Message ID | 20230914015531.1419405-19-seanjc@google.com (mailing list archive) |
---|---|
State | New, archived |
Headers | show |
Series | KVM: guest_memfd() and per-page attributes | expand |
On Wed, Sep 13, 2023 at 06:55:16PM -0700, Sean Christopherson wrote: .... > +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, > + struct kvm_page_fault *fault) > +{ > + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, > + PAGE_SIZE, fault->write, fault->exec, > + fault->is_private); > +} > + > +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, > + struct kvm_page_fault *fault) > +{ > + int max_order, r; > + > + if (!kvm_slot_can_be_private(fault->slot)) { > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > + return -EFAULT; > + } > + > + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, > + &max_order); > + if (r) { > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > + return r; > + } > + > + fault->max_level = min(kvm_max_level_for_order(max_order), > + fault->max_level); > + fault->map_writable = !(fault->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; > @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault > return RET_PF_EMULATE; > } > > + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { In patch 21, fault->is_private is set as: ".is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT)", then, the inequality here means memory attribute has been updated after last check. So, why an exit to user space for converting is required instead of a mere retry? Or, is it because how .is_private is assigned in patch 21 is subjected to change in future? > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > + return -EFAULT; > + } > + > + if (fault->is_private) > + return kvm_faultin_pfn_private(vcpu, fault); > + > async = false; > fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, > fault->write, &fault->map_writable, > @@ -7184,6 +7255,19 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) > } >
On Fri, Sep 15, 2023, Yan Zhao wrote: > On Wed, Sep 13, 2023 at 06:55:16PM -0700, Sean Christopherson wrote: > .... > > +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, > > + struct kvm_page_fault *fault) > > +{ > > + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, > > + PAGE_SIZE, fault->write, fault->exec, > > + fault->is_private); > > +} > > + > > +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, > > + struct kvm_page_fault *fault) > > +{ > > + int max_order, r; > > + > > + if (!kvm_slot_can_be_private(fault->slot)) { > > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > > + return -EFAULT; > > + } > > + > > + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, > > + &max_order); > > + if (r) { > > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > > + return r; > > + } > > + > > + fault->max_level = min(kvm_max_level_for_order(max_order), > > + fault->max_level); > > + fault->map_writable = !(fault->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; > > @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault > > return RET_PF_EMULATE; > > } > > > > + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { > In patch 21, > fault->is_private is set as: > ".is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT)", > then, the inequality here means memory attribute has been updated after > last check. > So, why an exit to user space for converting is required instead of a mere retry? > > Or, is it because how .is_private is assigned in patch 21 is subjected to change > in future? This. Retrying on SNP or TDX would hang the guest. I suppose we could special case VMs where .is_private is derived from the memory attributes, but the SW_PROTECTED_VM type is primary a development vehicle at this point. I'd like to have it mimic SNP/TDX as much as possible; performance is a secondary concern. E.g. userspace needs to be prepared for "spurious" exits due to races on SNP and TDX, which this can theoretically exercise. Though the window is quite small so I doubt that'll actually happen in practice; which of course also makes it less important to retry instead of exiting.
On Fri, Sep 15, 2023 at 07:26:16AM -0700, Sean Christopherson wrote: > On Fri, Sep 15, 2023, Yan Zhao wrote: > > On Wed, Sep 13, 2023 at 06:55:16PM -0700, Sean Christopherson wrote: > > .... > > > +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, > > > + struct kvm_page_fault *fault) > > > +{ > > > + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, > > > + PAGE_SIZE, fault->write, fault->exec, > > > + fault->is_private); > > > +} > > > + > > > +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, > > > + struct kvm_page_fault *fault) > > > +{ > > > + int max_order, r; > > > + > > > + if (!kvm_slot_can_be_private(fault->slot)) { > > > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > > > + return -EFAULT; > > > + } > > > + > > > + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, > > > + &max_order); > > > + if (r) { > > > + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); > > > + return r; > > > + } > > > + > > > + fault->max_level = min(kvm_max_level_for_order(max_order), > > > + fault->max_level); > > > + fault->map_writable = !(fault->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; > > > @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault > > > return RET_PF_EMULATE; > > > } > > > > > > + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { > > In patch 21, > > fault->is_private is set as: > > ".is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT)", > > then, the inequality here means memory attribute has been updated after > > last check. > > So, why an exit to user space for converting is required instead of a mere retry? > > > > Or, is it because how .is_private is assigned in patch 21 is subjected to change > > in future? > > This. Retrying on SNP or TDX would hang the guest. I suppose we could special Is this because if the guest access a page in private way (e.g. via private key in TDX), the returned page must be a private page? > case VMs where .is_private is derived from the memory attributes, but the > SW_PROTECTED_VM type is primary a development vehicle at this point. I'd like to > have it mimic SNP/TDX as much as possible; performance is a secondary concern. Ok. But this mimic is somewhat confusing as it may be problematic in below scenario, though sane guest should ensure no one is accessing a page before doing memory conversion. CPU 0 CPU 1 access GFN A in private way fault->is_private=true convert GFN A to shared set memory attribute of A to shared faultin, mismatch and exit set memory attribute of A to private vCPU access GFN A in shared way fault->is_private = true faultin, match and map a private PFN B vCPU accesses private PFN B in shared way > > E.g. userspace needs to be prepared for "spurious" exits due to races on SNP and > TDX, which this can theoretically exercise. Though the window is quite small so > I doubt that'll actually happen in practice; which of course also makes it less > important to retry instead of exiting.
