[PATCH] KVM: guest_memfd(): protect kvm_mmu_invalidate_end()

[Isaku Yamahata]

kvm_mmu_invalidate_end() updates struct kvm::mmu_invalidate_in_progress
and it's protected by kvm::mmu_lock.  call kvm_mmu_invalidate_end() before
unlocking it. Not after the unlock.

Fixes: edd048ffeaf6 ("KVM: Introduce per-page memory attributes")
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
 virt/kvm/kvm_main.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 9b4759b6dd87..6947f776851b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -548,6 +548,7 @@ struct kvm_mmu_notifier_range {
 	} arg;
 	gfn_handler_t handler;
 	on_lock_fn_t on_lock;
+	on_unlock_fn_t before_unlock;
 	on_unlock_fn_t on_unlock;
 	bool flush_on_ret;
 	bool may_block;
@@ -644,6 +645,8 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
 		kvm_flush_remote_tlbs(kvm);
 
 	if (locked) {
+		if (!IS_KVM_NULL_FN(range->before_unlock))
+			range->before_unlock(kvm);
 		KVM_MMU_UNLOCK(kvm);
 		if (!IS_KVM_NULL_FN(range->on_unlock))
 			range->on_unlock(kvm);
@@ -668,6 +671,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
 		.arg.pte	= pte,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.before_unlock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= true,
 		.may_block	= false,
@@ -687,6 +691,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn
 		.end		= end,
 		.handler	= handler,
 		.on_lock	= (void *)kvm_null_fn,
+		.before_unlock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= false,
@@ -791,6 +796,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= kvm_mmu_unmap_gfn_range,
 		.on_lock	= kvm_mmu_invalidate_begin,
+		.before_unlock	= (void *)kvm_null_fn,
 		.on_unlock	= kvm_arch_guest_memory_reclaimed,
 		.flush_on_ret	= true,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -830,6 +836,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 
 void kvm_mmu_invalidate_end(struct kvm *kvm)
 {
+	lockdep_assert_held_write(&kvm->mmu_lock);
+
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -861,6 +869,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 		.end		= range->end,
 		.handler	= (void *)kvm_null_fn,
 		.on_lock	= kvm_mmu_invalidate_end,
+		.before_unlock	= (void *)kvm_null_fn,
 		.on_unlock	= (void *)kvm_null_fn,
 		.flush_on_ret	= false,
 		.may_block	= mmu_notifier_range_blockable(range),
@@ -2466,6 +2475,8 @@ static __always_inline void kvm_handle_gfn_range(struct kvm *kvm,
 		kvm_flush_remote_tlbs(kvm);
 
 	if (locked) {
+		if (!IS_KVM_NULL_FN(range->before_unlock))
+			range->before_unlock(kvm);
 		KVM_MMU_UNLOCK(kvm);
 		if (!IS_KVM_NULL_FN(range->on_unlock))
 			range->on_unlock(kvm);
@@ -2480,6 +2491,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, unsigned long attributes,
 		.end = end,
 		.handler = kvm_mmu_unmap_gfn_range,
 		.on_lock = kvm_mmu_invalidate_begin,
+		.before_unlock	= (void *)kvm_null_fn,
 		.on_unlock = (void *)kvm_null_fn,
 		.flush_on_ret = true,
 		.may_block = true,
@@ -2490,7 +2502,8 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, unsigned long attributes,
 		.arg.attributes = attributes,
 		.handler = kvm_arch_post_set_memory_attributes,
 		.on_lock = (void *)kvm_null_fn,
-		.on_unlock = kvm_mmu_invalidate_end,
+		.before_unlock = kvm_mmu_invalidate_end,
+		.on_unlock = (void *)kvm_null_fn,
 		.may_block = true,
 	};
 	unsigned long i;
-- 
2.25.1


-- 
Isaku Yamahata <isaku.yamahata@xxxxxxxxx>