KVM: x86/mmu: Add support for lockless walks of rmap SPTEs

Add a lockless version of for_each_rmap_spte(), which is pretty much the
same as the normal version, except that it doesn't BUG() the host if a
non-present SPTE is encountered.  When mmu_lock is held, it should be
impossible for a different task to zap a SPTE, _and_ zapped SPTEs must
be removed from their rmap chain prior to dropping mmu_lock.  Thus, the
normal walker BUG()s if a non-present SPTE is encountered as something is
wildly broken.

When walking rmaps without holding mmu_lock, the SPTEs pointed at by the
rmap chain can be zapped/dropped, and so a lockless walk can observe a
non-present SPTE if it runs concurrently with a different operation that
is zapping SPTEs.

Signed-off-by: James Houghton <jthoughton@google.com>
Link: https://lore.kernel.org/r/20250204004038.1680123-11-jthoughton@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

Author: sean-jc

arch/x86/kvm/mmu/mmu.c

@@ -876,7 +876,7 @@ static struct kvm_memory_slot *gfn_to_memslot_dirty_bitmap(struct kvm_vcpu *vcpu
  */
 #define KVM_RMAP_LOCKED	BIT(1)
 
-static unsigned long kvm_rmap_lock(struct kvm_rmap_head *rmap_head)
+static unsigned long __kvm_rmap_lock(struct kvm_rmap_head *rmap_head)
 {
 	unsigned long old_val, new_val;
 
@@ -914,7 +914,7 @@ static unsigned long kvm_rmap_lock(struct kvm_rmap_head *rmap_head)
 	/*
 	 * Use try_cmpxchg_acquire() to prevent reads and writes to the rmap
 	 * from being reordered outside of the critical section created by
-	 * kvm_rmap_lock().
+	 * __kvm_rmap_lock().
 	 *
 	 * Pairs with the atomic_long_set_release() in kvm_rmap_unlock().
 	 *
@@ -923,39 +923,92 @@ static unsigned long kvm_rmap_lock(struct kvm_rmap_head *rmap_head)
 	 */
 	} while (!atomic_long_try_cmpxchg_acquire(&rmap_head->val, &old_val, new_val));
 
-	/* Return the old value, i.e. _without_ the LOCKED bit set. */
+	/*
+	 * Return the old value, i.e. _without_ the LOCKED bit set.  It's
+	 * impossible for the return value to be 0 (see above), i.e. the read-
+	 * only unlock flow can't get a false positive and fail to unlock.
+	 */
 	return old_val;
 }
 
-static void kvm_rmap_unlock(struct kvm_rmap_head *rmap_head,
-			    unsigned long new_val)
+static unsigned long kvm_rmap_lock(struct kvm *kvm,
+				   struct kvm_rmap_head *rmap_head)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	return __kvm_rmap_lock(rmap_head);
+}
+
+static void __kvm_rmap_unlock(struct kvm_rmap_head *rmap_head,
+			      unsigned long val)
 {
-	WARN_ON_ONCE(new_val & KVM_RMAP_LOCKED);
+	KVM_MMU_WARN_ON(val & KVM_RMAP_LOCKED);
 	/*
 	 * Ensure that all accesses to the rmap have completed before unlocking
 	 * the rmap.
 	 *
-	 * Pairs with the atomic_long_try_cmpxchg_acquire() in kvm_rmap_lock.
+	 * Pairs with the atomic_long_try_cmpxchg_acquire() in __kvm_rmap_lock().
 	 */
-	atomic_long_set_release(&rmap_head->val, new_val);
+	atomic_long_set_release(&rmap_head->val, val);
+}
+
+static void kvm_rmap_unlock(struct kvm *kvm,
+			    struct kvm_rmap_head *rmap_head,
+			    unsigned long new_val)
+{
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
+	__kvm_rmap_unlock(rmap_head, new_val);
 }
 
 static unsigned long kvm_rmap_get(struct kvm_rmap_head *rmap_head)
 {
 	return atomic_long_read(&rmap_head->val) & ~KVM_RMAP_LOCKED;
 }
 
