Re: [PATCH v2 6/7] KVM: mmu: Add slots_arch_lock for memslot arch fields

[Paolo Bonzini <pbonzini@redhat.com>]

On 29/04/21 23:18, Ben Gardon wrote:
> Add a new lock to protect the arch-specific fields of memslots if they
> need to be modified in a kvm->srcu read critical section. A future
> commit will use this lock to lazily allocate memslot rmaps for x86.

Here there should be a blurb about the possible races that can happen 
and why we decided for the slots_arch_lock.

> Signed-off-by: Ben Gardon <bgardon@google.com>
> ---
>   include/linux/kvm_host.h |  9 +++++++++
>   virt/kvm/kvm_main.c      | 31 ++++++++++++++++++++++++++-----
>   2 files changed, 35 insertions(+), 5 deletions(-)
> 
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 8895b95b6a22..2d5e797fbb08 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -472,6 +472,15 @@ struct kvm {
>   #endif /* KVM_HAVE_MMU_RWLOCK */
>   
>   	struct mutex slots_lock;
> +
> +	/*
> +	 * Protects the arch-specific fields of struct kvm_memory_slots in
> +	 * use by the VM. To be used under the slots_lock (above) or in a
> +	 * kvm->srcu read cirtical section where acquiring the slots_lock
> +	 * would lead to deadlock with the synchronize_srcu in
> +	 * install_new_memslots.
> +	 */

I think usage under slots_lock need not be mentioned here.  More like this:

	/*
	 * Protects the arch-specific fields of struct kvm_memory_slots
	 * in use by the VM.  Usually these are initialized by
	 * kvm_arch_prepare_memory_region and then protected by
	 * kvm->srcu; however, if they need to be initialized outside
	 * kvm_arch_prepare_memory_region, slots_arch_lock can
	 * be used instead as it is also held when calling
	 * kvm_arch_prepare_memory_region itself.  Note that using
	 * slots_lock would lead to deadlock with install_new_memslots,
	 * because it is held during synchronize_srcu:
	 *
	 *	idx = srcu_read_lock(&kvm->srcu);
	 *	mutex_lock(&kvm->slots_lock);
	 *				mutex_lock(&kvm->slots_lock);
	 *				synchronize_srcu(&kvm->srcu);
	 */

(Though a better place for this is in 
Documentation/virtual/kvm/locking.rst).

Paolo

> +	struct mutex slots_arch_lock;
>   	struct mm_struct *mm; /* userspace tied to this vm */
>   	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
>   	struct kvm_vcpu *vcpus[KVM_MAX_VCPUS];
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index c8010f55e368..97b03fa2d0c8 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -908,6 +908,7 @@ static struct kvm *kvm_create_vm(unsigned long type)
>   	mutex_init(&kvm->lock);
>   	mutex_init(&kvm->irq_lock);
>   	mutex_init(&kvm->slots_lock);
> +	mutex_init(&kvm->slots_arch_lock);
>   	INIT_LIST_HEAD(&kvm->devices);
>   
>   	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
> @@ -1280,6 +1281,10 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm,
>   	slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
>   
>   	rcu_assign_pointer(kvm->memslots[as_id], slots);
> +
> +	/* Acquired in kvm_set_memslot. */
> +	mutex_unlock(&kvm->slots_arch_lock);
> +
>   	synchronize_srcu_expedited(&kvm->srcu);
>   
>   	/*
> @@ -1351,6 +1356,9 @@ static int kvm_set_memslot(struct kvm *kvm,
>   	struct kvm_memslots *slots;
>   	int r;
>   
> +	/* Released in install_new_memslots. */
> +	mutex_lock(&kvm->slots_arch_lock);
> +
>   	slots = kvm_dup_memslots(__kvm_memslots(kvm, as_id), change);
>   	if (!slots)
>   		return -ENOMEM;
> @@ -1364,10 +1372,9 @@ static int kvm_set_memslot(struct kvm *kvm,
>   		slot->flags |= KVM_MEMSLOT_INVALID;
>   
>   		/*
> -		 * We can re-use the old memslots, the only difference from the
> -		 * newly installed memslots is the invalid flag, which will get
> -		 * dropped by update_memslots anyway.  We'll also revert to the
> -		 * old memslots if preparing the new memory region fails.
> +		 * We can re-use the memory from the old memslots.
> +		 * It will be overwritten with a copy of the new memslots
> +		 * after reacquiring the slots_arch_lock below.
>   		 */
>   		slots = install_new_memslots(kvm, as_id, slots);
>   
> @@ -1379,6 +1386,17 @@ static int kvm_set_memslot(struct kvm *kvm,
>   		 *	- kvm_is_visible_gfn (mmu_check_root)
>   		 */
>   		kvm_arch_flush_shadow_memslot(kvm, slot);
> +
> +		/* Released in install_new_memslots. */
> +		mutex_lock(&kvm->slots_arch_lock);
> +
> +		/*
> +		 * The arch-specific fields of the memslots could have changed
> +		 * between releasing the slots_arch_lock in
> +		 * install_new_memslots and here, so get a fresh copy of the
> +		 * slots.
> +		 */
> +		kvm_copy_memslots(__kvm_memslots(kvm, as_id), slots);
>   	}
>   
>   	r = kvm_arch_prepare_memory_region(kvm, new, mem, change);
> @@ -1394,8 +1412,11 @@ static int kvm_set_memslot(struct kvm *kvm,
>   	return 0;
>   
>   out_slots:
> -	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE)
> +	if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) {
> +		slot = id_to_memslot(slots, old->id);
> +		slot->flags &= ~KVM_MEMSLOT_INVALID;
>   		slots = install_new_memslots(kvm, as_id, slots);
> +	}
>   	kvfree(slots);
>   	return r;
>   }
>