From 67b43038ce14d6b0673bdffb2052d879065c94ae Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Mon, 4 Nov 2024 16:43:03 +0800 Subject: [PATCH 01/20] KVM: guest_memfd: Remove RCU-protected attribute from slot->gmem.file Remove the RCU-protected attribute from slot->gmem.file. No need to use RCU primitives rcu_assign_pointer()/synchronize_rcu() to update this pointer. - slot->gmem.file is updated in 3 places: kvm_gmem_bind(), kvm_gmem_unbind(), kvm_gmem_release(). All of them are protected by kvm->slots_lock. - slot->gmem.file is read in 2 paths: (1) kvm_gmem_populate kvm_gmem_get_file __kvm_gmem_get_pfn (2) kvm_gmem_get_pfn kvm_gmem_get_file __kvm_gmem_get_pfn Path (1) kvm_gmem_populate() requires holding kvm->slots_lock, so slot->gmem.file is protected by the kvm->slots_lock in this path. Path (2) kvm_gmem_get_pfn() does not require holding kvm->slots_lock. However, it's also not guarded by rcu_read_lock() and rcu_read_unlock(). So synchronize_rcu() in kvm_gmem_unbind()/kvm_gmem_release() actually will not wait for the readers in kvm_gmem_get_pfn() due to lack of RCU read-side critical section. The path (2) kvm_gmem_get_pfn() is safe without RCU protection because: a) kvm_gmem_bind() is called on a new memslot, before the memslot is visible to kvm_gmem_get_pfn(). b) kvm->srcu ensures that kvm_gmem_unbind() and freeing of a memslot occur after the memslot is no longer visible to kvm_gmem_get_pfn(). c) get_file_active() ensures that kvm_gmem_get_pfn() will not access the stale file if kvm_gmem_release() sets it to NULL. This is because if kvm_gmem_release() occurs before kvm_gmem_get_pfn(), get_file_active() will return NULL; if get_file_active() does not return NULL, kvm_gmem_release() should not occur until after kvm_gmem_get_pfn() releases the file reference. Signed-off-by: Yan Zhao Message-ID: <20241104084303.29909-1-yan.y.zhao@intel.com> Signed-off-by: Paolo Bonzini --- include/linux/kvm_host.h | 7 ++++++- virt/kvm/guest_memfd.c | 34 +++++++++++++++++++++------------- 2 files changed, 27 insertions(+), 14 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 401439bb21e3..9df216943eb4 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -596,7 +596,12 @@ struct kvm_memory_slot { #ifdef CONFIG_KVM_PRIVATE_MEM struct { - struct file __rcu *file; + /* + * Writes protected by kvm->slots_lock. Acquiring a + * reference via kvm_gmem_get_file() is protected by + * either kvm->slots_lock or kvm->srcu. + */ + struct file *file; pgoff_t pgoff; } gmem; #endif diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 47a9f68f7b24..18c87feaf68f 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -259,15 +259,19 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) * dereferencing the slot for existing bindings needs to be protected * against memslot updates, specifically so that unbind doesn't race * and free the memslot (kvm_gmem_get_file() will return NULL). + * + * Since .release is called only when the reference count is zero, + * after which file_ref_get() and get_file_active() fail, + * kvm_gmem_get_pfn() cannot be using the file concurrently. + * file_ref_put() provides a full barrier, and get_file_active() the + * matching acquire barrier. */ mutex_lock(&kvm->slots_lock); filemap_invalidate_lock(inode->i_mapping); xa_for_each(&gmem->bindings, index, slot) - rcu_assign_pointer(slot->gmem.file, NULL); - - synchronize_rcu(); + WRITE_ONCE(slot->gmem.file, NULL); /* * All in-flight operations are gone and new bindings can be created. @@ -296,8 +300,7 @@ static inline struct file *kvm_gmem_get_file(struct kvm_memory_slot *slot) /* * Do not return slot->gmem.file if it has already been closed; * there might be some time between the last fput() and when - * kvm_gmem_release() clears slot->gmem.file, and you do not - * want to spin in the meanwhile. + * kvm_gmem_release() clears slot->gmem.file. */ return get_file_active(&slot->gmem.file); } @@ -508,11 +511,11 @@ int kvm_gmem_bind(struct kvm *kvm, struct kvm_memory_slot *slot, } /* - * No synchronize_rcu() needed, any in-flight readers are guaranteed to - * be see either a NULL file or this new file, no need for them to go - * away. + * memslots of flag KVM_MEM_GUEST_MEMFD are immutable to change, so + * kvm_gmem_bind() must occur on a new memslot. Because the memslot + * is not visible yet, kvm_gmem_get_pfn() is guaranteed to see the file. */ - rcu_assign_pointer(slot->gmem.file, file); + WRITE_ONCE(slot->gmem.file, file); slot->gmem.pgoff = start; xa_store_range(&gmem->bindings, start, end - 1, slot, GFP_KERNEL); @@ -548,8 +551,12 @@ void kvm_gmem_unbind(struct kvm_memory_slot *slot) filemap_invalidate_lock(file->f_mapping); xa_store_range(&gmem->bindings, start, end - 1, NULL, GFP_KERNEL); - rcu_assign_pointer(slot->gmem.file, NULL); - synchronize_rcu(); + + /* + * synchronize_srcu(&kvm->srcu) ensured that kvm_gmem_get_pfn() + * cannot see this memslot. + */ + WRITE_ONCE(slot->gmem.file, NULL); filemap_invalidate_unlock(file->f_mapping); fput(file); @@ -561,11 +568,12 @@ static struct folio *__kvm_gmem_get_pfn(struct file *file, pgoff_t index, kvm_pfn_t *pfn, bool *is_prepared, int *max_order) { + struct file *gmem_file = READ_ONCE(slot->gmem.file); struct kvm_gmem *gmem = file->private_data; struct folio *folio; - if (file != slot->gmem.file) { - WARN_ON_ONCE(slot->gmem.file); + if (file != gmem_file) { + WARN_ON_ONCE(gmem_file); return ERR_PTR(-EFAULT); } From 35be969d1ef2c99a98f4b788f7839e6ee5b51ff8 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 18 Jul 2024 14:12:13 -0700 Subject: [PATCH 02/20] KVM: x86/mmu: Zap invalid roots with mmu_lock holding for write at uninit Prepare for a future TDX patch which asserts that atomic zapping (i.e. zapping with mmu_lock taken for read) don't operate on mirror roots. When tearing down a VM, all roots have to be zapped (including mirror roots once they're in place) so do that with the mmu_lock taken for write. kvm_mmu_uninit_tdp_mmu() is invoked either before or after executing any atomic operations on SPTEs by vCPU threads. Therefore, it will not impact vCPU threads performance if kvm_tdp_mmu_zap_invalidated_roots() acquires mmu_lock for write to zap invalid roots. Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-2-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/mmu/tdp_mmu.c | 16 +++++++++++----- arch/x86/kvm/mmu/tdp_mmu.h | 2 +- 3 files changed, 13 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 2401606db260..3f749fb5ec6c 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6467,7 +6467,7 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * lead to use-after-free. */ if (tdp_mmu_enabled) - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_zap_invalidated_roots(kvm, true); } void kvm_mmu_init_vm(struct kvm *kvm) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 2f15e0e33903..1054ccd9b861 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -38,7 +38,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * ultimately frees all roots. */ kvm_tdp_mmu_invalidate_all_roots(kvm); - kvm_tdp_mmu_zap_invalidated_roots(kvm); + kvm_tdp_mmu_zap_invalidated_roots(kvm, false); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); @@ -883,11 +883,14 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) * Zap all invalidated roots to ensure all SPTEs are dropped before the "fast * zap" completes. */ -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared) { struct kvm_mmu_page *root; - read_lock(&kvm->mmu_lock); + if (shared) + read_lock(&kvm->mmu_lock); + else + write_lock(&kvm->mmu_lock); for_each_tdp_mmu_root_yield_safe(kvm, root) { if (!root->tdp_mmu_scheduled_root_to_zap) @@ -905,7 +908,7 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * that may be zapped, as such entries are associated with the * ASID on both VMX and SVM. */ - tdp_mmu_zap_root(kvm, root, true); + tdp_mmu_zap_root(kvm, root, shared); /* * The referenced needs to be put *after* zapping the root, as @@ -915,7 +918,10 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) kvm_tdp_mmu_put_root(kvm, root); } - read_unlock(&kvm->mmu_lock); + if (shared) + read_unlock(&kvm->mmu_lock); + else + write_unlock(&kvm->mmu_lock); } /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index f03ca0dd13d9..6d7cdc462f58 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -23,7 +23,7 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool 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); -void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm); +void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); From dca6c88532322830d5d92486467fcc91b67a9ad8 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:14 -0700 Subject: [PATCH 03/20] KVM: Add member to struct kvm_gfn_range to indicate private/shared Add new members to strut kvm_gfn_range to indicate which mapping (private-vs-shared) to operate on: enum kvm_gfn_range_filter attr_filter. Update the core zapping operations to set them appropriately. TDX utilizes two GPA aliases for the same memslots, one for memory that is for private memory and one that is for shared. For private memory, KVM cannot always perform the same operations it does on memory for default VMs, such as zapping pages and having them be faulted back in, as this requires guest coordination. However, some operations such as guest driven conversion of memory between private and shared should zap private memory. Internally to the MMU, private and shared mappings are tracked on separate roots. Mapping and zapping operations will operate on the respective GFN alias for each root (private or shared). So zapping operations will by default zap both aliases. Add fields in struct kvm_gfn_range to allow callers to specify which aliases so they can only target the aliases appropriate for their specific operation. There was feedback that target aliases should be specified such that the default value (0) is to operate on both aliases. Several options were considered. Several variations of having separate bools defined such that the default behavior was to process both aliases. They either allowed nonsensical configurations, or were confusing for the caller. A simple enum was also explored and was close, but was hard to process in the caller. Instead, use an enum with the default value (0) reserved as a disallowed value. Catch ranges that didn't have the target aliases specified by looking for that specific value. Set target alias with enum appropriately for these MMU operations: - For KVM's mmu notifier callbacks, zap shared pages only because private pages won't have a userspace mapping - For setting memory attributes, kvm_arch_pre_set_memory_attributes() chooses the aliases based on the attribute. - For guest_memfd invalidations, zap private only. Link: https://lore.kernel.org/kvm/ZivIF9vjKcuGie3s@google.com/ Signed-off-by: Isaku Yamahata Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-3-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 6 ++++++ include/linux/kvm_host.h | 6 ++++++ virt/kvm/guest_memfd.c | 2 ++ virt/kvm/kvm_main.c | 14 ++++++++++++++ 4 files changed, 28 insertions(+) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 3f749fb5ec6c..a8f75971d3cb 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7452,6 +7452,12 @@ bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, if (WARN_ON_ONCE(!kvm_arch_has_private_mem(kvm))) return false; + /* Unmap the old attribute page. */ + if (range->arg.attributes & KVM_MEMORY_ATTRIBUTE_PRIVATE) + range->attr_filter = KVM_FILTER_SHARED; + else + range->attr_filter = KVM_FILTER_PRIVATE; + return kvm_unmap_gfn_range(kvm, range); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9df216943eb4..c788d0bd952a 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -255,11 +255,17 @@ union kvm_mmu_notifier_arg { unsigned long attributes; }; +enum kvm_gfn_range_filter { + KVM_FILTER_SHARED = BIT(0), + KVM_FILTER_PRIVATE = BIT(1), +}; + struct kvm_gfn_range { struct kvm_memory_slot *slot; gfn_t start; gfn_t end; union kvm_mmu_notifier_arg arg; + enum kvm_gfn_range_filter attr_filter; bool may_block; }; bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 18c87feaf68f..b2aa6bf24d3a 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -118,6 +118,8 @@ static void kvm_gmem_invalidate_begin(struct kvm_gmem *gmem, pgoff_t start, .end = slot->base_gfn + min(pgoff + slot->npages, end) - pgoff, .slot = slot, .may_block = true, + /* guest memfd is relevant to only private mappings. */ + .attr_filter = KVM_FILTER_PRIVATE, }; if (!found_memslot) { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index de2c11dae231..164cd4f7f8ba 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -594,6 +594,11 @@ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; + /* + * HVA-based notifications aren't relevant to private + * mappings as they don't have a userspace mapping. + */ + gfn_range.attr_filter = KVM_FILTER_SHARED; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = @@ -2408,6 +2413,14 @@ static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; + /* + * If/when KVM supports more attributes beyond private .vs shared, this + * _could_ set KVM_FILTER_{SHARED,PRIVATE} appropriately if the entire target + * range already has the desired private vs. shared state (it's unclear + * if that is a net win). For now, KVM reaches this point if and only + * if the private flag is being toggled, i.e. all mappings are in play. + */ + for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); @@ -2464,6 +2477,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, struct kvm_mmu_notifier_range pre_set_range = { .start = start, .end = end, + .arg.attributes = attributes, .handler = kvm_pre_set_memory_attributes, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, From 9364789567f9b49279b138f7d124f0c6db1d6589 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 18 Jul 2024 14:12:15 -0700 Subject: [PATCH 04/20] KVM: x86: Add a VM type define for TDX Add a VM type define for TDX. Future changes will need to lay the ground work for TDX support by making some behavior conditional on the VM being a TDX guest. Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-4-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/uapi/asm/kvm.h | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h index 88585c1de416..9e75da97bce0 100644 --- a/arch/x86/include/uapi/asm/kvm.h +++ b/arch/x86/include/uapi/asm/kvm.h @@ -925,5 +925,6 @@ struct kvm_hyperv_eventfd { #define KVM_X86_SEV_VM 2 #define KVM_X86_SEV_ES_VM 3 #define KVM_X86_SNP_VM 4 +#define KVM_X86_TDX_VM 5 #endif /* _ASM_X86_KVM_H */ From 3a4eb364a46d00b7b9f643011b4652bd7f4eecf2 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:16 -0700 Subject: [PATCH 05/20] KVM: x86/mmu: Add an external pointer to struct kvm_mmu_page Add an external pointer to struct kvm_mmu_page for TDX's private page table and add helper functions to allocate/initialize/free a private page table page. TDX will only be supported with the TDP MMU. Because KVM TDP MMU doesn't use unsync_children and write_flooding_count, pack them to have room for a pointer and use a union to avoid memory overhead. For private GPA, CPU refers to a private page table whose contents are encrypted. The dedicated APIs to operate on it (e.g. updating/reading its PTE entry) are used, and their cost is expensive. When KVM resolves the KVM page fault, it walks the page tables. To reuse the existing KVM MMU code and mitigate the heavy cost of directly walking the private page table allocate two sets of page tables for the private half of the GPA space. For the page tables that KVM will walk, allocate them like normal and refer to them as mirror page tables. Additionally allocate one more page for the page tables the CPU will walk, and call them external page tables. Resolve the KVM page fault with the existing code, and do additional operations necessary for modifying the external page table in future patches. The relationship of the types of page tables in this scheme is depicted below: KVM page fault | | | V | -------------+---------- | | | | V V | shared GPA private GPA | | | | V V | shared PT root mirror PT root | private PT root | | | | V V | V shared PT mirror PT --propagate--> external PT | | | | | \-----------------+------\ | | | | | V | V V shared guest page | private guest page | non-encrypted memory | encrypted memory | PT - Page table Shared PT - Visible to KVM, and the CPU uses it for shared mappings. External PT - The CPU uses it, but it is invisible to KVM. TDX module updates this table to map private guest pages. Mirror PT - It is visible to KVM, but the CPU doesn't use it. KVM uses it to propagate PT change to the actual private PT. Add a helper kvm_has_mirrored_tdp() to trigger this behavior and wire it to the TDX vm type. Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Reviewed-by: Binbin Wu Message-ID: <20240718211230.1492011-5-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 5 +++++ arch/x86/kvm/mmu.h | 5 +++++ arch/x86/kvm/mmu/mmu.c | 7 +++++++ arch/x86/kvm/mmu/mmu_internal.h | 31 +++++++++++++++++++++++++++---- arch/x86/kvm/mmu/tdp_mmu.c | 1 + 5 files changed, 45 insertions(+), 4 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c1251b371421..5f020b097922 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -813,6 +813,11 @@ struct kvm_vcpu_arch { struct kvm_mmu_memory_cache mmu_shadow_page_cache; struct kvm_mmu_memory_cache mmu_shadowed_info_cache; struct kvm_mmu_memory_cache mmu_page_header_cache; + /* + * This cache is to allocate external page table. E.g. private EPT used + * by the TDX module. + */ + struct kvm_mmu_memory_cache mmu_external_spt_cache; /* * QEMU userspace and the guest each have their own FPU state. diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index e9322358678b..538eb3156f09 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -287,4 +287,9 @@ static inline gpa_t kvm_translate_gpa(struct kvm_vcpu *vcpu, return gpa; return translate_nested_gpa(vcpu, gpa, access, exception); } + +static inline bool kvm_has_mirrored_tdp(const struct kvm *kvm) +{ + return kvm->arch.vm_type == KVM_X86_TDX_VM; +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a8f75971d3cb..d44d0a4db699 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -599,6 +599,12 @@ static int mmu_topup_memory_caches(struct kvm_vcpu *vcpu, bool maybe_indirect) 1 + PT64_ROOT_MAX_LEVEL + PTE_PREFETCH_NUM); if (r) return r; + if (kvm_has_mirrored_tdp(vcpu->kvm)) { + r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_external_spt_cache, + PT64_ROOT_MAX_LEVEL); + if (r) + return r; + } r = kvm_mmu_topup_memory_cache(&vcpu->arch.mmu_shadow_page_cache, PT64_ROOT_MAX_LEVEL); if (r) @@ -618,6 +624,7 @@ static void mmu_free_memory_caches(struct kvm_vcpu *vcpu) kvm_mmu_free_memory_cache(&vcpu->arch.mmu_pte_list_desc_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadow_page_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_shadowed_info_cache); + kvm_mmu_free_memory_cache(&vcpu->arch.mmu_external_spt_cache); kvm_mmu_free_memory_cache(&vcpu->arch.mmu_page_header_cache); } diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index b00abbe3f6cf..d9425064ecc5 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -101,7 +101,22 @@ struct kvm_mmu_page { int root_count; refcount_t tdp_mmu_root_count; }; - unsigned int unsync_children; + union { + /* These two members aren't used for TDP MMU */ + struct { + unsigned int unsync_children; + /* + * Number of writes since the last time traversal + * visited this page. + */ + atomic_t write_flooding_count; + }; + /* + * Page table page of external PT. + * Passed to TDX module, not accessed by KVM. + */ + void *external_spt; + }; union { struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */ tdp_ptep_t ptep; @@ -124,9 +139,6 @@ struct kvm_mmu_page { int clear_spte_count; #endif - /* Number of writes since the last time traversal visited this page. */ - atomic_t write_flooding_count; - #ifdef CONFIG_X86_64 /* Used for freeing the page asynchronously if it is a TDP MMU page. */ struct rcu_head rcu_head; @@ -145,6 +157,17 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } +static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) +{ + /* + * external_spt is allocated for TDX module to hold private EPT mappings, + * TDX module will initialize the page by itself. + * Therefore, KVM does not need to initialize or access external_spt. + * KVM only interacts with sp->spt for private EPT operations. + */ + sp->external_spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_external_spt_cache); +} + static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 1054ccd9b861..d79a260d213d 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -53,6 +53,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) static void tdp_mmu_free_sp(struct kvm_mmu_page *sp) { + free_page((unsigned long)sp->external_spt); free_page((unsigned long)sp->spt); kmem_cache_free(mmu_page_header_cache, sp); } From 6961ab0bae5282de221fed5fc3e9db2b9180c4d6 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:17 -0700 Subject: [PATCH 06/20] KVM: x86/mmu: Add an is_mirror member for union kvm_mmu_page_role Introduce a "is_mirror" member to the kvm_mmu_page_role union to identify SPTEs associated with the mirrored EPT. The TDX module maintains the private half of the EPT mapped in the TD in its protected memory. KVM keeps a copy of the private GPAs in a mirrored EPT tree within host memory. This "is_mirror" attribute enables vCPUs to find and get the root page of mirrored EPT from the MMU root list for a guest TD. This also allows KVM MMU code to detect changes in mirrored EPT according to the "is_mirror" mmu page role and propagate the changes to the private EPT managed by TDX module. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-6-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 8 +++++--- arch/x86/kvm/mmu/mmu_internal.h | 5 +++++ arch/x86/kvm/mmu/spte.h | 5 +++++ 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 5f020b097922..f9f1401cb5ae 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -313,10 +313,11 @@ struct kvm_kernel_irq_routing_entry; * the number of unique SPs that can theoretically be created is 2^n, where n * is the number of bits that are used to compute the role. * - * But, even though there are 19 bits in the mask below, not all combinations + * But, even though there are 20 bits in the mask below, not all combinations * of modes and flags are possible: * - * - invalid shadow pages are not accounted, so the bits are effectively 18 + * - invalid shadow pages are not accounted, mirror pages are not shadowed, + * so the bits are effectively 18. * * - quadrant will only be used if has_4_byte_gpte=1 (non-PAE paging); * execonly and ad_disabled are only used for nested EPT which has @@ -349,7 +350,8 @@ union kvm_mmu_page_role { unsigned ad_disabled:1; unsigned guest_mode:1; unsigned passthrough:1; - unsigned :5; + unsigned is_mirror:1; + unsigned :4; /* * This is left at the top of the word so that diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index d9425064ecc5..ff00341f26a2 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -157,6 +157,11 @@ static inline int kvm_mmu_page_as_id(struct kvm_mmu_page *sp) return kvm_mmu_role_as_id(sp->role); } +static inline bool is_mirror_sp(const struct kvm_mmu_page *sp) +{ + return sp->role.is_mirror; +} + static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { /* diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h index af10bc0380a3..59746854c0af 100644 --- a/arch/x86/kvm/mmu/spte.h +++ b/arch/x86/kvm/mmu/spte.h @@ -276,6 +276,11 @@ static inline struct kvm_mmu_page *root_to_sp(hpa_t root) return spte_to_child_sp(root); } +static inline bool is_mirror_sptep(tdp_ptep_t sptep) +{ + return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep))); +} + static inline bool is_mmio_spte(struct kvm *kvm, u64 spte) { return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value && From 243e13e810c070785b85470c436cc174cf115a3b Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 18 Jul 2024 14:12:18 -0700 Subject: [PATCH 07/20] KVM: x86/mmu: Make kvm_tdp_mmu_alloc_root() return void The kvm_tdp_mmu_alloc_root() function currently always returns 0. This allows for the caller, mmu_alloc_direct_roots(), to call kvm_tdp_mmu_alloc_root() and also return 0 in one line: return kvm_tdp_mmu_alloc_root(vcpu); So it is useful even though the return value of kvm_tdp_mmu_alloc_root() is always the same. However, in future changes, kvm_tdp_mmu_alloc_root() will be called twice in mmu_alloc_direct_roots(). This will force the first call to either awkwardly handle the return value that will always be zero or ignore it. So change kvm_tdp_mmu_alloc_root() to return void. Do it in a separate change so the future change will be cleaner. Signed-off-by: Rick Edgecombe Reviewed-by: Paolo Bonzini Message-ID: <20240718211230.1492011-7-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 6 ++++-- arch/x86/kvm/mmu/tdp_mmu.c | 3 +-- arch/x86/kvm/mmu/tdp_mmu.h | 2 +- 3 files changed, 6 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index d44d0a4db699..cbb77ef56898 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3663,8 +3663,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) unsigned i; int r; - if (tdp_mmu_enabled) - return kvm_tdp_mmu_alloc_root(vcpu); + if (tdp_mmu_enabled) { + kvm_tdp_mmu_alloc_root(vcpu); + return 0; + } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d79a260d213d..d29c06cc86d7 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -224,7 +224,7 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role role = mmu->root_role; @@ -285,7 +285,6 @@ out_read_unlock: */ mmu->root.hpa = __pa(root->spt); mmu->root.pgd = 0; - return 0; } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 6d7cdc462f58..51884fc6a512 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -int kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { From e23186da667d1573438c04d2f753440fbf223e59 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:19 -0700 Subject: [PATCH 08/20] KVM: x86/tdp_mmu: Take struct kvm in iter loops Add a struct kvm argument to the TDP MMU iterators. Future changes will want to change how the iterator behaves based on a member of struct kvm. Change the signature and callers of the iterator loop helpers in a separate patch to make the future one easier to review. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-8-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_iter.h | 6 +++--- arch/x86/kvm/mmu/tdp_mmu.c | 38 ++++++++++++++++++------------------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index 2880fd392e0c..d8f2884e3c66 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -122,13 +122,13 @@ struct tdp_iter { * Iterates over every SPTE mapping the GFN range [start, end) in a * preorder traversal. */ -#define for_each_tdp_pte_min_level(iter, root, min_level, start, end) \ +#define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) \ for (tdp_iter_start(&iter, root, min_level, start); \ iter.valid && iter.gfn < end; \ tdp_iter_next(&iter)) -#define for_each_tdp_pte(iter, root, start, end) \ - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) +#define for_each_tdp_pte(iter, kvm, root, start, end) \ + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) tdp_ptep_t spte_to_child_pt(u64 pte, int level); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d29c06cc86d7..30eefc710aec 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -625,18 +625,18 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, iter->gfn, iter->level); } -#define tdp_root_for_each_pte(_iter, _root, _start, _end) \ - for_each_tdp_pte(_iter, _root, _start, _end) +#define tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) -#define tdp_root_for_each_leaf_pte(_iter, _root, _start, _end) \ - tdp_root_for_each_pte(_iter, _root, _start, _end) \ +#define tdp_root_for_each_leaf_pte(_iter, _kvm, _root, _start, _end) \ + tdp_root_for_each_pte(_iter, _kvm, _root, _start, _end) \ if (!is_shadow_present_pte(_iter.old_spte) || \ !is_last_spte(_iter.old_spte, _iter.level)) \ continue; \ else -#define tdp_mmu_for_each_pte(_iter, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, root_to_sp(_mmu->root.hpa), _start, _end) +#define tdp_mmu_for_each_pte(_iter, _kvm, _mmu, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, root_to_sp(_mmu->root.hpa), _start, _end) static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm, struct tdp_iter *iter) @@ -708,7 +708,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t end = tdp_mmu_max_gfn_exclusive(); gfn_t start = 0; - for_each_tdp_pte_min_level(iter, root, zap_level, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, zap_level, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -812,7 +812,7 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) { if (can_yield && tdp_mmu_iter_cond_resched(kvm, &iter, flush, false)) { flush = false; @@ -1086,7 +1086,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); - tdp_mmu_for_each_pte(iter, mmu, fault->gfn, fault->gfn + 1) { + tdp_mmu_for_each_pte(iter, kvm, mmu, fault->gfn, fault->gfn + 1) { int r; if (fault->nx_huge_page_workaround_enabled) @@ -1212,7 +1212,7 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) { guard(rcu)(); - tdp_root_for_each_leaf_pte(iter, root, range->start, range->end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) { if (!is_accessed_spte(iter.old_spte)) continue; @@ -1253,7 +1253,7 @@ static bool wrprot_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, BUG_ON(min_level > KVM_MAX_HUGEPAGE_LEVEL); - for_each_tdp_pte_min_level(iter, root, min_level, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; @@ -1372,7 +1372,7 @@ static int tdp_mmu_split_huge_pages_root(struct kvm *kvm, * level above the target level (e.g. splitting a 1GB to 512 2MB pages, * and then splitting each of those to 512 4KB pages). */ - for_each_tdp_pte_min_level(iter, root, target_level + 1, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, target_level + 1, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; @@ -1470,7 +1470,7 @@ static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_pte(iter, root, start, end) { + tdp_root_for_each_pte(iter, kvm, root, start, end) { retry: if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) @@ -1518,7 +1518,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - tdp_root_for_each_leaf_pte(iter, root, gfn + __ffs(mask), + tdp_root_for_each_leaf_pte(iter, kvm, root, gfn + __ffs(mask), gfn + BITS_PER_LONG) { if (!mask) break; @@ -1572,7 +1572,7 @@ static int tdp_mmu_make_huge_spte(struct kvm *kvm, gfn_t end = start + KVM_PAGES_PER_HPAGE(parent->level); struct tdp_iter iter; - tdp_root_for_each_leaf_pte(iter, root, start, end) { + tdp_root_for_each_leaf_pte(iter, kvm, root, start, end) { /* * Use the parent iterator when checking for forward progress so * that KVM doesn't get stuck continuously trying to yield (i.e. @@ -1606,7 +1606,7 @@ static void recover_huge_pages_range(struct kvm *kvm, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_2M, start, end) { + for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_2M, start, end) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, flush, true)) { flush = false; @@ -1687,7 +1687,7 @@ static bool write_protect_gfn(struct kvm *kvm, struct kvm_mmu_page *root, rcu_read_lock(); - for_each_tdp_pte_min_level(iter, root, min_level, gfn, gfn + 1) { + for_each_tdp_pte_min_level(iter, kvm, root, min_level, gfn, gfn + 1) { if (!is_shadow_present_pte(iter.old_spte) || !is_last_spte(iter.old_spte, iter.level)) continue; @@ -1742,7 +1742,7 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, *root_level = vcpu->arch.mmu->root_role.level; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, mmu, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } @@ -1768,7 +1768,7 @@ u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_mmu *mmu = vcpu->arch.mmu; tdp_ptep_t sptep = NULL; - tdp_mmu_for_each_pte(iter, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, mmu, gfn, gfn + 1) { *spte = iter.old_spte; sptep = iter.sptep; } From 3fc3f71851129f9d7c6b8b192b6a81604a1cb2e3 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:20 -0700 Subject: [PATCH 09/20] KVM: x86/mmu: Support GFN direct bits Teach the MMU to map guest GFNs at a massaged position on the TDP, to aid in implementing TDX shared memory. Like other Coco technologies, TDX has the concept of private and shared memory. For TDX the private and shared mappings are managed on separate EPT roots. The private half is managed indirectly through calls into a protected runtime environment called the TDX module, where the shared half is managed within KVM in normal page tables. For TDX, the shared half will be mapped in the higher alias, with a "shared bit" set in the GPA. However, KVM will still manage it with the same memslots as the private half. This means memslot looks ups and zapping operations will be provided with a GFN without the shared bit set. So KVM will either need to apply or strip the shared bit before mapping or zapping the shared EPT. Having GFNs sometimes have the shared bit and sometimes not would make the code confusing. So instead arrange the code such that GFNs never have shared bit set. Create a concept of "direct bits", that is stripped from the fault address when setting fault->gfn, and applied within the TDP MMU iterator. Calling code will behave as if it is operating on the PTE mapping the GFN (without shared bits) but within the iterator, the actual mappings will be shifted using bits specific for the root. SPs will have the GFN set without the shared bit. In the end the TDP MMU will behave like it is mapping things at the GFN without the shared bit but with a strange page table format where everything is offset by the shared bit. Since TDX only needs to shift the mapping like this for the shared bit, which is mapped as the normal TDP root, add a "gfn_direct_bits" field to the kvm_arch structure for each VM with a default value of 0. It will have the bit set at the position of the GPA shared bit in GFN through TD specific initialization code. Keep TDX specific concepts out of the MMU code by not naming it "shared". Ranged TLB flushes (i.e. flush_remote_tlbs_range()) target specific GFN ranges. In convention established above, these would need to target the shifted GFN range. It won't matter functionally, since the actual implementation will always result in a full flush for the only planned user (TDX). For correctness reasons, future changes can provide a TDX x86_ops.flush_remote_tlbs_range implementation to return -EOPNOTSUPP and force the full flush for TDs. This leaves one problem. Some operations use a concept of max GFN (i.e. kvm_mmu_max_gfn()), to iterate over the whole TDP range. When applying the direct mask to the start of the range, the iterator would end up skipping iterating over the range not covered by the direct mask bit. For safety, make sure the __tdp_mmu_zap_root() operation iterates over the full GFN range supported by the underlying TDP format. Add a new iterator helper, for_each_tdp_pte_min_level_all(), that iterates the entire TDP GFN range, regardless of root. Signed-off-by: Isaku Yamahata Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-9-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 2 ++ arch/x86/kvm/mmu.h | 5 +++++ arch/x86/kvm/mmu/mmu_internal.h | 28 ++++++++++++++++++++++++++-- arch/x86/kvm/mmu/tdp_iter.c | 10 ++++++---- arch/x86/kvm/mmu/tdp_iter.h | 15 +++++++++++---- arch/x86/kvm/mmu/tdp_mmu.c | 5 +---- 6 files changed, 51 insertions(+), 