+/*
+ * If mmu_lock isn't held, rmaps can only be locked in read-only mode.  The
+ * actual locking is the same, but the caller is disallowed from modifying the
+ * rmap, and so the unlock flow is a nop if the rmap is/was empty.
+ */
+__maybe_unused
+static unsigned long kvm_rmap_lock_readonly(struct kvm_rmap_head *rmap_head)
+{
+	unsigned long rmap_val;
+
+	preempt_disable();
+	rmap_val = __kvm_rmap_lock(rmap_head);
+
+	if (!rmap_val)
+		preempt_enable();
+
+	return rmap_val;
+}
+
+__maybe_unused
+static void kvm_rmap_unlock_readonly(struct kvm_rmap_head *rmap_head,
+				     unsigned long old_val)
+{
+	if (!old_val)
+		return;
+
+	KVM_MMU_WARN_ON(old_val != kvm_rmap_get(rmap_head));
+
+	__kvm_rmap_unlock(rmap_head, old_val);
+	preempt_enable();
+}
+
 /*
  * Returns the number of pointers in the rmap chain, not counting the new one.
  */
-static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
-			struct kvm_rmap_head *rmap_head)
+static int pte_list_add(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
+			u64 *spte, struct kvm_rmap_head *rmap_head)
 {
 	unsigned long old_val, new_val;
 	struct pte_list_desc *desc;
 	int count = 0;
 
-	old_val = kvm_rmap_lock(rmap_head);
+	old_val = kvm_rmap_lock(kvm, rmap_head);
 
 	if (!old_val) {
 		new_val = (unsigned long)spte;
@@ -987,7 +1040,7 @@ static int pte_list_add(struct kvm_mmu_memory_cache *cache, u64 *spte,
 		desc->sptes[desc->spte_count++] = spte;
 	}
 
-	kvm_rmap_unlock(rmap_head, new_val);
+	kvm_rmap_unlock(kvm, rmap_head, new_val);
 
 	return count;
 }
@@ -1035,7 +1088,7 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 	unsigned long rmap_val;
 	int i;
 
-	rmap_val = kvm_rmap_lock(rmap_head);
+	rmap_val = kvm_rmap_lock(kvm, rmap_head);
 	if (KVM_BUG_ON_DATA_CORRUPTION(!rmap_val, kvm))
 		goto out;
 
@@ -1061,7 +1114,7 @@ static void pte_list_remove(struct kvm *kvm, u64 *spte,
 	}
 
 out:
-	kvm_rmap_unlock(rmap_head, rmap_val);
+	kvm_rmap_unlock(kvm, rmap_head, rmap_val);
 }
 
 static void kvm_zap_one_rmap_spte(struct kvm *kvm,
@@ -1079,7 +1132,7 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
 	unsigned long rmap_val;
 	int i;
 
-	rmap_val = kvm_rmap_lock(rmap_head);
+	rmap_val = kvm_rmap_lock(kvm, rmap_head);
 	if (!rmap_val)
 		return false;
 
@@ -1098,7 +1151,7 @@ static bool kvm_zap_all_rmap_sptes(struct kvm *kvm,
 	}
 out:
 	/* rmap_head is meaningless now, remember to reset it */
-	kvm_rmap_unlock(rmap_head, 0);
+	kvm_rmap_unlock(kvm, rmap_head, 0);
 	return true;
 }
 
@@ -1171,23 +1224,18 @@ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
 			   struct rmap_iterator *iter)
 {
 	unsigned long rmap_val = kvm_rmap_get(rmap_head);
-	u64 *sptep;
 
 	if (!rmap_val)
 		return NULL;
 
 	if (!(rmap_val & KVM_RMAP_MANY)) {
 		iter->desc = NULL;
-		sptep = (u64 *)rmap_val;
-		goto out;
+		return (u64 *)rmap_val;
 	}
 
 	iter->desc = (struct pte_list_desc *)(rmap_val & ~KVM_RMAP_MANY);
 	iter->pos = 0;
-	sptep = iter->desc->sptes[iter->pos];
-out:
-	BUG_ON(!is_shadow_present_pte(*sptep));
-	return sptep;
+	return iter->desc->sptes[iter->pos];
 }
 
