Re: [PATCH v4 18/30] KVM: x86/mmu: Zap only TDP MMU leafs in kvm_zap_gfn_range()

[Mingwei Zhang <mizhang@google.com>]

On Thu, Mar 03, 2022, Paolo Bonzini wrote:
> From: Sean Christopherson <seanjc@google.com>
> 
> Zap only leaf SPTEs in the TDP MMU's zap_gfn_range(), and rename various
> functions accordingly.  When removing mappings for functional correctness
> (except for the stupid VFIO GPU passthrough memslots bug), zapping the
> leaf SPTEs is sufficient as the paging structures themselves do not point
> at guest memory and do not directly impact the final translation (in the
> TDP MMU).
> 
> Note, this aligns the TDP MMU with the legacy/full MMU, which zaps only
> the rmaps, a.k.a. leaf SPTEs, in kvm_zap_gfn_range() and
> kvm_unmap_gfn_range().
> 
> Signed-off-by: Sean Christopherson <seanjc@google.com>
> Reviewed-by: Ben Gardon <bgardon@google.com>
> Message-Id: <20220226001546.360188-18-seanjc@google.com>
> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
> ---
>  arch/x86/kvm/mmu/mmu.c     |  4 ++--
>  arch/x86/kvm/mmu/tdp_mmu.c | 41 ++++++++++----------------------------
>  arch/x86/kvm/mmu/tdp_mmu.h |  8 +-------
>  3 files changed, 14 insertions(+), 39 deletions(-)
> 
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 8408d7db8d2a..febdcaaa7b94 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -5834,8 +5834,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
>  
>  	if (is_tdp_mmu_enabled(kvm)) {
>  		for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
> -			flush = kvm_tdp_mmu_zap_gfn_range(kvm, i, gfn_start,
> -							  gfn_end, flush);
> +			flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
> +						      gfn_end, true, flush);
>  	}
>  
>  	if (flush)
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
> index f3939ce4a115..c71debdbc732 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.c
> +++ b/arch/x86/kvm/mmu/tdp_mmu.c
> @@ -834,10 +834,8 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
>  }
>  
>  /*
> - * Tears down the mappings for the range of gfns, [start, end), and frees the
> - * non-root pages mapping GFNs strictly within that range. Returns true if
> - * SPTEs have been cleared and a TLB flush is needed before releasing the
> - * MMU lock.
> + * Zap leafs SPTEs for the range of gfns, [start, end). Returns true if SPTEs
> + * have been cleared and a TLB flush is needed before releasing the MMU lock.

I think the original code does not _over_ zapping. But the new version
does. Will that have some side effects? In particular, if the range is
within a huge page (or HugeTLB page of various sizes), then we choose to
zap it even if it is more than the range.

Regardless of side effect, I think we probably should mention that in
the comments?

>   *
>   * If can_yield is true, will release the MMU lock and reschedule if the
>   * scheduler needs the CPU or there is contention on the MMU lock. If this
> @@ -845,42 +843,25 @@ bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp)
>   * the caller must ensure it does not supply too large a GFN range, or the
>   * operation can cause a soft lockup.
>   */
> -static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
> -			  gfn_t start, gfn_t end, bool can_yield, bool flush)
> +static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
> +			      gfn_t start, gfn_t end, bool can_yield, bool flush)
>  {
> -	bool zap_all = (start == 0 && end >= tdp_mmu_max_gfn_host());
>  	struct tdp_iter iter;
>  
> -	/*
> -	 * No need to try to step down in the iterator when zapping all SPTEs,
> -	 * zapping the top-level non-leaf SPTEs will recurse on their children.
> -	 */
> -	int min_level = zap_all ? root->role.level : PG_LEVEL_4K;
> -
>  	end = min(end, tdp_mmu_max_gfn_host());
>  
>  	lockdep_assert_held_write(&kvm->mmu_lock);
>  
>  	rcu_read_lock();
>  
> -	for_each_tdp_pte_min_level(iter, root, min_level, start, end) {
> +	for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) {
>  		if (can_yield &&
>  		    tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) {
>  			flush = false;
>  			continue;
>  		}
>  
> -		if (!is_shadow_present_pte(iter.old_spte))
> -			continue;
> -
> -		/*
> -		 * If this is a non-last-level SPTE that covers a larger range
> -		 * than should be zapped, continue, and zap the mappings at a
> -		 * lower level, except when zapping all SPTEs.
> -		 */
> -		if (!zap_all &&
> -		    (iter.gfn < start ||
> -		     iter.gfn + KVM_PAGES_PER_HPAGE(iter.level) > end) &&
> +		if (!is_shadow_present_pte(iter.old_spte) ||
>  		    !is_last_spte(iter.old_spte, iter.level))
>  			continue;
>  
> @@ -898,13 +879,13 @@ static bool zap_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
>   * SPTEs have been cleared and a TLB flush is needed before releasing the
>   * MMU lock.
>   */
> -bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
> -				 gfn_t end, bool can_yield, bool flush)
> +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
> +			   bool can_yield, bool flush)
>  {
>  	struct kvm_mmu_page *root;
>  
>  	for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
> -		flush = zap_gfn_range(kvm, root, start, end, can_yield, flush);
> +		flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, false);
>  
>  	return flush;
>  }
> @@ -1202,8 +1183,8 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
>  bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
>  				 bool flush)
>  {
> -	return __kvm_tdp_mmu_zap_gfn_range(kvm, range->slot->as_id, range->start,
> -					   range->end, range->may_block, flush);
> +	return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
> +				     range->end, range->may_block, flush);
>  }
>  
>  typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
> diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
> index 5e5ef2576c81..54bc8118c40a 100644
> --- a/arch/x86/kvm/mmu/tdp_mmu.h
> +++ b/arch/x86/kvm/mmu/tdp_mmu.h
> @@ -15,14 +15,8 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
>  void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
>  			  bool shared);
>  
> -bool __kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id, gfn_t start,
> +bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
>  				 gfn_t end, bool can_yield, bool flush);
> -static inline bool kvm_tdp_mmu_zap_gfn_range(struct kvm *kvm, int as_id,
> -					     gfn_t start, gfn_t end, bool flush)
> -{
> -	return __kvm_tdp_mmu_zap_gfn_range(kvm, as_id, start, end, true, flush);
> -}
> -
>  bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
>  void kvm_tdp_mmu_zap_all(struct kvm *kvm);
>  void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
> -- 
> 2.31.1
> 
>