Re: [PATCH v2 03/16] KVM: arm64: Turn kvm_pgtable_stage2_set_owner into kvm_pgtable_stage2_annotate

[Andrew Jones <drjones@redhat.com>]

On Mon, Oct 04, 2021 at 06:48:36PM +0100, Marc Zyngier wrote:
> kvm_pgtable_stage2_set_owner() could be generalised into a way
> to store up to 63 bits in the page tables, as long as we don't
> set bit 0.
> 
> Let's just do that.
> 
> Signed-off-by: Marc Zyngier <maz@kernel.org>
> ---
>  arch/arm64/include/asm/kvm_pgtable.h          | 12 ++++++-----
>  arch/arm64/kvm/hyp/include/nvhe/mem_protect.h |  2 +-
>  arch/arm64/kvm/hyp/nvhe/mem_protect.c         | 11 ++++------
>  arch/arm64/kvm/hyp/nvhe/setup.c               | 10 +++++++++-
>  arch/arm64/kvm/hyp/pgtable.c                  | 20 ++++++-------------
>  5 files changed, 27 insertions(+), 28 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/kvm_pgtable.h b/arch/arm64/include/asm/kvm_pgtable.h
> index 027783829584..d4d3ae0b5edb 100644
> --- a/arch/arm64/include/asm/kvm_pgtable.h
> +++ b/arch/arm64/include/asm/kvm_pgtable.h
> @@ -329,14 +329,16 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  			   void *mc);
>  
>  /**
> - * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to
> - *				    track ownership.
> + * kvm_pgtable_stage2_annotate() - Unmap and annotate pages in the IPA space
> + *				   to track ownership (and more).
>   * @pgt:	Page-table structure initialised by kvm_pgtable_stage2_init*().
>   * @addr:	Base intermediate physical address to annotate.
>   * @size:	Size of the annotated range.
>   * @mc:		Cache of pre-allocated and zeroed memory from which to allocate
>   *		page-table pages.
> - * @owner_id:	Unique identifier for the owner of the page.
> + * @annotation:	A 63 bit value that will be stored in the page tables.
> + *		@annotation[0] must be 0, and @annotation[63:1] is stored
> + *		in the page tables.
>   *
>   * By default, all page-tables are owned by identifier 0. This function can be
>   * used to mark portions of the IPA space as owned by other entities. When a
> @@ -345,8 +347,8 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>   *
>   * Return: 0 on success, negative error code on failure.
>   */
> -int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
> -				 void *mc, u8 owner_id);
> +int kvm_pgtable_stage2_annotate(struct kvm_pgtable *pgt, u64 addr, u64 size,
> +				void *mc, kvm_pte_t annotation);
>  
>  /**
>   * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table.
> diff --git a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> index b58c910babaf..9d2ca173ea9a 100644
> --- a/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> +++ b/arch/arm64/kvm/hyp/include/nvhe/mem_protect.h
> @@ -53,7 +53,7 @@ int __pkvm_host_share_hyp(u64 pfn);
>  
>  bool addr_is_memory(phys_addr_t phys);
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size, enum kvm_pgtable_prot prot);
> -int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id);
> +int host_stage2_annotate_locked(phys_addr_t addr, u64 size, kvm_pte_t owner_id);
>  int kvm_host_prepare_stage2(void *pgt_pool_base);
>  void handle_host_mem_abort(struct kvm_cpu_context *host_ctxt);
>  
> diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> index bacd493a4eac..8cd0c3bdb911 100644
> --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c
> @@ -286,17 +286,14 @@ static int host_stage2_adjust_range(u64 addr, struct kvm_mem_range *range)
>  int host_stage2_idmap_locked(phys_addr_t addr, u64 size,
>  			     enum kvm_pgtable_prot prot)
>  {
> -	hyp_assert_lock_held(&host_kvm.lock);
> -
>  	return host_stage2_try(__host_stage2_idmap, addr, addr + size, prot);
>  }
>  
> -int host_stage2_set_owner_locked(phys_addr_t addr, u64 size, u8 owner_id)
> +int host_stage2_annotate_locked(phys_addr_t addr, u64 size,
> +				kvm_pte_t annotation)
>  {
> -	hyp_assert_lock_held(&host_kvm.lock);

Hi Marc,

Why are the lock asserts getting dropped?

