bitmap;
- if (exit_reason == EXIT_REASON_MSR_WRITE)
+ if (exit_reason.basic == EXIT_REASON_MSR_WRITE)
bitmap += 2048;
if (msr_index >= 0xc0000000) {
msr_index -= 0xc0000000;
@@ -5219,7 +5669,7 @@
static bool nested_vmx_exit_handled_cr(struct kvm_vcpu *vcpu,
struct vmcs12 *vmcs12)
{
- unsigned long exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+ unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
int cr = exit_qualification & 15;
int reg;
unsigned long val;
@@ -5235,15 +5685,6 @@
return true;
break;
case 3:
- if ((vmcs12->cr3_target_count >= 1 &&
- vmcs12->cr3_target_value0 == val) ||
- (vmcs12->cr3_target_count >= 2 &&
- vmcs12->cr3_target_value1 == val) ||
- (vmcs12->cr3_target_count >= 3 &&
- vmcs12->cr3_target_value2 == val) ||
- (vmcs12->cr3_target_count >= 4 &&
- vmcs12->cr3_target_value3 == val))
- return false;
if (nested_cpu_has(vmcs12, CPU_BASED_CR3_LOAD_EXITING))
return true;
break;
@@ -5319,70 +5760,115 @@
return 1 & (b >> (field & 7));
}
-/*
- * Return 1 if we should exit from L2 to L1 to handle an exit, or 0 if we
- * should handle it ourselves in L0 (and then continue L2). Only call this
- * when in is_guest_mode (L2).
- */
-bool nested_vmx_exit_reflected(struct kvm_vcpu *vcpu, u32 exit_reason)
+static bool nested_vmx_exit_handled_mtf(struct vmcs12 *vmcs12)
{
- u32 intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ u32 entry_intr_info = vmcs12->vm_entry_intr_info_field;
- if (vmx->nested.nested_run_pending)
- return false;
-
- if (unlikely(vmx->fail)) {
- trace_kvm_nested_vmenter_failed(
- "hardware VM-instruction error: ",
- vmcs_read32(VM_INSTRUCTION_ERROR));
+ if (nested_cpu_has_mtf(vmcs12))
return true;
- }
/*
- * The host physical addresses of some pages of guest memory
- * are loaded into the vmcs02 (e.g. vmcs12's Virtual APIC
- * Page). The CPU may write to these pages via their host
- * physical address while L2 is running, bypassing any
- * address-translation-based dirty tracking (e.g. EPT write
- * protection).
- *
- * Mark them dirty on every exit from L2 to prevent them from
- * getting out of sync with dirty tracking.
+ * An MTF VM-exit may be injected into the guest by setting the
+ * interruption-type to 7 (other event) and the vector field to 0. Such
+ * is the case regardless of the 'monitor trap flag' VM-execution
+ * control.
*/
- nested_mark_vmcs12_pages_dirty(vcpu);
+ return entry_intr_info == (INTR_INFO_VALID_MASK
+ | INTR_TYPE_OTHER_EVENT);
+}
- trace_kvm_nested_vmexit(kvm_rip_read(vcpu), exit_reason,
- vmcs_readl(EXIT_QUALIFICATION),
- vmx->idt_vectoring_info,
- intr_info,
- vmcs_read32(VM_EXIT_INTR_ERROR_CODE),
- KVM_ISA_VMX);
+/*
+ * Return true if L0 wants to handle an exit from L2 regardless of whether or not
+ * L1 wants the exit. Only call this when in is_guest_mode (L2).