On 9/15/2023 10:26 PM, Sean Christopherson wrote: > On Fri, Sep 15, 2023, Yan Zhao wrote: >> On Wed, Sep 13, 2023 at 06:55:16PM -0700, Sean Christopherson wrote: >> .... >>> +static void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, >>> + struct kvm_page_fault *fault) >>> +{ >>> + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, >>> + PAGE_SIZE, fault->write, fault->exec, >>> + fault->is_private); >>> +} >>> + >>> +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, >>> + struct kvm_page_fault *fault) >>> +{ >>> + int max_order, r; >>> + >>> + if (!kvm_slot_can_be_private(fault->slot)) { >>> + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); >>> + return -EFAULT; >>> + } >>> + >>> + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, >>> + &max_order); >>> + if (r) { >>> + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); >>> + return r; >>> + } >>> + >>> + fault->max_level = min(kvm_max_level_for_order(max_order), >>> + fault->max_level); >>> + fault->map_writable = !(fault->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; >>> @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault >>> return RET_PF_EMULATE; >>> } >>> >>> + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { >> In patch 21, >> fault->is_private is set as: >> ".is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT)", >> then, the inequality here means memory attribute has been updated after >> last check. >> So, why an exit to user space for converting is required instead of a mere retry? >> >> Or, is it because how .is_private is assigned in patch 21 is subjected to change >> in future? > This. Retrying on SNP or TDX would hang the guest. I suppose we could special > case VMs where .is_private is derived from the memory attributes, but the > SW_PROTECTED_VM type is primary a development vehicle at this point. I'd like to > have it mimic SNP/TDX as much as possible; performance is a secondary concern. So when .is_private is derived from the memory attributes, and if I didn't miss anything, there is no explicit conversion mechanism introduced yet so far, does it mean for pure sw-protected VM (withouth SNP/TDX), the page fault will be handled according to the memory attributes setup by host/user vmm, no implicit conversion will be triggered, right? > > E.g. userspace needs to be prepared for "spurious" exits due to races on SNP and > TDX, which this can theoretically exercise. Though the window is quite small so > I doubt that'll actually happen in practice; which of course also makes it less > important to retry instead of exiting.
On Mon, Sep 18, 2023, Yan Zhao wrote: > On Fri, Sep 15, 2023 at 07:26:16AM -0700, Sean Christopherson wrote: > > On Fri, Sep 15, 2023, Yan Zhao wrote: > > > > static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) > > > > { > > > > struct kvm_memory_slot *slot = fault->slot; > > > > @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault > > > > return RET_PF_EMULATE; > > > > } > > > > > > > > + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { > > > In patch 21, > > > fault->is_private is set as: > > > ".is_private = kvm_mem_is_private(vcpu->kvm, cr2_or_gpa >> PAGE_SHIFT)", > > > then, the inequality here means memory attribute has been updated after > > > last check. > > > So, why an exit to user space for converting is required instead of a mere retry? > > > > > > Or, is it because how .is_private is assigned in patch 21 is subjected to change > > > in future? > > > > This. Retrying on SNP or TDX would hang the guest. I suppose we could special > Is this because if the guest access a page in private way (e.g. via > private key in TDX), the returned page must be a private page? Yes, the returned page must be private, because the GHCI (TDX) and GHCB (SNP) require that the host allow implicit conversions. I.e. if the guest accesses memory as private (or shared), then the host must map memory as private (or shared). Simply resuming the guest will not change the guest access, nor will it change KVM's memory attributes. Ideally (IMO), implicit conversions would be disallowed, but even if implicit conversions weren't a thing, retrying would still be wrong as KVM would either inject an exception into the guest or exit to userspace to let userspace handle the illegal access. > > case VMs where .is_private is derived from the memory attributes, but the > > SW_PROTECTED_VM type is primary a development vehicle at this point. I'd like to > > have it mimic SNP/TDX as much as possible; performance is a secondary concern. > Ok. But this mimic is somewhat confusing as it may be problematic in below scenario, > though sane guest should ensure no one is accessing a page before doing memory > conversion. > > > CPU 0 CPU 1 > access GFN A in private way > fault->is_private=true > convert GFN A to shared > set memory attribute of A to shared > > faultin, mismatch and exit > set memory attribute of A > to private > > vCPU access GFN A in shared way > fault->is_private = true > faultin, match and map a private PFN B > > vCPU accesses private PFN B in shared way If this is a TDX or SNP VM, then the private vs. shared information comes from the guest itself, e.g. this sequence vCPU access GFN A in shared way fault->is_private = true cannot happen because is_private will be false based on the error code (SNP) or the GPA (TDX). And when hardware doesn't generate page faults based on private vs. shared, i.e. for non-TDX/SNP VMs, from a fault handling perspective there is no concept of the guest accessing a GFN in a "private way" or a "shared way". I.e. there are no implicit conversions. For SEV and SEV-ES, the guest can access memory as private vs. shared, but the and the host VMM absolutely must be in agreement and synchronized with respect to the state of a page, otherwise guest memory will be corrupted. But that has nothing to do with the fault handling, e.g. creating aliases in the guest to access a single GFN as shared and private from two CPUs will create incoherent cache entries and/or corrupt data without any involvement from KVM. In other words, the above isn't possible for TDX/SNP, and for all other types, the conflict between CPU0 and CPU1 is unequivocally a guest bug.
