[PATCH v2 3/3] KVM: x86/mmu: Don't allow TDP MMU to yield when recovering NX pages

[Sean Christopherson <seanjc@google.com>]

Prevent the TDP MMU from yielding when zapping a gfn range during NX
page recovery.  If a flush is pending from a previous invocation of the
zapping helper, either in the TDP MMU or the legacy MMU, but the TDP MMU
has not accumulated a flush for the current invocation, then yielding
will release mmu_lock with stale TLB entriesr

That being said, this isn't technically a bug fix in the current code, as
the TDP MMU will never yield in this case.  tdp_mmu_iter_cond_resched()
will yield if and only if it has made forward progress, as defined by the
current gfn vs. the last yielded (or starting) gfn.  Because zapping a
single shadow page is guaranteed to (a) find that page and (b) step
sideways at the level of the shadow page, the TDP iter will break its loop
before getting a chance to yield.

But that is all very, very subtle, and will break at the slightest sneeze,
e.g. zapping while holding mmu_lock for read would break as the TDP MMU
wouldn't be guaranteed to see the present shadow page, and thus could step
sideways at a lower level.

Cc: Ben Gardon <bgardon@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/mmu/mmu.c     |  4 +---
 arch/x86/kvm/mmu/tdp_mmu.c |  5 +++--
 arch/x86/kvm/mmu/tdp_mmu.h | 23 ++++++++++++++++++++++-
 3 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 5a53743b37bc..7a99e59c8c1c 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5940,7 +5940,6 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 	unsigned int ratio;
 	LIST_HEAD(invalid_list);
 	bool flush = false;
-	gfn_t gfn_end;
 	ulong to_zap;
 
 	rcu_idx = srcu_read_lock(&kvm->srcu);
@@ -5962,8 +5961,7 @@ static void kvm_recover_nx_lpages(struct kvm *kvm)
 				      lpage_disallowed_link);
 		WARN_ON_ONCE(!sp->lpage_disallowed);
 		if (is_tdp_mmu_page(sp)) {
-			gfn_end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
-			flush = kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, gfn_end);
+			flush = kvm_tdp_mmu_zap_sp(kvm, sp);
 		} else {
 			kvm_mmu_prepare_zap_page(kvm, sp, &invalid_list);
 			WARN_ON_ONCE(sp->lpage_disallowed);
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6cf08c3c537f..08667e3cf091 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -709,13 +709,14 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
  * SPTEs have been cleared and a TLB flush is needed before releasing the
  * MMU lock.
  */
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end)
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield)
 {
 	struct kvm_mmu_page *root;
 	bool flush = false;
 
 	for_each_tdp_mmu_root_yield_safe(kvm, root)
-		flush = zap_gfn_range(kvm, root, start, end, true, flush);
+		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
 
 	return flush;
 }
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 3b761c111bff..715aa4e0196d 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -8,7 +8,28 @@
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
 void kvm_tdp_mmu_free_root(struct kvm *kvm, struct kvm_mmu_page *root);
 
-bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end);
+bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start, gfn_t end,
+				 bool can_yield);
+static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, gfn_t start,
+					     gfn_t end)
+{
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, start, end, true);
+}
+static inline bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
+{
+	gfn_t end = sp->gfn + KVM_PAGES_PER_HPAGE(sp->role.level);
+
+	/*
+	 * Don't allow yielding, as the caller may have a flush pending.  Note,
+	 * if mmu_lock is held for write, zapping will never yield in this case,
+	 * but explicitly disallow it for safety.  The TDP MMU does not yield
+	 * until it has made forward progress (steps sideways), and when zapping
+	 * a single shadow page that it's guaranteed to see (thus the mmu_lock
+	 * requirement), its "step sideways" will always step beyond the bounds
+	 * of the shadow page's gfn range and stop iterating before yielding.
+	 */
+	return __kvm_tdp_mmu_zap_gfn_range(kvm, sp->gfn, end, false);
+}
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 
 int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
-- 
2.31.0.291.g576ba9dcdaf-goog