+ */
+static bool nested_vmx_l0_wants_exit(struct kvm_vcpu *vcpu,
+ union vmx_exit_reason exit_reason)
+{
+ u32 intr_info;
- switch ((u16)exit_reason) {
+ switch ((u16)exit_reason.basic) {
case EXIT_REASON_EXCEPTION_NMI:
+ intr_info = vmx_get_intr_info(vcpu);
if (is_nmi(intr_info))
- return false;
+ return true;
else if (is_page_fault(intr_info))
- return !vmx->vcpu.arch.apf.host_apf_reason && enable_ept;
+ return vcpu->arch.apf.host_apf_flags ||
+ vmx_need_pf_intercept(vcpu);
else if (is_debug(intr_info) &&
vcpu->guest_debug &
(KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))
- return false;
+ return true;
else if (is_breakpoint(intr_info) &&
vcpu->guest_debug & KVM_GUESTDBG_USE_SW_BP)
- return false;
+ return true;
+ else if (is_alignment_check(intr_info) &&
+ !vmx_guest_inject_ac(vcpu))
+ return true;
+ return false;
+ case EXIT_REASON_EXTERNAL_INTERRUPT:
+ return true;
+ case EXIT_REASON_MCE_DURING_VMENTRY:
+ return true;
+ case EXIT_REASON_EPT_VIOLATION:
+ /*
+ * L0 always deals with the EPT violation. If nested EPT is
+ * used, and the nested mmu code discovers that the address is
+ * missing in the guest EPT table (EPT12), the EPT violation
+ * will be injected with nested_ept_inject_page_fault()
+ */
+ return true;
+ case EXIT_REASON_EPT_MISCONFIG:
+ /*
+ * L2 never uses directly L1's EPT, but rather L0's own EPT
+ * table (shadow on EPT) or a merged EPT table that L0 built
+ * (EPT on EPT). So any problems with the structure of the
+ * table is L0's fault.
+ */
+ return true;
+ case EXIT_REASON_PREEMPTION_TIMER:
+ return true;
+ case EXIT_REASON_PML_FULL:
+ /* We emulate PML support to L1. */
+ return true;
+ case EXIT_REASON_VMFUNC:
+ /* VM functions are emulated through L2->L0 vmexits. */
+ return true;
+ case EXIT_REASON_ENCLS:
+ /* SGX is never exposed to L1 */
+ return true;
+ default:
+ break;
+ }
+ return false;
+}
+
+/*
+ * Return 1 if L1 wants to intercept an exit from L2. Only call this when in
+ * is_guest_mode (L2).
+ */
+static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
+ union vmx_exit_reason exit_reason)
+{
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+ u32 intr_info;
+
+ switch ((u16)exit_reason.basic) {
+ case EXIT_REASON_EXCEPTION_NMI:
+ intr_info = vmx_get_intr_info(vcpu);
+ if (is_nmi(intr_info))
+ return true;
+ else if (is_page_fault(intr_info))
+ return true;
return vmcs12->exception_bitmap &
(1u << (intr_info & INTR_INFO_VECTOR_MASK));
case EXIT_REASON_EXTERNAL_INTERRUPT:
- return false;
+ return nested_exit_on_intr(vcpu);
case EXIT_REASON_TRIPLE_FAULT:
return true;
- case EXIT_REASON_PENDING_INTERRUPT:
- return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_INTR_PENDING);
+ case EXIT_REASON_INTERRUPT_WINDOW:
+ return nested_cpu_has(vmcs12, CPU_BASED_INTR_WINDOW_EXITING);
case EXIT_REASON_NMI_WINDOW:
- return nested_cpu_has(vmcs12, CPU_BASED_VIRTUAL_NMI_PENDING);
+ return nested_cpu_has(vmcs12, CPU_BASED_NMI_WINDOW_EXITING);
case EXIT_REASON_TASK_SWITCH:
return true;
case EXIT_REASON_CPUID:
@@ -5433,7 +5919,7 @@
case EXIT_REASON_MWAIT_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MWAIT_EXITING);
case EXIT_REASON_MONITOR_TRAP_FLAG:
- return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_TRAP_FLAG);
+ return nested_vmx_exit_handled_mtf(vmcs12);
case EXIT_REASON_MONITOR_INSTRUCTION:
return nested_cpu_has(vmcs12, CPU_BASED_MONITOR_EXITING);
case EXIT_REASON_PAUSE_INSTRUCTION:
@@ -5441,7 +5927,7 @@
nested_cpu_has2(vmcs12,
SECONDARY_EXEC_PAUSE_LOOP_EXITING);
case EXIT_REASON_MCE_DURING_VMENTRY:
- return false;
+ return true;
case EXIT_REASON_TPR_BELOW_THRESHOLD:
return nested_cpu_has(vmcs12, CPU_BASED_TPR_SHADOW);
case EXIT_REASON_APIC_ACCESS:
@@ -5453,22 +5939,6 @@
* delivery" only come from vmcs12.
