KVM: Move MMU notifier's mmu_lock acquisition into common helper

Acquire and release mmu_lock in the __kvm_handle_hva_range() helper
instead of requiring the caller to do the same.  This paves the way for
future patches to take mmu_lock if and only if an overlapping memslot is
found, without also having to introduce the on_lock() shenanigans used
to manipulate the notifier count and sequence.

No functional change intended.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-Id: <20210402005658.3024832-8-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

1 files changed, 80 insertions, 41 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d4c249719a56..e768b862cbd9 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -453,28 +453,57 @@ static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
 
 typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
 
+typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
+			     unsigned long end);
+
 struct kvm_hva_range {
 	unsigned long start;
 	unsigned long end;
 	pte_t pte;
 	hva_handler_t handler;
+	on_lock_fn_t on_lock;
 	bool flush_on_ret;
 	bool may_block;
 };
 
+/*
+ * Use a dedicated stub instead of NULL to indicate that there is no callback
+ * function/handler.  The compiler technically can't guarantee that a real
+ * function will have a non-zero address, and so it will generate code to
+ * check for !NULL, whereas comparing against a stub will be elided at compile
+ * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
+ */
+static void kvm_null_fn(void)
+{
+
+}
+#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
+
 static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 						  const struct kvm_hva_range *range)
 {
+	struct kvm_gfn_range gfn_range;
 	struct kvm_memory_slot *slot;
 	struct kvm_memslots *slots;
-	struct kvm_gfn_range gfn_range;
 	bool ret = false;
 	int i, idx;
 
-	lockdep_assert_held_write(&kvm->mmu_lock);
+	/* A null handler is allowed if and only if on_lock() is provided. */
+	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
+			 IS_KVM_NULL_FN(range->handler)))
+		return 0;
+
+	KVM_MMU_LOCK(kvm);
 
 	idx = srcu_read_lock(&kvm->srcu);
 
+	if (!IS_KVM_NULL_FN(range->on_lock)) {
+		range->on_lock(kvm, range->start, range->end);
+
+		if (IS_KVM_NULL_FN(range->handler))
+			goto out_unlock;
+	}
+
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		slots = __kvm_memslots(kvm, i);
 		kvm_for_each_memslot(slot, slots) {
@@ -510,6 +539,9 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 	if (range->flush_on_ret && (ret || kvm->tlbs_dirty))
 		kvm_flush_remote_tlbs(kvm);
 
+out_unlock:
+	KVM_MMU_UNLOCK(kvm);
+
 	srcu_read_unlock(&kvm->srcu, idx);
 
 	/* The notifiers are averse to booleans. :-( */
@@ -528,16 +560,12 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.end		= end,
 		.pte		= pte,
 		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
 	};
-	int ret;
 
-	KVM_MMU_LOCK(kvm);
-	ret = __kvm_handle_hva_range(kvm, &range);
-	KVM_MMU_UNLOCK(kvm);
-
-	return ret;
+	return __kvm_handle_hva_range(kvm, &range);
 }
 
 static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
@@ -551,16 +579,12 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.end		= end,
 		.pte		= __pte(0),
 		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
 	};
-	int ret;
-
-	KVM_MMU_LOCK(kvm);
-	ret = __kvm_handle_hva_range(kvm, &range);
-	KVM_MMU_UNLOCK(kvm);
 
-	return ret;
+	return __kvm_handle_hva_range(kvm, &range);
 }
 static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 					struct mm_struct *mm,
@@ -581,22 +605,9 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
 	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
 }
 
-static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
-					const struct mmu_notifier_range *range)
+static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	const struct kvm_hva_range hva_range = {
-		.start		= range->start,
-		.end		= range->end,
-		.pte		= __pte(0),
-		.handler	= kvm_unmap_gfn_range,
-		.flush_on_ret	= true,
-		.may_block	= mmu_notifier_range_blockable(range),
-	};
-
-	trace_kvm_unmap_hva_range(range->start, range->end);
-
-	KVM_MMU_LOCK(kvm);
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
@@ -604,8 +615,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 */
 	kvm->mmu_notifier_count++;
 	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = range->start;
-		kvm->mmu_notifier_range_end = range->end;
+		kvm->mmu_notifier_range_start = start;
+		kvm->mmu_notifier_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has dimishing
@@ -617,24 +628,36 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		 * complete.
 		 */
 		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, range->start);
+			min(kvm->mmu_notifier_range_start, start);
 		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, range->end);
+			max(kvm->mmu_notifier_range_end, end);
 	}
+}
 
-	__kvm_handle_hva_range(kvm, &hva_range);
+static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
+					const struct mmu_notifier_range *range)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= kvm_unmap_gfn_range,
+		.on_lock	= kvm_inc_notifier_count,
+		.flush_on_ret	= true,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
 
-	KVM_MMU_UNLOCK(kvm);
+	trace_kvm_unmap_hva_range(range->start, range->end);
+
+	__kvm_handle_hva_range(kvm, &hva_range);
 
 	return 0;
 }
 
-static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
-					const struct mmu_notifier_range *range)
+static void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-
-	KVM_MMU_LOCK(kvm);
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -648,7 +671,23 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 * in conjunction with the smp_rmb in mmu_notifier_retry().
 	 */
 	kvm->mmu_notifier_count--;
-	KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+					const struct mmu_notifier_range *range)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= (void *)kvm_null_fn,
+		.on_lock	= kvm_dec_notifier_count,
+		.flush_on_ret	= false,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
+
+	__kvm_handle_hva_range(kvm, &hva_range);
 
 	BUG_ON(kvm->mmu_notifier_count < 0);
 }