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a079f36a8bf5..9b48d8d0300b 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3147,9 +3147,9 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn, return level; } -int kvm_mmu_max_mapping_level(struct kvm *kvm, - const struct kvm_memory_slot *slot, gfn_t gfn, - int max_level) +static int __kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, + gfn_t gfn, int max_level, bool is_private) { struct kvm_lpage_info *linfo; int host_level; @@ -3161,6 +3161,9 @@ 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; @@ -3168,6 +3171,16 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, return min(host_level, max_level); } +int kvm_mmu_max_mapping_level(struct kvm *kvm, + const struct kvm_memory_slot *slot, gfn_t gfn, + int max_level) +{ + bool is_private = kvm_slot_can_be_private(slot) && + kvm_mem_is_private(kvm, gfn); + + return __kvm_mmu_max_mapping_level(kvm, slot, gfn, max_level, is_private); +} + void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { struct kvm_memory_slot *slot = fault->slot; @@ -3188,8 +3201,9 @@ void kvm_mmu_hugepage_adjust(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault * Enforce the iTLB multihit workaround after capturing the requested * 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->req_level = __kvm_mmu_max_mapping_level(vcpu->kvm, slot, + fault->gfn, fault->max_level, + fault->is_private); if (fault->req_level == PG_LEVEL_4K || fault->huge_page_disallowed) return; @@ -4261,6 +4275,55 @@ 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, NULL); } +static inline u8 kvm_max_level_for_order(int order) +{ + BUILD_BUG_ON(KVM_MAX_HUGEPAGE_LEVEL > PG_LEVEL_1G); + + KVM_MMU_WARN_ON(order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_1G) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_2M) && + order != KVM_HPAGE_GFN_SHIFT(PG_LEVEL_4K)); + + 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 void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + kvm_prepare_memory_fault_exit(vcpu, fault->gfn << PAGE_SHIFT, + PAGE_SIZE, fault->write, fault->exec, + fault->is_private); +} + +static int kvm_faultin_pfn_private(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + int max_order, r; + + if (!kvm_slot_can_be_private(fault->slot)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + r = kvm_gmem_get_pfn(vcpu->kvm, fault->slot, fault->gfn, &fault->pfn, + &max_order); + if (r) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return r; + } + + fault->max_level = min(kvm_max_level_for_order(max_order), + fault->max_level); + fault->map_writable = !(fault->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; @@ -4293,6 +4356,14 @@ static int __kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault return RET_PF_EMULATE; } + if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + kvm_mmu_prepare_memory_fault_exit(vcpu, fault); + return -EFAULT; + } + + if (fault->is_private) + return kvm_faultin_pfn_private(vcpu, fault); + async = false; fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, false, false, &async, fault->write, &fault->map_writable, @@ -7184,6 +7255,19 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) } #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range) +{ + /* + * KVM x86 currently only supports KVM_MEMORY_ATTRIBUTE_PRIVATE, skip + * the slot if the slot will never consume the PRIVATE attribute. + */ + if (!kvm_slot_can_be_private(range->slot)) + return false; + + return kvm_mmu_unmap_gfn_range(kvm, range); +} + static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b102014e2c60..4efbf43b4b18 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -202,6 +202,7 @@ struct kvm_page_fault { /* Derived from mmu and global state. */ const bool is_tdp; + const bool is_private; const bool nx_huge_page_workaround_enabled; /*