*/
return true;
- case EXIT_REASON_EPT_VIOLATION:
- /*
- * L0 always deals with the EPT violation. If nested EPT is
- * used, and the nested mmu code discovers that the address is
- * missing in the guest EPT table (EPT12), the EPT violation
- * will be injected with nested_ept_inject_page_fault()
- */
- return false;
- case EXIT_REASON_EPT_MISCONFIG:
- /*
- * L2 never uses directly L1's EPT, but rather L0's own EPT
- * table (shadow on EPT) or a merged EPT table that L0 built
- * (EPT on EPT). So any problems with the structure of the
- * table is L0's fault.
- */
- return false;
case EXIT_REASON_INVPCID:
return
nested_cpu_has2(vmcs12, SECONDARY_EXEC_ENABLE_INVPCID) &&
@@ -5485,17 +5955,6 @@
* the XSS exit bitmap in vmcs12.
*/
return nested_cpu_has2(vmcs12, SECONDARY_EXEC_XSAVES);
- case EXIT_REASON_PREEMPTION_TIMER:
- return false;
- case EXIT_REASON_PML_FULL:
- /* We emulate PML support to L1. */
- return false;
- case EXIT_REASON_VMFUNC:
- /* VM functions are emulated through L2->L0 vmexits. */
- return false;
- case EXIT_REASON_ENCLS:
- /* SGX is never exposed to L1 */
- return false;
case EXIT_REASON_UMWAIT:
case EXIT_REASON_TPAUSE:
return nested_cpu_has2(vmcs12,
@@ -5505,6 +5964,61 @@
}
}
+/*
+ * Conditionally reflect a VM-Exit into L1. Returns %true if the VM-Exit was
+ * reflected into L1.
+ */
+bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ union vmx_exit_reason exit_reason = vmx->exit_reason;
+ unsigned long exit_qual;
+ u32 exit_intr_info;
+
+ WARN_ON_ONCE(vmx->nested.nested_run_pending);
+
+ /*
+ * Late nested VM-Fail shares the same flow as nested VM-Exit since KVM
+ * has already loaded L2's state.
+ */
+ if (unlikely(vmx->fail)) {
+ trace_kvm_nested_vmenter_failed(
+ "hardware VM-instruction error: ",
+ vmcs_read32(VM_INSTRUCTION_ERROR));
+ exit_intr_info = 0;
+ exit_qual = 0;
+ goto reflect_vmexit;
+ }
+
+ trace_kvm_nested_vmexit(exit_reason.full, vcpu, KVM_ISA_VMX);
+
+ /* If L0 (KVM) wants the exit, it trumps L1's desires. */
+ if (nested_vmx_l0_wants_exit(vcpu, exit_reason))
+ return false;
+
+ /* If L1 doesn't want the exit, handle it in L0. */
+ if (!nested_vmx_l1_wants_exit(vcpu, exit_reason))
+ return false;
+
+ /*
+ * vmcs.VM_EXIT_INTR_INFO is only valid for EXCEPTION_NMI exits. For
+ * EXTERNAL_INTERRUPT, the value for vmcs12->vm_exit_intr_info would
+ * need to be synthesized by querying the in-kernel LAPIC, but external
+ * interrupts are never reflected to L1 so it's a non-issue.
