KVM: X86: Don't unsync pagetables when speculative

We'd better only unsync the pagetable when there just was a really
write fault on a level-1 pagetable.

Signed-off-by: Lai Jiangshan <laijs@linux.alibaba.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210918005636.3675-10-jiangshanlai@gmail.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index ccfcdc0..73aa15e 100644 (file)
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -2582,7 +2582,8 @@ static void kvm_unsync_page(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
  * were marked unsync (or if there is no shadow page), -EPERM if the SPTE must
  * be write-protected.
  */
-int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
+int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync,
+                           bool speculative)
 {
        struct kvm_mmu_page *sp;
        bool locked = false;
@@ -2608,6 +2609,9 @@ int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync)
                if (sp->unsync)
                        continue;
 
+               if (speculative)
+                       return -EEXIST;
+
                /*
                 * TDP MMU page faults require an additional spinlock as they
                 * run with mmu_lock held for read, not write, and the unsync

diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index bf2bdbf..2ba12ef 100644 (file)
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -124,7 +124,8 @@ static inline bool is_nx_huge_page_enabled(void)
        return READ_ONCE(nx_huge_pages);
 }
 
-int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync);
+int mmu_try_to_unsync_pages(struct kvm_vcpu *vcpu, gfn_t gfn, bool can_unsync,
+                           bool speculative);
 
 void kvm_mmu_gfn_disallow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);
 void kvm_mmu_gfn_allow_lpage(const struct kvm_memory_slot *slot, gfn_t gfn);

diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 3e97cdb..b68a580 100644 (file)
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -159,7 +159,7 @@ int make_spte(struct kvm_vcpu *vcpu, unsigned int pte_access, int level,
                 * e.g. it's write-tracked (upper-level SPs) or has one or more
                 * shadow pages and unsync'ing pages is not allowed.
                 */
-               if (mmu_try_to_unsync_pages(vcpu, gfn, can_unsync)) {
+               if (mmu_try_to_unsync_pages(vcpu, gfn, can_unsync, speculative)) {
                        pgprintk("%s: found shadow page for %llx, marking ro\n",
                                 __func__, gfn);
                        ret |= SET_SPTE_WRITE_PROTECTED_PT;