> -
> -	return host_stage2_try(kvm_pgtable_stage2_set_owner, &host_kvm.pgt,
> -			       addr, size, &host_s2_pool, owner_id);
> +	return host_stage2_try(kvm_pgtable_stage2_annotate, &host_kvm.pgt,
> +			       addr, size, &host_s2_pool, annotation);
>  }
>  
>  static bool host_stage2_force_pte_cb(u64 addr, u64 end, enum kvm_pgtable_prot prot)
> diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c
> index 57c27846320f..d489fb9b8c29 100644
> --- a/arch/arm64/kvm/hyp/nvhe/setup.c
> +++ b/arch/arm64/kvm/hyp/nvhe/setup.c
> @@ -159,6 +159,13 @@ static void hpool_put_page(void *addr)
>  	hyp_put_page(&hpool, addr);
>  }
>  
> +#define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
> +
> +static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
> +{
> +	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
> +}
> +
>  static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
>  					 kvm_pte_t *ptep,
>  					 enum kvm_pgtable_walk_flags flag,
> @@ -186,7 +193,8 @@ static int finalize_host_mappings_walker(u64 addr, u64 end, u32 level,
>  	state = pkvm_getstate(kvm_pgtable_hyp_pte_prot(pte));
>  	switch (state) {
>  	case PKVM_PAGE_OWNED:
> -		return host_stage2_set_owner_locked(phys, PAGE_SIZE, pkvm_hyp_id);
> +		return host_stage2_annotate_locked(phys, PAGE_SIZE,
> +						   kvm_init_invalid_leaf_owner(pkvm_hyp_id));
>  	case PKVM_PAGE_SHARED_OWNED:
>  		prot = pkvm_mkstate(PKVM_HOST_MEM_PROT, PKVM_PAGE_SHARED_BORROWED);
>  		break;
> diff --git a/arch/arm64/kvm/hyp/pgtable.c b/arch/arm64/kvm/hyp/pgtable.c
> index 6bbfd952f0c5..4201e512da48 100644
> --- a/arch/arm64/kvm/hyp/pgtable.c
> +++ b/arch/arm64/kvm/hyp/pgtable.c
> @@ -46,9 +46,6 @@
>  					 KVM_PTE_LEAF_ATTR_LO_S2_S2AP_W | \
>  					 KVM_PTE_LEAF_ATTR_HI_S2_XN)
>  
> -#define KVM_INVALID_PTE_OWNER_MASK	GENMASK(9, 2)
> -#define KVM_MAX_OWNER_ID		1
> -
>  struct kvm_pgtable_walk_data {
>  	struct kvm_pgtable		*pgt;
>  	struct kvm_pgtable_walker	*walker;
> @@ -167,11 +164,6 @@ static kvm_pte_t kvm_init_valid_leaf_pte(u64 pa, kvm_pte_t attr, u32 level)
>  	return pte;
>  }
>  
> -static kvm_pte_t kvm_init_invalid_leaf_owner(u8 owner_id)
> -{
> -	return FIELD_PREP(KVM_INVALID_PTE_OWNER_MASK, owner_id);
> -}
> -
>  static int kvm_pgtable_visitor_cb(struct kvm_pgtable_walk_data *data, u64 addr,
>  				  u32 level, kvm_pte_t *ptep,
>  				  enum kvm_pgtable_walk_flags flag)
> @@ -503,7 +495,7 @@ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt)
>  struct stage2_map_data {
>  	u64				phys;
>  	kvm_pte_t			attr;
> -	u8				owner_id;
> +	u64				annotation;
>  
>  	kvm_pte_t			*anchor;
>  	kvm_pte_t			*childp;
> @@ -670,7 +662,7 @@ static int stage2_map_walker_try_leaf(u64 addr, u64 end, u32 level,
>  	if (kvm_phys_is_valid(phys))
>  		new = kvm_init_valid_leaf_pte(phys, data->attr, level);
>  	else
> -		new = kvm_init_invalid_leaf_owner(data->owner_id);
> +		new = data->annotation;
>  
>  	if (stage2_pte_is_counted(old)) {
>  		/*
> @@ -859,8 +851,8 @@ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  	return ret;
>  }
>  
> -int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
> -				 void *mc, u8 owner_id)
> +int kvm_pgtable_stage2_annotate(struct kvm_pgtable *pgt, u64 addr, u64 size,
> +				void *mc, kvm_pte_t annotation)
>  {
>  	int ret;
>  	struct stage2_map_data map_data = {
> @@ -868,8 +860,8 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  		.mmu		= pgt->mmu,
>  		.memcache	= mc,
>  		.mm_ops		= pgt->mm_ops,
> -		.owner_id	= owner_id,
>  		.force_pte	= true,
> +		.annotation	= annotation,
>  	};
>  	struct kvm_pgtable_walker walker = {
>  		.cb		= stage2_map_walker,
> @@ -879,7 +871,7 @@ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size,
>  		.arg		= &map_data,
>  	};
>  
> -	if (owner_id > KVM_MAX_OWNER_ID)
> +	if (annotation & PTE_VALID)
>  		return -EINVAL;
>  
>  	ret = kvm_pgtable_walk(pgt, addr, size, &walker);
> -- 
> 2.30.2
>

Thanks,
drew