+ */
+ exit_intr_info = vmx_get_intr_info(vcpu);
+ if (is_exception_with_error_code(exit_intr_info)) {
+ struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+
+ vmcs12->vm_exit_intr_error_code =
+ vmcs_read32(VM_EXIT_INTR_ERROR_CODE);
+ }
+ exit_qual = vmx_get_exit_qual(vcpu);
+
+reflect_vmexit:
+ nested_vmx_vmexit(vcpu, exit_reason.full, exit_intr_info, exit_qual);
+ return true;
+}
static int vmx_get_nested_state(struct kvm_vcpu *vcpu,
struct kvm_nested_state __user *user_kvm_nested_state,
@@ -5516,8 +6030,10 @@
.flags = 0,
.format = KVM_STATE_NESTED_FORMAT_VMX,
.size = sizeof(kvm_state),
+ .hdr.vmx.flags = 0,
.hdr.vmx.vmxon_pa = -1ull,
.hdr.vmx.vmcs12_pa = -1ull,
+ .hdr.vmx.preemption_timer_deadline = 0,
};
struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
&user_kvm_nested_state->data.vmx[0];
@@ -5556,6 +6072,17 @@
if (vmx->nested.nested_run_pending)
kvm_state.flags |= KVM_STATE_NESTED_RUN_PENDING;
+
+ if (vmx->nested.mtf_pending)
+ kvm_state.flags |= KVM_STATE_NESTED_MTF_PENDING;
+
+ if (nested_cpu_has_preemption_timer(vmcs12) &&
+ vmx->nested.has_preemption_timer_deadline) {
+ kvm_state.hdr.vmx.flags |=
+ KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE;
+ kvm_state.hdr.vmx.preemption_timer_deadline =
+ vmx->nested.preemption_timer_deadline;
+ }
}
}
@@ -5604,7 +6131,6 @@
get_shadow_vmcs12(vcpu), VMCS12_SIZE))
return -EFAULT;
}
-
out:
return kvm_state.size;
}
@@ -5627,7 +6153,7 @@
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
struct vmcs12 *vmcs12;
- u32 exit_qual;
+ enum vm_entry_failure_code ignored;
struct kvm_vmx_nested_state_data __user *user_vmx_nested_state =
&user_kvm_nested_state->data.vmx[0];
int ret;
@@ -5669,6 +6195,9 @@
~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
return -EINVAL;
+ if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE)
+ return -EINVAL;
+
/*
* SMM temporarily disables VMX, so we cannot be in guest mode,
* nor can VMLAUNCH/VMRESUME be pending. Outside SMM, SMM flags
@@ -5698,9 +6227,16 @@
if (ret)
return ret;
- /* Empty 'VMXON' state is permitted */
- if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
- return 0;
+ /* Empty 'VMXON' state is permitted if no VMCS loaded */
+ if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) {
+ /* See vmx_has_valid_vmcs12. */
+ if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) ||
+ (kvm_state->flags & KVM_STATE_NESTED_EVMCS) ||
+ (kvm_state->hdr.vmx.vmcs12_pa != -1ull))
+ return -EINVAL;
+ else
+ return 0;
+ }
if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) {
if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
@@ -5710,10 +6246,12 @@
set_current_vmptr(vmx, kvm_state->hdr.vmx.vmcs12_pa);
} else if (kvm_state->flags & KVM_STATE_NESTED_EVMCS) {
/*
- * Sync eVMCS upon entry as we may not have
- * HV_X64_MSR_VP_ASSIST_PAGE set up yet.
+ * nested_vmx_handle_enlightened_vmptrld() cannot be called
+ * directly from here as HV_X64_MSR_VP_ASSIST_PAGE may not be
+ * restored yet. EVMCS will be mapped from
+ * nested_get_vmcs12_pages().