14 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index f9f1401cb5ae..7cf4bd9348b5 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1543,6 +1543,8 @@ struct kvm_arch { */ #define SPLIT_DESC_CACHE_MIN_NR_OBJECTS (SPTE_ENT_PER_PAGE + 1) struct kvm_mmu_memory_cache split_desc_cache; + + gfn_t gfn_direct_bits; }; struct kvm_vm_stat { diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 538eb3156f09..091002975374 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -292,4 +292,9 @@ static inline bool kvm_has_mirrored_tdp(const struct kvm *kvm) { return kvm->arch.vm_type == KVM_X86_TDX_VM; } + +static inline gfn_t kvm_gfn_direct_bits(const struct kvm *kvm) +{ + return kvm->arch.gfn_direct_bits; +} #endif diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index ff00341f26a2..957636660149 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,6 +6,8 @@ #include #include +#include "mmu.h" + #ifdef CONFIG_KVM_PROVE_MMU #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else @@ -173,6 +175,18 @@ static inline void kvm_mmu_alloc_external_spt(struct kvm_vcpu *vcpu, struct kvm_ sp->external_spt = kvm_mmu_memory_cache_alloc(&vcpu->arch.mmu_external_spt_cache); } +static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mmu_page *root) +{ + /* + * Since mirror SPs are used only for TDX, which maps private memory + * at its "natural" GFN, no mask needs to be applied to them - and, dually, + * we expect that the bits is only used for the shared PT. + */ + if (is_mirror_sp(root)) + return 0; + return kvm_gfn_direct_bits(kvm); +} + static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp) { /* @@ -257,7 +271,12 @@ struct kvm_page_fault { */ u8 goal_level; - /* Shifted addr, or result of guest page table walk if addr is a gva. */ + /* + * Shifted addr, or result of guest page table walk if addr is a gva. In + * the case of VM where memslot's can be mapped at multiple GPA aliases + * (i.e. TDX), the gfn field does not contain the bit that selects between + * the aliases (i.e. the shared bit for TDX). + */ gfn_t gfn; /* The memslot containing gfn. May be NULL. */ @@ -345,7 +364,12 @@ static inline int kvm_mmu_do_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, int r; if (vcpu->arch.mmu->root_role.direct) { - fault.gfn = fault.addr >> PAGE_SHIFT; + /* + * Things like memslots don't understand the concept of a shared + * bit. Strip it so that the GFN can be used like normal, and the + * fault.addr can be used when the shared bit is needed. + */ + fault.gfn = gpa_to_gfn(fault.addr) & ~kvm_gfn_direct_bits(vcpu->kvm); fault.slot = kvm_vcpu_gfn_to_memslot(vcpu, fault.gfn); } diff --git a/arch/x86/kvm/mmu/tdp_iter.c b/arch/x86/kvm/mmu/tdp_iter.c index 04c247bfe318..9e17bfa80901 100644 --- a/arch/x86/kvm/mmu/tdp_iter.c +++ b/arch/x86/kvm/mmu/tdp_iter.c @@ -12,7 +12,7 @@ static void tdp_iter_refresh_sptep(struct tdp_iter *iter) { iter->sptep = iter->pt_path[iter->level - 1] + - SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level); + SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level); iter->old_spte = kvm_tdp_mmu_read_spte(iter->sptep); } @@ -37,15 +37,17 @@ void tdp_iter_restart(struct tdp_iter *iter) * rooted at root_pt, starting with the walk to translate next_last_level_gfn. */ void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn) + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits) { if (WARN_ON_ONCE(!root || (root->role.level < 1) || - (root->role.level > PT64_ROOT_MAX_LEVEL))) { + (root->role.level > PT64_ROOT_MAX_LEVEL) || + (gfn_bits && next_last_level_gfn >= gfn_bits))) { iter->valid = false; return; } iter->next_last_level_gfn = next_last_level_gfn; + iter->gfn_bits = gfn_bits; iter->root_level = root->role.level; iter->min_level = min_level; iter->pt_path[iter->root_level - 1] = (tdp_ptep_t)root->spt; @@ -113,7 +115,7 @@ static bool try_step_side(struct tdp_iter *iter) * Check if the iterator is already at the end of the current page * table. */ - if (SPTE_INDEX(iter->gfn << PAGE_SHIFT, iter->level) == + if (SPTE_INDEX((iter->gfn | iter->gfn_bits) << PAGE_SHIFT, iter->level) == (SPTE_ENT_PER_PAGE - 1)) return false; diff --git a/arch/x86/kvm/mmu/tdp_iter.h b/arch/x86/kvm/mmu/tdp_iter.h index d8f2884e3c66..047b78333653 100644 --- a/arch/x86/kvm/mmu/tdp_iter.h +++ b/arch/x86/kvm/mmu/tdp_iter.h @@ -93,8 +93,10 @@ struct tdp_iter { tdp_ptep_t pt_path[PT64_ROOT_MAX_LEVEL]; /* A pointer to the current SPTE */ tdp_ptep_t sptep; - /* The lowest GFN mapped by the current SPTE */ + /* The lowest GFN (mask bits excluded) mapped by the current SPTE */ gfn_t gfn; + /* Mask applied to convert the GFN to the mapping GPA */ + gfn_t gfn_bits; /* The level of the root page given to the iterator */ int root_level; /* The lowest level the iterator should traverse to */ @@ -123,17 +125,22 @@ struct tdp_iter { * preorder traversal. */ #define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, end) \ - for (tdp_iter_start(&iter, root, min_level, start); \ - iter.valid && iter.gfn < end; \ + for (tdp_iter_start(&iter, root, min_level, start, kvm_gfn_root_bits(kvm, root)); \ + iter.valid && iter.gfn < end; \ tdp_iter_next(&iter)) +#define for_each_tdp_pte_min_level_all(iter, root, min_level) \ + for (tdp_iter_start(&iter, root, min_level, 0, 0); \ + iter.valid && iter.gfn < tdp_mmu_max_gfn_exclusive(); \ + tdp_iter_next(&iter)) + #define for_each_tdp_pte(iter, kvm, root, start, end) \ for_each_tdp_pte_min_level(iter, kvm, root, PG_LEVEL_4K, start, end) tdp_ptep_t spte_to_child_pt(u64 pte, int level); void tdp_iter_start(struct tdp_iter *iter, struct kvm_mmu_page *root, - int min_level, gfn_t next_last_level_gfn); + int min_level, gfn_t next_last_level_gfn, gfn_t gfn_bits); void tdp_iter_next(struct tdp_iter *iter); void tdp_iter_restart(struct tdp_iter *iter); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 30eefc710aec..5b01038ddce8 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -705,10 +705,7 @@ static void __tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root, { struct tdp_iter iter; - gfn_t end = tdp_mmu_max_gfn_exclusive(); - gfn_t start = 0; - - for_each_tdp_pte_min_level(iter, kvm, root, zap_level, start, end) { + for_each_tdp_pte_min_level_all(iter, root, zap_level) { retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, shared)) continue; From e84b8e4e4430d2a81a3464be8ebe5959da9a6d4a Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:21 -0700 Subject: [PATCH 10/20] KVM: x86/tdp_mmu: Extract root invalid check from tdx_mmu_next_root() Extract tdp_mmu_root_match() to check if the root has given types and use it for the root page table iterator. It checks only_invalid now. TDX KVM operates on a shared page table only (Shared-EPT), a mirrored page table only (Secure-EPT), or both based on the operation. KVM MMU notifier operations only on shared page table. KVM guest_memfd invalidation operations only on mirrored page table, and so on. Introduce a centralized matching function instead of open coding matching logic in the iterator. The next step is to extend the function to check whether the page is shared or private Link: https://lore.kernel.org/kvm/ZivazWQw1oCU8VBC@google.com/ Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-10-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 5b01038ddce8..e0ccfdd4200b 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -92,6 +92,14 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static bool tdp_mmu_root_match(struct kvm_mmu_page *root, bool only_valid) +{ + if (only_valid && root->role.invalid) + return false; + + return true; +} + /* * Returns the next root after @prev_root (or the first root if @prev_root is * NULL). A reference to the returned root is acquired, and the reference to @@ -125,7 +133,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, typeof(*next_root), link); while (next_root) { - if ((!only_valid || !next_root->role.invalid) && + if (tdp_mmu_root_match(next_root, only_valid) && kvm_tdp_mmu_get_root(next_root)) break; @@ -176,7 +184,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ - ((_only_valid) && (_root)->role.invalid))) { \ + !tdp_mmu_root_match((_root), (_only_valid)))) { \ } else #define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ From de86ef7bf50f181b29dcc1046e903ff1ca7eeb9f Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:22 -0700 Subject: [PATCH 11/20] KVM: x86/tdp_mmu: Introduce KVM MMU root types to specify page table type Define an enum kvm_tdp_mmu_root_types to specify the KVM MMU root type [1] so that the iterator on the root page table can consistently filter the root page table type instead of only_valid. TDX KVM will operate on KVM page tables with specified types. Shared page table, private page table, or both. Introduce an enum instead of bool only_valid so that we can easily enhance page table types applicable to shared, private, or both in addition to valid or not. Replace only_valid=false with KVM_ANY_ROOTS and only_valid=true with KVM_ANY_VALID_ROOTS. Use KVM_ANY_ROOTS and KVM_ANY_VALID_ROOTS to wrap KVM_VALID_ROOTS to avoid further code churn when direct vs mirror root concepts are introduced in future patches. Link: https://lore.kernel.org/kvm/ZivazWQw1oCU8VBC@google.com/ [1] Suggested-by: Sean Christopherson Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-11-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 42 +++++++++++++++++++++----------------- arch/x86/kvm/mmu/tdp_mmu.h | 7 +++++++ 2 files changed, 30 insertions(+), 19 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index e0ccfdd4200b..9fbf4770ba3e 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -92,9 +92,13 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root) call_rcu(&root->rcu_head, tdp_mmu_free_sp_rcu_callback); } -static bool tdp_mmu_root_match(struct kvm_mmu_page *root, bool only_valid) +static bool tdp_mmu_root_match(struct kvm_mmu_page *root, + enum kvm_tdp_mmu_root_types types) { - if (only_valid && root->role.invalid) + if (WARN_ON_ONCE(!(types & KVM_VALID_ROOTS))) + return false; + + if (root->role.invalid && !(types & KVM_INVALID_ROOTS)) return false; return true; @@ -102,17 +106,17 @@ static bool tdp_mmu_root_match(struct kvm_mmu_page *root, bool only_valid) /* * Returns the next root after @prev_root (or the first root if @prev_root is - * NULL). A reference to the returned root is acquired, and the reference to - * @prev_root is released (the caller obviously must hold a reference to - * @prev_root if it's non-NULL). + * NULL) that matches with @types. A reference to the returned root is + * acquired, and the reference to @prev_root is released (the caller obviously + * must hold a reference to @prev_root if it's non-NULL). * - * If @only_valid is true, invalid roots are skipped. + * Roots that doesn't match with @types are skipped. * * Returns NULL if the end of tdp_mmu_roots was reached. */ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, struct kvm_mmu_page *prev_root, - bool only_valid) + enum kvm_tdp_mmu_root_types types) { struct kvm_mmu_page *next_root; @@ -133,7 +137,7 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, typeof(*next_root), link); while (next_root) { - if (tdp_mmu_root_match(next_root, only_valid) && + if (tdp_mmu_root_match(next_root, types) && kvm_tdp_mmu_get_root(next_root)) break; @@ -158,20 +162,20 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * If shared is set, this function is operating under the MMU lock in read * mode. */ -#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _only_valid) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, _only_valid); \ +#define __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _types) \ + for (_root = tdp_mmu_next_root(_kvm, NULL, _types); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, _only_valid)) \ + _root = tdp_mmu_next_root(_kvm, _root, _types)) \ if (_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) { \ } else #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, true) + __for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, KVM_VALID_ROOTS) #define for_each_tdp_mmu_root_yield_safe(_kvm, _root) \ - for (_root = tdp_mmu_next_root(_kvm, NULL, false); \ + for (_root = tdp_mmu_next_root(_kvm, NULL, KVM_ALL_ROOTS); \ ({ lockdep_assert_held(&(_kvm)->mmu_lock); }), _root; \ - _root = tdp_mmu_next_root(_kvm, _root, false)) + _root = tdp_mmu_next_root(_kvm, _root, KVM_ALL_ROOTS)) /* * Iterate over all TDP MMU roots. Requires that mmu_lock be held for write, @@ -180,18 +184,18 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, * Holding mmu_lock for write obviates the need for RCU protection as the list * is guaranteed to be stable. */ -#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _only_valid) \ +#define __for_each_tdp_mmu_root(_kvm, _root, _as_id, _types) \ list_for_each_entry(_root, &_kvm->arch.tdp_mmu_roots, link) \ if (kvm_lockdep_assert_mmu_lock_held(_kvm, false) && \ ((_as_id >= 0 && kvm_mmu_page_as_id(_root) != _as_id) || \ - !tdp_mmu_root_match((_root), (_only_valid)))) { \ + !tdp_mmu_root_match((_root), (_types)))) { \ } else #define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, false) + __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_ALL_ROOTS) #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, true) + __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS) static struct kvm_mmu_page *tdp_mmu_alloc_sp(struct kvm_vcpu *vcpu) { @@ -1164,7 +1168,7 @@ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, { struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false) + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, KVM_ALL_ROOTS) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 51884fc6a512..a2028d036c0c 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -19,6 +19,13 @@ __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); +enum kvm_tdp_mmu_root_types { + KVM_INVALID_ROOTS = BIT(0), + + KVM_VALID_ROOTS = BIT(1), + KVM_ALL_ROOTS = KVM_VALID_ROOTS | KVM_INVALID_ROOTS, +}; + bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); From 00d98dd4a855443b69cba050a0092dc958baae53 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:23 -0700 Subject: [PATCH 12/20] KVM: x86/tdp_mmu: Take root in tdp_mmu_for_each_pte() Take the root as an argument of tdp_mmu_for_each_pte() instead of looking it up in the mmu. With no other purpose of passing the mmu, drop it. Future changes will want to change which root is used based on the context of the MMU operation. So change the callers to pass in the root currently used, mmu->root.hpa in a preparatory patch to make the later one smaller and easier to review. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-12-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 9fbf4770ba3e..1634506b2699 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -647,8 +647,8 @@ static inline void tdp_mmu_iter_set_spte(struct kvm *kvm, struct tdp_iter *iter, continue; \ else -#define tdp_mmu_for_each_pte(_iter, _kvm, _mmu, _start, _end) \ - for_each_tdp_pte(_iter, _kvm, root_to_sp(_mmu->root.hpa), _start, _end) +#define tdp_mmu_for_each_pte(_iter, _kvm, _root, _start, _end) \ + for_each_tdp_pte(_iter, _kvm, _root, _start, _end) static inline bool __must_check tdp_mmu_iter_need_resched(struct kvm *kvm, struct tdp_iter *iter) @@ -1083,8 +1083,8 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, */ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { - struct kvm_mmu *mmu = vcpu->arch.mmu; struct kvm *kvm = vcpu->kvm; + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; struct kvm_mmu_page *sp; int ret = RET_PF_RETRY; @@ -1095,7 +1095,7 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) rcu_read_lock(); - tdp_mmu_for_each_pte(iter, kvm, mmu, fault->gfn, fault->gfn + 1) { + tdp_mmu_for_each_pte(iter, kvm, root, fault->gfn, fault->gfn + 1) { int r; if (fault->nx_huge_page_workaround_enabled) @@ -1744,14 +1744,14 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm, int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, int *root_level) { + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; gfn_t gfn = addr >> PAGE_SHIFT; int leaf = -1; *root_level = vcpu->arch.mmu->root_role.level; - tdp_mmu_for_each_pte(iter, vcpu->kvm, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } @@ -1773,11 +1773,11 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte) { + struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; - struct kvm_mmu *mmu = vcpu->arch.mmu; tdp_ptep_t sptep = NULL; - tdp_mmu_for_each_pte(iter, vcpu->kvm, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { *spte = iter.old_spte; sptep = iter.sptep; } From fabaa76501485864725448d9da0f7a83254ead8f Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:24 -0700 Subject: [PATCH 13/20] KVM: x86/tdp_mmu: Support mirror root for TDP MMU Add the ability for the TDP MMU to maintain a mirror of a separate mapping. Like other Coco technologies, TDX has the concept of private and shared memory. For TDX the private and shared mappings are managed on separate EPT roots. The private half is managed indirectly through calls into a protected runtime environment called the TDX module, where the shared half is managed within KVM in normal page tables. In order to handle both shared and private memory, KVM needs to learn to handle faults and other operations on the correct root for the operation. KVM could learn the concept of private roots, and operate on them by calling out to operations that call into the TDX module. But there are two problems with that: 1. Calls into the TDX module are relatively slow compared to the simple accesses required to read a PTE managed directly by KVM. 2. Other Coco technologies deal with private memory completely differently and it will make the code confusing when being read from their perspective. Special operations added for TDX that set private or zap private memory will have nothing to do with these other private memory technologies. (SEV, etc). To handle these, instead teach the TDP MMU about a new concept "mirror roots". Such roots maintain page tables that are not actually mapped, and are just used to traverse quickly to determine if the mid level page tables need to be installed. When the memory be mirrored needs to actually be changed, calls can be made to via x86_ops. private KVM page fault | | | V | private GPA | CPU protected EPTP | | | V | V mirror PT root | external PT root | | | V | V mirror PT --hook to propagate-->external PT | | | \--------------------+------\ | | | | | V V | private guest page | | non-encrypted memory | encrypted memory | Leave calling out to actually update the private page tables that are being mirrored for later changes. Just implement the handling of MMU operations on to mirrored roots. In order to direct operations to correct root, add root types KVM_DIRECT_ROOTS and KVM_MIRROR_ROOTS. Tie the usage of mirrored/direct roots to private/shared with conditionals. It could also be implemented by making the kvm_tdp_mmu_root_types and kvm_gfn_range_filter enum bits line up such that conversion could be a direct assignment with a case. Don't do this because the mapping of private to mirrored is confusing enough. So it is worth not hiding the logic in type casting. Cleanup the mirror root in kvm_mmu_destroy() instead of the normal place in kvm_mmu_free_roots(), because the private root that is being cannot be rebuilt like a normal root. It needs to persist for the lifetime of the VM. The TDX module will also need to be provided with page tables to use for the actual mapping being mirrored by the mirrored page tables. Allocate these in the mapping path using the recently added kvm_mmu_alloc_external_spt(). Don't support 2M page for now. This is avoided by forcing 4k pages in the fault. Add a KVM_BUG_ON() to verify. Signed-off-by: Isaku Yamahata Co-developed-by: Kai Huang Signed-off-by: Kai Huang Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-13-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/mmu.h | 16 ++++++++++++ arch/x86/kvm/mmu/mmu.c | 12 ++++++++- arch/x86/kvm/mmu/tdp_mmu.c | 31 ++++++++++++++++++------ arch/x86/kvm/mmu/tdp_mmu.h | 43 ++++++++++++++++++++++++++++++--- 5 files changed, 91 insertions(+), 12 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7cf4bd9348b5..15601a221213 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -459,6 +459,7 @@ struct kvm_mmu { int (*sync_spte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, int i); struct kvm_mmu_root_info root; + hpa_t mirror_root_hpa; union kvm_cpu_role cpu_role; union kvm_mmu_page_role root_role; diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 091002975374..d1775a38ffd3 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,15 @@ void kvm_mmu_track_write(struct kvm_vcpu *vcpu, gpa_t gpa, const u8 *new, static inline int kvm_mmu_reload(struct kvm_vcpu *vcpu) { + /* + * Checking root.hpa is sufficient even when KVM has mirror root. + * We can have either: + * (1) mirror_root_hpa = INVALID_PAGE, root.hpa = INVALID_PAGE + * (2) mirror_root_hpa = root, root.hpa = INVALID_PAGE + * (3) mirror_root_hpa = root1, root.hpa = root2 + * We don't ever have: + * mirror_root_hpa = INVALID_PAGE, root.hpa = root + */ if (likely(vcpu->arch.mmu->root.hpa != INVALID_PAGE)) return 0; @@ -297,4 +306,11 @@ static inline gfn_t kvm_gfn_direct_bits(const struct kvm *kvm) { return kvm->arch.gfn_direct_bits; } + +static inline bool kvm_is_addr_direct(struct kvm *kvm, gpa_t gpa) +{ + gpa_t gpa_direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(kvm)); + + return !gpa_direct_bits || (gpa & gpa_direct_bits); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index cbb77ef56898..7a71e6077094 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3664,7 +3664,10 @@ static int mmu_alloc_direct_roots(struct kvm_vcpu *vcpu) int r; if (tdp_mmu_enabled) { - kvm_tdp_mmu_alloc_root(vcpu); + if (kvm_has_mirrored_tdp(vcpu->kvm) && + !VALID_PAGE(mmu->mirror_root_hpa)) + kvm_tdp_mmu_alloc_root(vcpu, true); + kvm_tdp_mmu_alloc_root(vcpu, false); return 0; } @@ -6281,6 +6284,7 @@ static int __kvm_mmu_create(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu) mmu->root.hpa = INVALID_PAGE; mmu->root.pgd = 0; + mmu->mirror_root_hpa = INVALID_PAGE; for (i = 0; i < KVM_MMU_NUM_PREV_ROOTS; i++) mmu->prev_roots[i] = KVM_MMU_ROOT_INFO_INVALID; @@ -7229,6 +7233,12 @@ out: void kvm_mmu_destroy(struct kvm_vcpu *vcpu) { kvm_mmu_unload(vcpu); + if (tdp_mmu_enabled) { + read_lock(&vcpu->kvm->mmu_lock); + mmu_free_root_page(vcpu->kvm, &vcpu->arch.mmu->mirror_root_hpa, + NULL); + read_unlock(&vcpu->kvm->mmu_lock); + } free_mmu_pages(&vcpu->arch.root_mmu); free_mmu_pages(&vcpu->arch.guest_mmu); mmu_free_memory_caches(vcpu); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 1634506b2699..cf623ec00637 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -101,7 +101,9 @@ static bool tdp_mmu_root_match(struct kvm_mmu_page *root, if (root->role.invalid && !