 /*
@@ -1197,35 +1245,36 @@ static u64 *rmap_get_first(struct kvm_rmap_head *rmap_head,
  */
 static u64 *rmap_get_next(struct rmap_iterator *iter)
 {
-	u64 *sptep;
-
 	if (iter->desc) {
 		if (iter->pos < PTE_LIST_EXT - 1) {
 			++iter->pos;
-			sptep = iter->desc->sptes[iter->pos];
-			if (sptep)
-				goto out;
+			if (iter->desc->sptes[iter->pos])
+				return iter->desc->sptes[iter->pos];
 		}
 
 		iter->desc = iter->desc->more;
 
 		if (iter->desc) {
 			iter->pos = 0;
 			/* desc->sptes[0] cannot be NULL */
-			sptep = iter->desc->sptes[iter->pos];
-			goto out;
+			return iter->desc->sptes[iter->pos];
 		}
 	}
 
 	return NULL;
-out:
-	BUG_ON(!is_shadow_present_pte(*sptep));
-	return sptep;
 }
 
-#define for_each_rmap_spte(_rmap_head_, _iter_, _spte_)			\
-	for (_spte_ = rmap_get_first(_rmap_head_, _iter_);		\
-	     _spte_; _spte_ = rmap_get_next(_iter_))
+#define __for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)	\
+	for (_sptep_ = rmap_get_first(_rmap_head_, _iter_);	\
+	     _sptep_; _sptep_ = rmap_get_next(_iter_))
+
+#define for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+	__for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+		if (!WARN_ON_ONCE(!is_shadow_present_pte(*(_sptep_))))	\
+
+#define for_each_rmap_spte_lockless(_rmap_head_, _iter_, _sptep_, _spte_)	\
+	__for_each_rmap_spte(_rmap_head_, _iter_, _sptep_)			\
+		if (is_shadow_present_pte(_spte_ = mmu_spte_get_lockless(sptep)))
 
 static void drop_spte(struct kvm *kvm, u64 *sptep)
 {
@@ -1311,12 +1360,13 @@ static bool __rmap_clear_dirty(struct kvm *kvm, struct kvm_rmap_head *rmap_head,
 	struct rmap_iterator iter;
 	bool flush = false;
 
-	for_each_rmap_spte(rmap_head, &iter, sptep)
+	for_each_rmap_spte(rmap_head, &iter, sptep) {
 		if (spte_ad_need_write_protect(*sptep))
 			flush |= test_and_clear_bit(PT_WRITABLE_SHIFT,
 						    (unsigned long *)sptep);
 		else
 			flush |= spte_clear_dirty(sptep);
+	}
 
 	return flush;
 }
@@ -1637,7 +1687,7 @@ static void __rmap_add(struct kvm *kvm,
 	kvm_update_page_stats(kvm, sp->role.level, 1);
 
 	rmap_head = gfn_to_rmap(gfn, sp->role.level, slot);
-	rmap_count = pte_list_add(cache, spte, rmap_head);
+	rmap_count = pte_list_add(kvm, cache, spte, rmap_head);
 
 	if (rmap_count > kvm->stat.max_mmu_rmap_size)
 		kvm->stat.max_mmu_rmap_size = rmap_count;
@@ -1771,13 +1821,14 @@ static unsigned kvm_page_table_hashfn(gfn_t gfn)
 	return hash_64(gfn, KVM_MMU_HASH_SHIFT);
 }
 
-static void mmu_page_add_parent_pte(struct kvm_mmu_memory_cache *cache,
+static void mmu_page_add_parent_pte(struct kvm *kvm,
+				    struct kvm_mmu_memory_cache *cache,
 				    struct kvm_mmu_page *sp, u64 *parent_pte)
 {
 	if (!parent_pte)
 		return;
 
-	pte_list_add(cache, parent_pte, &sp->parent_ptes);
+	pte_list_add(kvm, cache, parent_pte, &sp->parent_ptes);
 }
 
 static void mmu_page_remove_parent_pte(struct kvm *kvm, struct kvm_mmu_page *sp,
@@ -2467,7 +2518,7 @@ static void __link_shadow_page(struct kvm *kvm,
 
 	mmu_spte_set(sptep, spte);
 
-	mmu_page_add_parent_pte(cache, sp, sptep);
+	mmu_page_add_parent_pte(kvm, cache, sp, sptep);
 
 	/*
 	 * The non-direct sub-pagetable must be updated before linking.  For