*/
- vmx->nested.need_vmcs12_to_shadow_sync = true;
+ kvm_make_request(KVM_REQ_GET_NESTED_STATE_PAGES, vcpu);
} else {
return -EINVAL;
}
@@ -5739,6 +6277,9 @@
vmx->nested.nested_run_pending =
!!(kvm_state->flags & KVM_STATE_NESTED_RUN_PENDING);
+ vmx->nested.mtf_pending =
+ !!(kvm_state->flags & KVM_STATE_NESTED_MTF_PENDING);
+
ret = -EINVAL;
if (nested_cpu_has_shadow_vmcs(vmcs12) &&
vmcs12->vmcs_link_pointer != -1ull) {
@@ -5761,9 +6302,16 @@
goto error_guest_mode;
}
+ vmx->nested.has_preemption_timer_deadline = false;
+ if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) {
+ vmx->nested.has_preemption_timer_deadline = true;
+ vmx->nested.preemption_timer_deadline =
+ kvm_state->hdr.vmx.preemption_timer_deadline;
+ }
+
if (nested_vmx_check_controls(vcpu, vmcs12) ||
nested_vmx_check_host_state(vcpu, vmcs12) ||
- nested_vmx_check_guest_state(vcpu, vmcs12, &exit_qual))
+ nested_vmx_check_guest_state(vcpu, vmcs12, &ignored))
goto error_guest_mode;
vmx->nested.dirty_vmcs12 = true;
@@ -5778,7 +6326,7 @@
return ret;
}
-void nested_vmx_vcpu_setup(void)
+void nested_vmx_set_vmcs_shadowing_bitmap(void)
{
if (enable_shadow_vmcs) {
vmcs_write64(VMREAD_BITMAP, __pa(vmx_vmread_bitmap));
@@ -5809,7 +6357,7 @@
* reason is that if one of these bits is necessary, it will appear
* in vmcs01 and prepare_vmcs02, when it bitwise-or's the control
* fields of vmcs01 and vmcs02, will turn these bits off - and
- * nested_vmx_exit_reflected() will not pass related exits to L1.
+ * nested_vmx_l1_wants_exit() will not pass related exits to L1.
* These rules have exceptions below.
*/
@@ -5839,7 +6387,8 @@
#ifdef CONFIG_X86_64
VM_EXIT_HOST_ADDR_SPACE_SIZE |
#endif
- VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT;
+ VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
+ VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
msrs->exit_ctls_high |=
VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
@@ -5858,7 +6407,8 @@
#ifdef CONFIG_X86_64
VM_ENTRY_IA32E_MODE |
#endif
- VM_ENTRY_LOAD_IA32_PAT;
+ VM_ENTRY_LOAD_IA32_PAT | VM_ENTRY_LOAD_BNDCFGS |
+ VM_ENTRY_LOAD_IA32_PERF_GLOBAL_CTRL;
msrs->entry_ctls_high |=
(VM_ENTRY_ALWAYSON_WITHOUT_TRUE_MSR | VM_ENTRY_LOAD_IA32_EFER);
@@ -5872,8 +6422,8 @@
msrs->procbased_ctls_low =
CPU_BASED_ALWAYSON_WITHOUT_TRUE_MSR;
msrs->procbased_ctls_high &=
- CPU_BASED_VIRTUAL_INTR_PENDING |
- CPU_BASED_VIRTUAL_NMI_PENDING | CPU_BASED_USE_TSC_OFFSETING |
+ CPU_BASED_INTR_WINDOW_EXITING |
+ CPU_BASED_NMI_WINDOW_EXITING | CPU_BASED_USE_TSC_OFFSETTING |
CPU_BASED_HLT_EXITING | CPU_BASED_INVLPG_EXITING |
CPU_BASED_MWAIT_EXITING | CPU_BASED_CR3_LOAD_EXITING |
CPU_BASED_CR3_STORE_EXITING |
@@ -5901,7 +6451,8 @@
/*
* secondary cpu-based controls. Do not include those that
- * depend on CPUID bits, they are added later by vmx_cpuid_update.
+ * depend on CPUID bits, they are added later by
+ * vmx_vcpu_after_set_cpuid.
