Re: [PATCH v9 7/8] KVM: Handle page fault for private memory

[Ackerley Tng]

> A memslot with KVM_MEM_PRIVATE being set can include both fd-based
> private memory and hva-based shared memory. Architecture code (like TDX
> code) can tell whether the on-going fault is private or not. This patch
> adds a 'is_private' field to kvm_page_fault to indicate this and
> architecture code is expected to set it.
>
> To handle page fault for such memslot, the handling logic is different
> depending on whether the fault is private or shared. KVM checks if
> 'is_private' matches the host's view of the page (maintained in
> mem_attr_array).
>   - For a successful match, private pfn is obtained with
>     restrictedmem_get_page () from private fd and shared pfn is obtained
>     with existing get_user_pages().
>   - For a failed match, KVM causes a KVM_EXIT_MEMORY_FAULT exit to
>     userspace. Userspace then can convert memory between private/shared
>     in host's view and retry the fault.
>
> Co-developed-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
> Signed-off-by: Yu Zhang <yu.c.zhang@xxxxxxxxxxxxxxx>
> Signed-off-by: Chao Peng <chao.p.peng@xxxxxxxxxxxxxxx>
> ---
>  arch/x86/kvm/mmu/mmu.c          | 56 +++++++++++++++++++++++++++++++--
>  arch/x86/kvm/mmu/mmu_internal.h | 14 ++++++++-
>  arch/x86/kvm/mmu/mmutrace.h     |  1 +
>  arch/x86/kvm/mmu/spte.h         |  6 ++++
>  arch/x86/kvm/mmu/tdp_mmu.c      |  3 +-
>  include/linux/kvm_host.h        | 28 +++++++++++++++++
>  6 files changed, 103 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index 67a9823a8c35..10017a9f26ee 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3030,7 +3030,7 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
>
>  int kvm_mmu_max_mapping_level(struct kvm *kvm,
>  			      const struct kvm_memory_slot *slot, gfn_t gfn,
> -			      int max_level)
> +			      int max_level, bool is_private)
>  {
>  	struct kvm_lpage_info *linfo;
>  	int host_level;
> @@ -3042,6 +3042,9 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm,
>  			break;
>  	}
>
> +	if (is_private)
> +		return max_level;
> +
>  	if (max_level == PG_LEVEL_4K)
>  		return PG_LEVEL_4K;
>
> @@ -3070,7 +3073,8 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
>  	 * level, which will be used to do precise, accurate accounting.
>  	 */
>  	fault->req_level = kvm_mmu_max_mapping_level(vcpu->kvm, slot,
> -						     fault->gfn, fault->max_level);
> +						     fault->gfn, fault->max_level,
> +						     fault->is_private);
>  	if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed)
>  		return;
>
> @@ -4141,6 +4145,32 @@ void kvm_arch_async_page_ready(struct kvm_vcpu *vcpu, struct kvm_async_pf *work)
>  	kvm_mmu_do_page_fault(vcpu, work->cr2_or_gpa, 0, true);
>  }
>
> +static inline u8 order_to_level(int order)
> +{
> +	BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G);
> +
> +	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G))
> +		return PG_LEVEL_1G;
> +
> +	if (order >= KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M))
> +		return PG_LEVEL_2M;
> +
> +	return PG_LEVEL_4K;
> +}
> +
> +static int kvm_faultin_pfn_private(struct kvm_page_fault *fault)
>  +{
>  +	int order;
>  +	struct kvm_memory_slot *slot = fault->slot;
>  +
>  +	if (kvm_restricted_mem_get_pfn(slot, fault->gfn, &fault->pfn, &order))
>+		return RET_PF_RETRY;
>+
>+	fault->max_level = min(order_to_level(order), fault->max_level);
>+	fault->map_writable = !(slot->flags & KVM_MEM_READONLY);
>+	return RET_PF_CONTINUE;
>+}
>+
> static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> {
> 	struct kvm_memory_slot *slot = fault->slot;
>@@ -4173,6 +4203,22 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> 			return RET_PF_EMULATE;
> 	}
>
>+	if (kvm_slot_can_be_private(slot) &&
>+	    fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) {
>+		vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
>+		if (fault->is_private)
>+			vcpu->run->memory.flags = KVM_MEMORY_EXIT_FLAG_PRIVATE;
>+		else
>+			vcpu->run->memory.flags = 0;
>+		vcpu->run->memory.padding = 0;
>+		vcpu->run->memory.gpa = fault->gfn << PAGE_SHIFT;
>+		vcpu->run->memory.size = PAGE_SIZE;
>+		return RET_PF_USER;
>+	}
>+
>+	if (fault->is_private)
>+		return kvm_faultin_pfn_private(fault);
>+

Since each memslot may also not be backed by restricted memory, we
should also check if the memslot has been set up for private memory
with

	if (fault->is_private && kvm_slot_can_be_private(slot))
		return kvm_faultin_pfn_private(fault);

Without this check, restrictedmem_get_page will get called with NULL
in slot->restricted_file, which causes a NULL pointer dereference.

> 	async = false;
> 	fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, &async,
> 					  fault->write, &fault->map_writable,
>@@ -5557,6 +5603,9 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err
> 			return -EIO;
> 	}
>
>+	if (r == RET_PF_USER)
>+		return 0;
>+
> 	if (r < 0)
> 		return r;
> 	if (r != RET_PF_EMULATE)
>@@ -6408,7 +6457,8 @@ static bool kvm_mmu_zap_collapsible_spte(struct kvm *kvm,
> 		 */
> 		if (sp->role.direct &&
> 		    sp->role.level < kvm_mmu_max_mapping_level(kvm, slot, sp->gfn,
>-							       PG_LEVEL_NUM)) {
>+							       PG_LEVEL_NUM,
>+							       false)) {
> 			kvm_zap_one_rmap_spte(kvm, rmap_head, sptep);
>
> 			if (kvm_available_flush_tlb_with_range())