Re: [PATCH RFC 04/10] KVM: Refactor kvm_handle_hva_range() to avoid conditional mmu_lock

[Sean Christopherson]

On Thu, Sep 10, 2026, Marco Elver wrote:
> Refactor kvm_handle_hva_range() to check for overlapping memslots
> upfront via interval_tree_iter_first() instead of tracking found
> memslots inside the range iteration with a 'found_memslot' flag and
> conditionally acquiring and releasing mmu_lock.
> 
> This simplifies the control flow by cleanly decoupling the search for
> overlapping memslots from the subsequent walk. It also separates the
> lockless path from the serialized path into distinct branches,
> eliminating the conditional locking, which subsequently enables Clang
> context analysis to validate locking in this function.

At the cost of duplicating code and adding overhead when there is a relevant
memslot.  I'm not wedded to the exact implementation, but IMO this is not at all
an improvement.  Without a clear explanation of what value is added by enabling
Clang to "validate locking", I don't see any justificatoin for the change.

> No functional change intended.
> 
> Signed-off-by: Marco Elver <elver@xxxxxxxxxx>
> ---
>  virt/kvm/kvm_main.c | 94 ++++++++++++++++++++++++++++-----------------
>  1 file changed, 58 insertions(+), 36 deletions(-)
> 
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 65eb26a0520d..f7bfa2d32507 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -558,31 +558,14 @@ static void kvm_null_fn(void)
>  	     node;							     \
>  	     node = interval_tree_iter_next(node, start, last))	     \
>  
> -static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
> -							 const struct kvm_mmu_notifier_range *range)
> +static __always_inline bool __kvm_handle_hva_range_walk(struct kvm *kvm,
> +							const struct kvm_mmu_notifier_range *range)
>  {
> -	struct kvm_mmu_notifier_return r = {
> -		.ret = false,
> -		.found_memslot = false,
> -	};
>  	struct kvm_gfn_range gfn_range;
>  	struct kvm_memory_slot *slot;
>  	struct kvm_memslots *slots;
> -	int i, idx;
> -
> -	if (WARN_ON_ONCE(range->end <= range->start))
> -		return r;
> -
> -	/* 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 r;
> -
> -	/* on_lock will never be called for lockless walks */
> -	if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock)))
> -		return r;
> -
> -	idx = srcu_read_lock(&kvm->srcu);
> +	bool ret = false;
> +	int i;
>  
>  	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
>  		struct interval_tree_node *node;
> @@ -620,28 +603,67 @@ static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
>  			gfn_range.slot = slot;
>  			gfn_range.lockless = range->lockless;
>  
> -			if (!r.found_memslot) {
> -				r.found_memslot = true;
> -				if (!range->lockless) {
> -					KVM_MMU_LOCK(kvm);
> -					if (!IS_KVM_NULL_FN(range->on_lock))
> -						range->on_lock(kvm);
> +			ret |= range->handler(kvm, &gfn_range);
> +		}
> +	}
> +
> +	return ret;
> +}
>  
> -					if (IS_KVM_NULL_FN(range->handler))
> -						goto mmu_unlock;
> -				}
> -			}
> -			r.ret |= range->handler(kvm, &gfn_range);
> +static __always_inline kvm_mn_ret_t kvm_handle_hva_range(struct kvm *kvm,
> +							 const struct kvm_mmu_notifier_range *range)
> +{
> +	struct kvm_mmu_notifier_return r = {
> +		.ret = false,
> +		.found_memslot = false,
> +	};
> +	struct kvm_memslots *slots;
> +	int i, idx;
> +
> +	if (WARN_ON_ONCE(range->end <= range->start))
> +		return r;
> +
> +	/* 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 r;
> +
> +	/* on_lock will never be called for lockless walks */
> +	if (WARN_ON_ONCE(range->lockless && !IS_KVM_NULL_FN(range->on_lock)))
> +		return r;
> +
> +	idx = srcu_read_lock(&kvm->srcu);
> +
> +	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
> +		slots = __kvm_memslots(kvm, i);
> +		if (interval_tree_iter_first(&slots->hva_tree, range->start, range->end - 1)) {
> +			r.found_memslot = true;
> +			break;
>  		}
>  	}
>  
> -	if (range->flush_on_ret && r.ret)
> -		kvm_flush_remote_tlbs(kvm);
> +	if (!r.found_memslot)
> +		goto out;
> +
> +	if (range->lockless) {
> +		r.ret = __kvm_handle_hva_range_walk(kvm, range);
> +		if (range->flush_on_ret && r.ret)
> +			kvm_flush_remote_tlbs(kvm);
> +	} else {
> +		KVM_MMU_LOCK(kvm);
> +		if (!IS_KVM_NULL_FN(range->on_lock))
> +			range->on_lock(kvm);
> +
> +		if (!IS_KVM_NULL_FN(range->handler))
> +			r.ret = __kvm_handle_hva_range_walk(kvm, range);
> +
> +		if (range->flush_on_ret && r.ret)
> +			kvm_flush_remote_tlbs(kvm);
>  
> -mmu_unlock:
> -	if (r.found_memslot && !range->lockless)
>  		KVM_MMU_UNLOCK(kvm);
> +	}
>  
> +out:
>  	srcu_read_unlock(&kvm->srcu, idx);
>  
>  	return r;
> -- 
> 2.55.0.1003.g10538fe699-goog
>