*/
if (msrs->procbased_ctls_high & CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)
rdmsr(MSR_IA32_VMX_PROCBASED_CTLS2,
@@ -5911,7 +6462,7 @@
msrs->secondary_ctls_low = 0;
msrs->secondary_ctls_high &=
SECONDARY_EXEC_DESC |
- SECONDARY_EXEC_RDTSCP |
+ SECONDARY_EXEC_ENABLE_RDTSCP |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
SECONDARY_EXEC_WBINVD_EXITING |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -5932,11 +6483,13 @@
/* nested EPT: emulate EPT also to L1 */
msrs->secondary_ctls_high |=
SECONDARY_EXEC_ENABLE_EPT;
- msrs->ept_caps = VMX_EPT_PAGE_WALK_4_BIT |
- VMX_EPTP_WB_BIT | VMX_EPT_INVEPT_BIT;
- if (cpu_has_vmx_ept_execute_only())
- msrs->ept_caps |=
- VMX_EPT_EXECUTE_ONLY_BIT;
+ msrs->ept_caps =
+ VMX_EPT_PAGE_WALK_4_BIT |
+ VMX_EPT_PAGE_WALK_5_BIT |
+ VMX_EPTP_WB_BIT |
+ VMX_EPT_INVEPT_BIT |
+ VMX_EPT_EXECUTE_ONLY_BIT;
+
msrs->ept_caps &= ept_caps;
msrs->ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT |
VMX_EPT_EXTENT_CONTEXT_BIT | VMX_EPT_2MB_PAGE_BIT |
@@ -6058,25 +6611,30 @@
init_vmcs_shadow_fields();
}
- exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear,
- exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch,
- exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld,
- exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst,
- exit_handlers[EXIT_REASON_VMREAD] = handle_vmread,
- exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume,
- exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite,
- exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff,
- exit_handlers[EXIT_REASON_VMON] = handle_vmon,
- exit_handlers[EXIT_REASON_INVEPT] = handle_invept,
- exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid,
- exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc,
-
- kvm_x86_ops->check_nested_events = vmx_check_nested_events;
- kvm_x86_ops->get_nested_state = vmx_get_nested_state;
- kvm_x86_ops->set_nested_state = vmx_set_nested_state;
- kvm_x86_ops->get_vmcs12_pages = nested_get_vmcs12_pages,
- kvm_x86_ops->nested_enable_evmcs = nested_enable_evmcs;
- kvm_x86_ops->nested_get_evmcs_version = nested_get_evmcs_version;
+ exit_handlers[EXIT_REASON_VMCLEAR] = handle_vmclear;
+ exit_handlers[EXIT_REASON_VMLAUNCH] = handle_vmlaunch;
+ exit_handlers[EXIT_REASON_VMPTRLD] = handle_vmptrld;
+ exit_handlers[EXIT_REASON_VMPTRST] = handle_vmptrst;
+ exit_handlers[EXIT_REASON_VMREAD] = handle_vmread;
+ exit_handlers[EXIT_REASON_VMRESUME] = handle_vmresume;
+ exit_handlers[EXIT_REASON_VMWRITE] = handle_vmwrite;
+ exit_handlers[EXIT_REASON_VMOFF] = handle_vmoff;
+ exit_handlers[EXIT_REASON_VMON] = handle_vmon;
+ exit_handlers[EXIT_REASON_INVEPT] = handle_invept;
+ exit_handlers[EXIT_REASON_INVVPID] = handle_invvpid;
+ exit_handlers[EXIT_REASON_VMFUNC] = handle_vmfunc;
return 0;
}
+
+struct kvm_x86_nested_ops vmx_nested_ops = {
+ .leave_nested = vmx_leave_nested,
+ .check_events = vmx_check_nested_events,
+ .hv_timer_pending = nested_vmx_preemption_timer_pending,
+ .get_state = vmx_get_nested_state,
+ .set_state = vmx_set_nested_state,
+ .get_nested_state_pages = vmx_get_nested_state_pages,
+ .write_log_dirty = nested_vmx_write_pml_buffer,
+ .enable_evmcs = nested_enable_evmcs,
+ .get_evmcs_version = nested_get_evmcs_version,
+};