[PATCH v9 034/105] KVM: x86/mmu: Track shadow MMIO value on a per-VM basis

From: isaku . yamahata
Date: Fri Sep 30 2022 - 06:22:21 EST


From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

TDX will use a different shadow PTE entry value for MMIO from VMX. Add
members to kvm_arch and track value for MMIO per-VM instead of global
variables. By using the per-VM EPT entry value for MMIO, the existing VMX
logic is kept working. To untangle the logic to initialize
shadow_mmio_access_mask, introduce a separate setter function.

Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
arch/x86/include/asm/kvm_host.h | 2 ++
arch/x86/kvm/mmu.h | 1 +
arch/x86/kvm/mmu/mmu.c | 7 ++++---
arch/x86/kvm/mmu/spte.c | 11 +++++++++--
arch/x86/kvm/mmu/spte.h | 4 ++--
arch/x86/kvm/mmu/tdp_mmu.c | 6 +++---
6 files changed, 21 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index fc28bf9c0552..4d4794789c42 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1165,6 +1165,8 @@ struct kvm_arch {
*/
spinlock_t mmu_unsync_pages_lock;

+ u64 shadow_mmio_value;
+
struct list_head assigned_dev_head;
struct iommu_domain *iommu_domain;
bool iommu_noncoherent;
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index 000a0a6ac815..f86fb04fb7d7 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -101,6 +101,7 @@ static inline u8 kvm_get_shadow_phys_bits(void)
}

void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value);
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ff8de361067c..fdd773ef9400 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2409,7 +2409,7 @@ static int mmu_page_zap_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
return kvm_mmu_prepare_zap_page(kvm, child,
invalid_list);
}
- } else if (is_mmio_spte(pte)) {
+ } else if (is_mmio_spte(kvm, pte)) {
mmu_spte_clear_no_track(spte);
}
return 0;
@@ -4068,7 +4068,7 @@ static int handle_mmio_page_fault(struct kvm_vcpu *vcpu, u64 addr, bool direct)
if (WARN_ON(reserved))
return -EINVAL;

- if (is_mmio_spte(spte)) {
+ if (is_mmio_spte(vcpu->kvm, spte)) {
gfn_t gfn = get_mmio_spte_gfn(spte);
unsigned int access = get_mmio_spte_access(spte);

@@ -4569,7 +4569,7 @@ static unsigned long get_cr3(struct kvm_vcpu *vcpu)
static bool sync_mmio_spte(struct kvm_vcpu *vcpu, u64 *sptep, gfn_t gfn,
unsigned int access)
{
- if (unlikely(is_mmio_spte(*sptep))) {
+ if (unlikely(is_mmio_spte(vcpu->kvm, *sptep))) {
if (gfn != get_mmio_spte_gfn(*sptep)) {
mmu_spte_clear_no_track(sptep);
return true;
@@ -6052,6 +6052,7 @@ int kvm_mmu_init_vm(struct kvm *kvm)
struct kvm_page_track_notifier_node *node = &kvm->arch.mmu_sp_tracker;
int r;

+ kvm->arch.shadow_mmio_value = shadow_mmio_value;
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
INIT_LIST_HEAD(&kvm->arch.lpage_disallowed_mmu_pages);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 5d5c06d4fd89..8f468ee2b985 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -74,10 +74,10 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
u64 spte = generation_mmio_spte_mask(gen);
u64 gpa = gfn << PAGE_SHIFT;

- WARN_ON_ONCE(!shadow_mmio_value);
+ WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);

access &= shadow_mmio_access_mask;
- spte |= shadow_mmio_value | access;
+ spte |= vcpu->kvm->arch.shadow_mmio_value | access;
spte |= gpa | shadow_nonpresent_or_rsvd_mask;
spte |= (gpa & shadow_nonpresent_or_rsvd_mask)
<< SHADOW_NONPRESENT_OR_RSVD_MASK_LEN;
@@ -352,6 +352,7 @@ u64 mark_spte_for_access_track(u64 spte)
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
{
BUG_ON((u64)(unsigned)access_mask != access_mask);
+
WARN_ON(mmio_value & shadow_nonpresent_or_rsvd_lower_gfn_mask);

/*
@@ -401,6 +402,12 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);

+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value)
+{
+ kvm->arch.shadow_mmio_value = mmio_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_value);
+
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
{
/* shadow_me_value must be a subset of shadow_me_mask */
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 7e0f79e8f45b..82f0d5c08b77 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -241,9 +241,9 @@ static inline int spte_index(u64 *sptep)
*/
extern u64 __read_mostly shadow_nonpresent_or_rsvd_lower_gfn_mask;

-static inline bool is_mmio_spte(u64 spte)
+static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
{
- return (spte & shadow_mmio_mask) == shadow_mmio_value &&
+ return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
likely(enable_mmio_caching);
}

diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index af510dd31ebc..b80422ea798d 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -569,8 +569,8 @@ static void __handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn,
* impact the guest since both the former and current SPTEs
* are nonpresent.
*/
- if (WARN_ON(!is_mmio_spte(old_spte) &&
- !is_mmio_spte(new_spte) &&
+ if (WARN_ON(!is_mmio_spte(kvm, old_spte) &&
+ !is_mmio_spte(kvm, new_spte) &&
!is_removed_spte(new_spte)))
pr_err("Unexpected SPTE change! Nonpresent SPTEs\n"
"should not be replaced with another,\n"
@@ -1094,7 +1094,7 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
}

/* If a MMIO SPTE is installed, the MMIO will need to be emulated. */
- if (unlikely(is_mmio_spte(new_spte))) {
+ if (unlikely(is_mmio_spte(vcpu->kvm, new_spte))) {
vcpu->stat.pf_mmio_spte_created++;
trace_mark_mmio_spte(rcu_dereference(iter->sptep), iter->gfn,
new_spte);
--
2.25.1