(types & KVM_INVALID_ROOTS)) return false; - return true; + if (likely(!is_mirror_sp(root))) + return types & KVM_DIRECT_ROOTS; + return types & KVM_MIRROR_ROOTS; } /* @@ -236,7 +238,7 @@ static void tdp_mmu_init_child_sp(struct kvm_mmu_page *child_sp, tdp_mmu_init_sp(child_sp, iter->sptep, iter->gfn, role); } -void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool mirror) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role role = mmu->root_role; @@ -244,6 +246,9 @@ void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu) struct kvm *kvm = vcpu->kvm; struct kvm_mmu_page *root; + if (mirror) + role.is_mirror = true; + /* * Check for an existing root before acquiring the pages lock to avoid * unnecessary serialization if multiple vCPUs are loading a new root. @@ -295,8 +300,12 @@ out_read_unlock: * and actually consuming the root if it's invalidated after dropping * mmu_lock, and the root can't be freed as this vCPU holds a reference. */ - mmu->root.hpa = __pa(root->spt); - mmu->root.pgd = 0; + if (mirror) { + mmu->mirror_root_hpa = __pa(root->spt); + } else { + mmu->root.hpa = __pa(root->spt); + mmu->root.pgd = 0; + } } static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, @@ -1083,8 +1092,8 @@ static int tdp_mmu_split_huge_page(struct kvm *kvm, struct tdp_iter *iter, */ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) { + struct kvm_mmu_page *root = tdp_mmu_get_root_for_fault(vcpu, fault); struct kvm *kvm = vcpu->kvm; - struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); struct tdp_iter iter; struct kvm_mmu_page *sp; int ret = RET_PF_RETRY; @@ -1122,13 +1131,18 @@ int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) */ sp = tdp_mmu_alloc_sp(vcpu); tdp_mmu_init_child_sp(sp, &iter); + if (is_mirror_sp(sp)) + kvm_mmu_alloc_external_spt(vcpu, sp); sp->nx_huge_page_disallowed = fault->huge_page_disallowed; - if (is_shadow_present_pte(iter.old_spte)) + if (is_shadow_present_pte(iter.old_spte)) { + /* Don't support large page for mirrored roots (TDX) */ + KVM_BUG_ON(is_mirror_sptep(iter.sptep), vcpu->kvm); r = tdp_mmu_split_huge_page(kvm, &iter, sp, true); - else + } else { r = tdp_mmu_link_sp(kvm, &iter, sp, true); + } /* * Force the guest to retry if installing an upper level SPTE @@ -1773,7 +1787,8 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes, u64 *kvm_tdp_mmu_fast_pf_get_last_sptep(struct kvm_vcpu *vcpu, gfn_t gfn, u64 *spte) { - struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa); + /* Fast pf is not supported for mirrored roots */ + struct kvm_mmu_page *root = tdp_mmu_get_root(vcpu, KVM_DIRECT_ROOTS); struct tdp_iter iter; tdp_ptep_t sptep = NULL; diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index a2028d036c0c..9887441cd703 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -10,7 +10,7 @@ void kvm_mmu_init_tdp_mmu(struct kvm *kvm); void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm); -void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu); +void kvm_tdp_mmu_alloc_root(struct kvm_vcpu *vcpu, bool private); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { @@ -21,11 +21,48 @@ void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root); enum kvm_tdp_mmu_root_types { KVM_INVALID_ROOTS = BIT(0), - - KVM_VALID_ROOTS = BIT(1), + KVM_DIRECT_ROOTS = BIT(1), + KVM_MIRROR_ROOTS = BIT(2), + KVM_VALID_ROOTS = KVM_DIRECT_ROOTS | KVM_MIRROR_ROOTS, KVM_ALL_ROOTS = KVM_VALID_ROOTS | KVM_INVALID_ROOTS, }; +static inline enum kvm_tdp_mmu_root_types kvm_gfn_range_filter_to_root_types(struct kvm *kvm, + enum kvm_gfn_range_filter process) +{ + enum kvm_tdp_mmu_root_types ret = 0; + + if (!kvm_has_mirrored_tdp(kvm)) + return KVM_DIRECT_ROOTS; + + if (process & KVM_FILTER_PRIVATE) + ret |= KVM_MIRROR_ROOTS; + if (process & KVM_FILTER_SHARED) + ret |= KVM_DIRECT_ROOTS; + + WARN_ON_ONCE(!ret); + + return ret; +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root_for_fault(struct kvm_vcpu *vcpu, + struct kvm_page_fault *fault) +{ + if (unlikely(!kvm_is_addr_direct(vcpu->kvm, fault->addr))) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + +static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu, + enum kvm_tdp_mmu_root_types type) +{ + if (unlikely(type == KVM_MIRROR_ROOTS)) + return root_to_sp(vcpu->arch.mmu->mirror_root_hpa); + + return root_to_sp(vcpu->arch.mmu->root.hpa); +} + bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush); bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp); void kvm_tdp_mmu_zap_all(struct kvm *kvm); From de1bf90488708104299639ae49961a9bd0b5a22f Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Tue, 10 Dec 2024 10:00:23 -0500 Subject: [PATCH 14/20] KVM: x86/tdp_mmu: Propagate attr_filter to MMU notifier callbacks Teach the MMU notifier callbacks how to check kvm_gfn_range.process to filter which KVM MMU root types to operate on. The private GPAs are backed by guest memfd. Such memory is not subjected to MMU notifier callbacks because it can't be mapped into the host user address space. Now kvm_gfn_range conveys info about which root to operate on. Enhance the callback to filter the root page table type. The KVM MMU notifier comes down to two functions. kvm_tdp_mmu_unmap_gfn_range() and __kvm_tdp_mmu_age_gfn_range(): - invalidate_range_start() calls kvm_tdp_mmu_unmap_gfn_range() - invalidate_range_end() doesn't call into arch code - the other callbacks call __kvm_tdp_mmu_age_gfn_range() For VM's without a private/shared split in the EPT, all operations should target the normal(direct) root. With the switch from for_each_tdp_mmu_root() to __for_each_tdp_mmu_root() in kvm_tdp_mmu_handle_gfn(), there are no longer any users of for_each_tdp_mmu_root(). Remove it. Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-14-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index cf623ec00637..8e584be64523 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -193,9 +193,6 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm, !tdp_mmu_root_match((_root), (_types)))) { \ } else -#define for_each_tdp_mmu_root(_kvm, _root, _as_id) \ - __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_ALL_ROOTS) - #define for_each_valid_tdp_mmu_root(_kvm, _root, _as_id) \ __for_each_tdp_mmu_root(_kvm, _root, _as_id, KVM_VALID_ROOTS) @@ -1177,12 +1174,16 @@ retry: return ret; } +/* Used by mmu notifier via kvm_unmap_gfn_range() */ bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool flush) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; - __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, KVM_ALL_ROOTS) + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter) | KVM_INVALID_ROOTS; + + __for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, types) flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end, range->may_block, flush); @@ -1222,17 +1223,21 @@ static bool __kvm_tdp_mmu_age_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range, bool test_only) { + enum kvm_tdp_mmu_root_types types; struct kvm_mmu_page *root; struct tdp_iter iter; bool ret = false; + types = kvm_gfn_range_filter_to_root_types(kvm, range->attr_filter); + /* * Don't support rescheduling, none of the MMU notifiers that funnel * into this helper allow blocking; it'd be dead, wasteful code. Note, * this helper must NOT be used to unmap GFNs, as it processes only * valid roots! */ - for_each_valid_tdp_mmu_root(kvm, root, range->slot->as_id) { + WARN_ON(types & ~KVM_VALID_ROOTS); + __for_each_tdp_mmu_root(kvm, root, range->slot->as_id, types) { guard(rcu)(); tdp_root_for_each_leaf_pte(iter, kvm, root, range->start, range->end) { From 77ac7079e66d5ce45cd72b2790ca7dbaddd7aa2d Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 14 Nov 2024 13:42:29 -0500 Subject: [PATCH 15/20] KVM: x86/tdp_mmu: Propagate building mirror page tables Integrate hooks for mirroring page table operations for cases where TDX will set PTEs or link page tables. Like other Coco technologies, TDX has the concept of private and shared memory. For TDX the private and shared mappings are managed on separate EPT roots. The private half is managed indirectly through calls into a protected runtime environment called the TDX module, where the shared half is managed within KVM in normal page tables. Since calls into the TDX module are relatively slow, walking private page tables by making calls into the TDX module would not be efficient. Because of this, previous changes have taught the TDP MMU to keep a mirror root, which is separate, unmapped TDP root that private operations can be directed to. Currently this root is disconnected from any actual guest mapping. Now add plumbing to propagate changes to the "external" page tables being mirrored. Just create the x86_ops for now, leave plumbing the operations into the TDX module for future patches. Add two operations for setting up external page tables, one for linking new page tables and one for setting leaf PTEs. Don't add any op for configuring the root PFN, as TDX handles this itself. Don't provide a way to set permissions on the PTEs also, as TDX doesn't support it. This results in MMU "mirroring" support that is very targeted towards TDX. Since it is likely there will be no other user, the main benefit of making the support generic is to keep TDX specific *looking* code outside of the MMU. As a generic feature it will make enough sense from TDX's perspective. For developers unfamiliar with TDX arch it can express the general concepts such that they can continue to work in the code. TDX MMU support will exclude certain MMU operations, so only plug in the mirroring x86 ops where they will be needed. For setting/linking, only hook tdp_mmu_set_spte_atomic() which is used for mapping and linking PTs. Don't bother hooking tdp_mmu_iter_set_spte() as it is only used for setting PTEs in operations unsupported by TDX: splitting huge pages and write protecting. Sprinkle KVM_BUG_ON()s to document as code that these paths are not supported for mirrored page tables. For zapping operations, leave those for near future changes. Many operations in the TDP MMU depend on atomicity of the PTE update. While the mirror PTE on KVM's side can be updated atomically, the update that happens inside the external operations (S-EPT updates via TDX module call) can't happen atomically with the mirror update. The following race could result during two vCPU's populating private memory: * vcpu 1: atomically update 2M level mirror EPT entry to be present * vcpu 2: read 2M level EPT entry that is present * vcpu 2: walk down into 4K level EPT * vcpu 2: atomically update 4K level mirror EPT entry to be present * vcpu 2: set_exterma;_spte() to update 4K secure EPT entry => error because 2M secure EPT entry is not populated yet * vcpu 1: link_external_spt() to update 2M secure EPT entry Prevent this by setting the mirror PTE to FROZEN_SPTE while the reflect operations are performed. Only write the actual mirror PTE value once the reflect operations have completed. When trying to set a PTE to present and encountering a frozen SPTE, retry the fault. By doing this the race is prevented as follows: * vcpu 1: atomically update 2M level EPT entry to be FROZEN_SPTE * vcpu 2: read 2M level EPT entry that is FROZEN_SPTE * vcpu 2: find that the EPT entry is frozen abandon page table walk to resume guest execution * vcpu 1: link_external_spt() to update 2M secure EPT entry * vcpu 1: atomically update 2M level EPT entry to be present (unfreeze) * vcpu 2: resume guest execution Depending on vcpu 1 state, vcpu 2 may result in EPT violation again or make progress on guest execution Signed-off-by: Isaku Yamahata Co-developed-by: Kai Huang Signed-off-by: Kai Huang Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-15-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 2 + arch/x86/include/asm/kvm_host.h | 7 +++ arch/x86/kvm/mmu/tdp_mmu.c | 98 ++++++++++++++++++++++++++---- 3 files changed, 94 insertions(+), 13 deletions(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 5aff7222e40f..dbbdaa8586ab 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -94,6 +94,8 @@ KVM_X86_OP_OPTIONAL_RET0(set_tss_addr) KVM_X86_OP_OPTIONAL_RET0(set_identity_map_addr) KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) KVM_X86_OP(load_mmu_pgd) +KVM_X86_OP_OPTIONAL(link_external_spt) +KVM_X86_OP_OPTIONAL(set_external_spte) KVM_X86_OP(has_wbinvd_exit) KVM_X86_OP(get_l2_tsc_offset) KVM_X86_OP(get_l2_tsc_multiplier) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 15601a221213..809788b343bf 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1759,6 +1759,13 @@ struct kvm_x86_ops { void (*load_mmu_pgd)(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level); + /* Update external mapping with page table link. */ + int (*link_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + /* Update the external page table from spte getting set. */ + int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 8e584be64523..865b5805f929 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -440,6 +440,59 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); } +static void *get_external_spt(gfn_t gfn, u64 new_spte, int level) +{ + if (is_shadow_present_pte(new_spte) && !is_last_spte(new_spte, level)) { + struct kvm_mmu_page *sp = spte_to_child_sp(new_spte); + + WARN_ON_ONCE(sp->role.level + 1 != level); + WARN_ON_ONCE(sp->gfn != gfn); + return sp->external_spt; + } + + return NULL; +} + +static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sptep, + gfn_t gfn, u64 old_spte, + u64 new_spte, int level) +{ + bool was_present = is_shadow_present_pte(old_spte); + bool is_present = is_shadow_present_pte(new_spte); + bool is_leaf = is_present && is_last_spte(new_spte, level); + kvm_pfn_t new_pfn = spte_to_pfn(new_spte); + int ret = 0; + + KVM_BUG_ON(was_present, kvm); + + lockdep_assert_held(&kvm->mmu_lock); + /* + * We need to lock out other updates to the SPTE until the external + * page table has been modified. Use FROZEN_SPTE similar to + * the zapping case. + */ + if (!try_cmpxchg64(rcu_dereference(sptep), &old_spte, FROZEN_SPTE)) + return -EBUSY; + + /* + * Use different call to either set up middle level + * external page table, or leaf. + */ + if (is_leaf) { + ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn); + } else { + void *external_spt = get_external_spt(gfn, new_spte, level); + + KVM_BUG_ON(!external_spt, kvm); + ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt); + } + if (ret) + __kvm_tdp_mmu_write_spte(sptep, old_spte); + else + __kvm_tdp_mmu_write_spte(sptep, new_spte); + return ret; +} + /** * handle_changed_spte - handle bookkeeping associated with an SPTE change * @kvm: kvm instance @@ -540,11 +593,10 @@ static void handle_changed_spte(struct kvm *kvm, int as_id, gfn_t gfn, handle_removed_pt(kvm, spte_to_child_pt(old_spte, level), shared); } -static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, +static inline int __must_check __tdp_mmu_set_spte_atomic(struct kvm *kvm, + struct tdp_iter *iter, u64 new_spte) { - u64 *sptep = rcu_dereference(iter->sptep); - /* * The caller is responsible for ensuring the old SPTE is not a FROZEN * SPTE. KVM should never attempt to zap or manipulate a FROZEN SPTE, @@ -553,15 +605,27 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct tdp_iter *iter, */ WARN_ON_ONCE(iter->yielded || is_frozen_spte(iter->old_spte)); - /* - * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs and - * does not hold the mmu_lock. On failure, i.e. if a different logical - * CPU modified the SPTE, try_cmpxchg64() updates iter->old_spte with - * the current value, so the caller operates on fresh data, e.g. if it - * retries tdp_mmu_set_spte_atomic() - */ - if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) - return -EBUSY; + if (is_mirror_sptep(iter->sptep) && !is_frozen_spte(new_spte)) { + int ret; + + ret = set_external_spte_present(kvm, iter->sptep, iter->gfn, + iter->old_spte, new_spte, iter->level); + if (ret) + return ret; + } else { + u64 *sptep = rcu_dereference(iter->sptep); + + /* + * Note, fast_pf_fix_direct_spte() can also modify TDP MMU SPTEs + * and does not hold the mmu_lock. On failure, i.e. if a + * different logical CPU modified the SPTE, try_cmpxchg64() + * updates iter->old_spte with the current value, so the caller + * operates on fresh data, e.g. if it retries + * tdp_mmu_set_spte_atomic() + */ + if (!try_cmpxchg64(sptep, &iter->old_spte, new_spte)) + return -EBUSY; + } return 0; } @@ -591,7 +655,7 @@ static inline int __must_check tdp_mmu_set_spte_atomic(struct kvm *kvm, lockdep_assert_held_read(&kvm->mmu_lock); - ret = __tdp_mmu_set_spte_atomic(iter, new_spte); + ret = __tdp_mmu_set_spte_atomic(kvm, iter, new_spte); if (ret) return ret; @@ -631,6 +695,14 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, old_spte = kvm_tdp_mmu_write_spte(sptep, old_spte, new_spte, level); handle_changed_spte(kvm, as_id, gfn, old_spte, new_spte, level, false); + + /* + * Users that do non-atomic setting of PTEs don't operate on mirror + * roots, so don't handle it and bug the VM if it's seen. + */ + if (is_mirror_sptep(sptep)) + KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm); + return old_spte; } From 94faba8999b95d86a2eba47d2d78925dc80f38ed Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:27 -0700 Subject: [PATCH 16/20] KVM: x86/tdp_mmu: Propagate tearing down mirror page tables Integrate hooks for mirroring page table operations for cases where TDX will zap PTEs or free page tables. Like other Coco technologies, TDX has the concept of private and shared memory. For TDX the private and shared mappings are managed on separate EPT roots. The private half is managed indirectly though calls into a protected runtime environment called the TDX module, where the shared half is managed within KVM in normal page tables. Since calls into the TDX module are relatively slow, walking private page tables by making calls into the TDX module would not be efficient. Because of this, previous changes have taught the TDP MMU to keep a mirror root, which is separate, unmapped TDP root that private operations can be directed to. Currently this root is disconnected from the guest. Now add plumbing to propagate changes to the "external" page tables being mirrored. Just create the x86_ops for now, leave plumbing the operations into the TDX module for future patches. Add two operations for tearing down page tables, one for freeing page tables (free_external_spt) and one for zapping PTEs (remove_external_spte). Define them such that remove_external_spte will perform a TLB flush as well. (in TDX terms "ensure there are no active translations"). TDX MMU support will exclude certain MMU operations, so only plug in the mirroring x86 ops where they will be needed. For zapping/freeing, only hook tdp_mmu_iter_set_spte() which is used for mapping and linking PTs. Don't bother hooking tdp_mmu_set_spte_atomic() as it is only used for zapping PTEs in operations unsupported by TDX: zapping collapsible PTEs and kvm_mmu_zap_all_fast(). In previous changes to address races around concurrent populating using tdp_mmu_set_spte_atomic(), a solution was introduced to temporarily set FROZEN_SPTE in the mirrored page tables while performing the external operations. Such a solution is not needed for the tear down paths in TDX as these will always be performed with the mmu_lock held for write. Sprinkle some KVM_BUG_ON()s to reflect this. Signed-off-by: Isaku Yamahata Co-developed-by: Kai Huang Signed-off-by: Kai Huang Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Co-developed-by: Rick Edgecombe Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-16-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/kvm-x86-ops.h | 2 ++ arch/x86/include/asm/kvm_host.h | 8 +++++ arch/x86/kvm/mmu/tdp_mmu.c | 51 +++++++++++++++++++++++++++++- 3 files changed, 60 insertions(+), 1 deletion(-) diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index dbbdaa8586ab..c82cd6635402 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -96,6 +96,8 @@ KVM_X86_OP_OPTIONAL_RET0(get_mt_mask) KVM_X86_OP(load_mmu_pgd) KVM_X86_OP_OPTIONAL(link_external_spt) KVM_X86_OP_OPTIONAL(set_external_spte) +KVM_X86_OP_OPTIONAL(free_external_spt) +KVM_X86_OP_OPTIONAL(remove_external_spte) KVM_X86_OP(has_wbinvd_exit) KVM_X86_OP(get_l2_tsc_offset) KVM_X86_OP(get_l2_tsc_multiplier) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 809788b343bf..0dad81d7e988 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1766,6 +1766,14 @@ struct kvm_x86_ops { int (*set_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, kvm_pfn_t pfn_for_gfn); + /* Update external page tables for page table about to be freed. */ + int (*free_external_spt)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + void *external_spt); + + /* Update external page table from spte getting removed, and flush TLB. */ + int (*remove_external_spte)(struct kvm *kvm, gfn_t gfn, enum pg_level level, + kvm_pfn_t pfn_for_gfn); + bool (*has_wbinvd_exit)(void); u64 (*get_l2_tsc_offset)(struct kvm_vcpu *vcpu); diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 865b5805f929..7ebadc7f2640 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -340,6 +340,29 @@ static void tdp_mmu_unlink_sp(struct kvm *kvm, struct kvm_mmu_page *sp) spin_unlock(&kvm->arch.tdp_mmu_pages_lock); } +static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte, + int level) +{ + kvm_pfn_t old_pfn = spte_to_pfn(old_spte); + int ret; + + /* + * External (TDX) SPTEs are limited to PG_LEVEL_4K, and external + * PTs are removed in a special order, involving free_external_spt(). + * But remove_external_spte() will be called on non-leaf PTEs via + * __tdp_mmu_zap_root(), so avoid the error the former would return + * in this case. + */ + if (!is_last_spte(old_spte, level)) + return; + + /* Zapping leaf spte is allowed only when write lock is held. */ + lockdep_assert_held_write(&kvm->mmu_lock); + /* Because write lock is held, operation should success. */ + ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn); + KVM_BUG_ON(ret, kvm); +} + /** * handle_removed_pt() - handle a page table removed from the TDP structure * @@ -435,6 +458,23 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared) } handle_changed_spte(kvm, kvm_mmu_page_as_id(sp), gfn, old_spte, FROZEN_SPTE, level, shared); + + if (is_mirror_sp(sp)) { + KVM_BUG_ON(shared, kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } + } + + if (is_mirror_sp(sp) && + WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level, + sp->external_spt))) { + /* + * Failed to free page table page in mirror page table and + * there is nothing to do further. + * Intentionally leak the page to prevent the kernel from + * accessing the encrypted page. + */ + sp->external_spt = NULL; } call_rcu(&sp->rcu_head, tdp_mmu_free_sp_rcu_callback); @@ -608,6 +648,13 @@ static inline int __must_check __tdp_mmu_set_spte_atomic(struct kvm *kvm, if (is_mirror_sptep(iter->sptep) && !is_frozen_spte(new_spte)) { int ret; + /* + * Users of atomic zapping don't operate on mirror roots, + * so don't handle it and bug the VM if it's seen. + */ + if (KVM_BUG_ON(!is_shadow_present_pte(new_spte), kvm)) + return -EBUSY; + ret = set_external_spte_present(kvm, iter->sptep, iter->gfn, iter->old_spte, new_spte, iter->level); if (ret) @@ -700,8 +747,10 @@ static u64 tdp_mmu_set_spte(struct kvm *kvm, int as_id, tdp_ptep_t sptep, * Users that do non-atomic setting of PTEs don't operate on mirror * roots, so don't handle it and bug the VM if it's seen. */ - if (is_mirror_sptep(sptep)) + if (is_mirror_sptep(sptep)) { KVM_BUG_ON(is_shadow_present_pte(new_spte), kvm); + remove_external_spte(kvm, gfn, old_spte, level); + } return old_spte; } From a89ecbb56bc722a1ca7a11f5554ae3d8f1d73887 Mon Sep 17 00:00:00 2001 From: Isaku Yamahata Date: Thu, 18 Jul 2024 14:12:28 -0700 Subject: [PATCH 17/20] KVM: x86/tdp_mmu: Take root types for kvm_tdp_mmu_invalidate_all_roots() Rename kvm_tdp_mmu_invalidate_all_roots() to kvm_tdp_mmu_invalidate_roots(), and make it enum kvm_tdp_mmu_root_types as an argument. kvm_tdp_mmu_invalidate_roots() is called with different root types. For kvm_mmu_zap_all_fast() it only operates on shared roots. But when tearing down a VM it needs to invalidate all roots. Have the callers only invalidate the required roots instead of all roots. Within kvm_tdp_mmu_invalidate_roots(), respect the root type passed by checking the root type in root iterator. Suggested-by: Chao Gao Signed-off-by: Isaku Yamahata Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-17-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 9 +++++++-- arch/x86/kvm/mmu/tdp_mmu.c | 15 +++++++++++++-- arch/x86/kvm/mmu/tdp_mmu.h | 3 ++- 3 files changed, 22 insertions(+), 5 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 7a71e6077094..1fac5971604f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6454,8 +6454,13 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm) * write and in the same critical section as making the reload request, * e.g. before kvm_zap_obsolete_pages() could drop mmu_lock and yield. */ - if (tdp_mmu_enabled) - kvm_tdp_mmu_invalidate_all_roots(kvm); + if (tdp_mmu_enabled) { + /* + * External page tables don't support fast zapping, therefore + * their mirrors must be invalidated separately by the caller. + */ + kvm_tdp_mmu_invalidate_roots(kvm, KVM_DIRECT_ROOTS); + } /* * Notify all vcpus to reload its shadow page table and flush TLB. diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index 7ebadc7f2640..ca2b95b75ca4 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -37,7 +37,7 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm) * for zapping and thus puts the TDP MMU's reference to each root, i.e. * ultimately frees all roots. */ - kvm_tdp_mmu_invalidate_all_roots(kvm); + kvm_tdp_mmu_invalidate_roots(kvm, KVM_VALID_ROOTS); kvm_tdp_mmu_zap_invalidated_roots(kvm, false); WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages)); @@ -1070,10 +1070,18 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared) * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference. * See kvm_tdp_mmu_alloc_root(). */ -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types) { struct kvm_mmu_page *root; + /* + * Invalidating invalid roots doesn't make sense, prevent developers from + * having to think about it. + */ + if (WARN_ON_ONCE(root_types & KVM_INVALID_ROOTS)) + root_types &= ~KVM_INVALID_ROOTS; + /* * mmu_lock must be held for write to ensure that a root doesn't become * invalid while there are active readers (invalidating a root while @@ -1095,6 +1103,9 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm) * or get/put references to roots. */ list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) { + if (!tdp_mmu_root_match(root, root_types)) + continue; + /* * Note, invalid roots can outlive a memslot update! Invalid * roots must be *zapped* before the memslot update completes, diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index 9887441cd703..52acf99d40a0 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.h +++ b/arch/x86/kvm/mmu/tdp_mmu.h @@ -66,7 +66,8 @@ static inline struct kvm_mmu_page *tdp_mmu_get_root(struct kvm_vcpu *vcpu, bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool 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); +void kvm_tdp_mmu_invalidate_roots(struct kvm *kvm, + enum kvm_tdp_mmu_root_types root_types); void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm, bool shared); int kvm_tdp_mmu_map(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); From df4af9f89cd853f7a06187dbbfd410fc6fd73bce Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 18 Jul 2024 14:12:29 -0700 Subject: [PATCH 18/20] KVM: x86/tdp_mmu: Don't zap valid mirror roots in kvm_tdp_mmu_zap_all() Don't zap valid mirror roots in kvm_tdp_mmu_zap_all(), which in effect is only direct roots (invalid and valid). For TDX, kvm_tdp_mmu_zap_all() is only called during MMU notifier release. Since, mirrored EPT comes from guest mem, it will never be mapped to userspace, and won't apply. But in addition to be unnecessary, mirrored EPT is cleaned up in a special way during VM destruction. Pass the KVM_INVALID_ROOTS bit into __for_each_tdp_mmu_root_yield_safe() as well, to clean up invalid direct roots, as is the current behavior. While at it, remove an obsolete reference to work item-based zapping. Co-developed-by: Yan Zhao Signed-off-by: Yan Zhao Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-18-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/tdp_mmu.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index ca2b95b75ca4..046b6ba31197 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -999,19 +999,21 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm) struct kvm_mmu_page *root; /* - * Zap all roots, including invalid roots, as all SPTEs must be dropped - * before returning to the caller. Zap directly even if the root is - * also being zapped by a worker. Walking zapped top-level SPTEs isn't - * all that expensive and mmu_lock is already held, which means the - * worker has yielded, i.e. flushing the work instead of zapping here - * isn't guaranteed to be any faster. + * Zap all direct roots, including invalid direct roots, as all direct + * SPTEs must be dropped before returning to the caller. For TDX, mirror + * roots don't need handling in response to the mmu notifier (the caller). + * + * Zap directly even if the root is also being zapped by a concurrent + * "fast zap". Walking zapped top-level SPTEs isn't all that expensive + * and mmu_lock is already held, which means the other thread has yielded. * * A TLB flush is unnecessary, KVM zaps everything if and only the VM * is being destroyed or the userspace VMM has exited. In both cases, * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request. */ lockdep_assert_held_write(&kvm->mmu_lock); - for_each_tdp_mmu_root_yield_safe(kvm, root) + __for_each_tdp_mmu_root_yield_safe(kvm, root, -1, + KVM_DIRECT_ROOTS | KVM_INVALID_ROOTS) tdp_mmu_zap_root(kvm, root, false); } From 2c3412e999738bfd60859c493ff47f5c268814a3 Mon Sep 17 00:00:00 2001 From: Rick Edgecombe Date: Thu, 18 Jul 2024 14:12:30 -0700 Subject: [PATCH 19/20] KVM: x86/mmu: Prevent aliased memslot GFNs Add a few sanity checks to prevent memslot GFNs from ever having alias bits set. Like other Coco technologies, TDX has the concept of private and shared memory. For TDX the private and shared mappings are managed on separate EPT roots. The private half is managed indirectly though calls into a protected runtime environment called the TDX module, where the shared half is managed within KVM in normal page tables. For TDX, the shared half will be mapped in the higher alias, with a "shared bit" set in the GPA. However, KVM will still manage it with the same memslots as the private half. This means memslot looks ups and zapping operations will be provided with a GFN without the shared bit set. If these memslot GFNs ever had the bit that selects between the two aliases it could lead to unexpected behavior in the complicated code that directs faulting or zapping operations between the roots that map the two aliases. As a safety measure, prevent memslots from being set at a GFN range that contains the alias bit. Also, check in the kvm_faultin_pfn() for the fault path. This later check does less today, as the alias bits are specifically stripped from the GFN being checked, however future code could possibly call in to the fault handler in a way that skips this stripping. Since kvm_faultin_pfn() now has many references to vcpu->kvm, extract it to local variable. Link: https://lore.kernel.org/kvm/ZpbKqG_ZhCWxl-Fc@google.com/ Suggested-by: Sean Christopherson Signed-off-by: Rick Edgecombe Message-ID: <20240718211230.1492011-19-rick.p.edgecombe@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu.h | 5 +++++ arch/x86/kvm/mmu/mmu.c | 10 +++++++--- arch/x86/kvm/x86.c | 3 +++ 3 files changed, 15 insertions(+), 3 deletions(-) diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index d1775a38ffd3..878061d0063e 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -313,4 +313,9 @@ static inline bool kvm_is_addr_direct(struct kvm *kvm, gpa_t gpa) return !gpa_direct_bits || (gpa & gpa_direct_bits); } + +static inline bool kvm_is_gfn_alias(struct kvm *kvm, gfn_t gfn) +{ + return gfn & kvm_gfn_direct_bits(kvm); +} #endif diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 1fac5971604f..4489d192162e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4391,8 +4391,12 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault, unsigned int access) { struct kvm_memory_slot *slot = fault->slot; + struct kvm *kvm = vcpu->kvm; int ret; + if (KVM_BUG_ON(kvm_is_gfn_alias(kvm, fault->gfn), kvm)) + return -EFAULT; + /* * Note that the mmu_invalidate_seq also serves to detect a concurrent * change in attributes. is_page_fault_stale() will detect an @@ -4406,7 +4410,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * Now that we have a snapshot of mmu_invalidate_seq we can check for a * private vs. shared mismatch. */ - if (fault->is_private != kvm_mem_is_private(vcpu->kvm, fault->gfn)) { + if (fault->is_private != kvm_mem_is_private(kvm, fault->gfn)) { kvm_mmu_prepare_memory_fault_exit(vcpu, fault); return -EFAULT; } @@ -4468,7 +4472,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * *guaranteed* to need to retry, i.e. waiting until mmu_lock is held * to detect retry guarantees the worst case latency for the vCPU. */ - if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) return RET_PF_RETRY; ret = __kvm_mmu_faultin_pfn(vcpu, fault); @@ -4488,7 +4492,7 @@ static int kvm_mmu_faultin_pfn(struct kvm_vcpu *vcpu, * overall cost of failing to detect the invalidation until after * mmu_lock is acquired. */ - if (mmu_invalidate_retry_gfn_unsafe(vcpu->kvm, fault->mmu_seq, fault->gfn)) { + if (mmu_invalidate_retry_gfn_unsafe(kvm, fault->mmu_seq, fault->gfn)) { kvm_mmu_finish_page_fault(vcpu, fault, RET_PF_RETRY); return RET_PF_RETRY; } diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index ad3fc35703a8..1dffea9c3b11 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13010,6 +13010,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm, if ((new->base_gfn + new->npages - 1) > kvm_mmu_max_gfn()) return -EINVAL; + if (kvm_is_gfn_alias(kvm, new->base_gfn + new->npages - 1)) + return -EINVAL; + return kvm_alloc_memslot_metadata(kvm, new); } From 7c54803863002989ac979adc14847fea5c80bf4b Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Mon, 13 Jan 2025 10:11:38 +0800 Subject: [PATCH 20/20] KVM: x86/mmu: Return RET_PF* instead of 1 in kvm_mmu_page_fault() Return RET_PF* (excluding RET_PF_EMULATE/RET_PF_CONTINUE/RET_PF_INVALID) instead of 1 in kvm_mmu_page_fault(). The callers of kvm_mmu_page_fault() are KVM page fault handlers (i.e., npf_interception(), handle_ept_misconfig(), __vmx_handle_ept_violation(), kvm_handle_page_fault()). They either check if the return value is > 0 (as in npf_interception()) or pass it further to vcpu_run() to decide whether to break out of the kernel loop and return to the user when r <= 0. Therefore, returning any positive value is equivalent to returning 1. Warn if r == RET_PF_CONTINUE (which should not be a valid value) to ensure a positive return value. This is a preparation to allow TDX's EPT violation handler to check the RET_PF* value and retry internally for RET_PF_RETRY. No functional changes are intended. Signed-off-by: Yan Zhao Message-ID: <20250113021138.18875-1-yan.y.zhao@intel.com> Signed-off-by: Paolo Bonzini --- arch/x86/kvm/mmu/mmu.c | 10 +++++++++- arch/x86/kvm/mmu/mmu_internal.h | 12 +++++++++--- 2 files changed, 18 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 4489d192162e..5e2d3de7328f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -6111,8 +6111,16 @@ int noinline kvm_mmu_page_fault(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa, u64 err else if (r == RET_PF_SPURIOUS) vcpu->stat.pf_spurious++; + /* + * None of handle_mmio_page_fault(), kvm_mmu_do_page_fault(), or + * kvm_mmu_write_protect_fault() return RET_PF_CONTINUE. + * kvm_mmu_do_page_fault() only uses RET_PF_CONTINUE internally to + * indicate continuing the page fault handling until to the final + * page table mapping phase. + */ + WARN_ON_ONCE(r == RET_PF_CONTINUE); if (r != RET_PF_EMULATE) - return 1; + return r; emulate: return x86_emulate_instruction(vcpu, cr2_or_gpa, emulation_type, insn, diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 957636660149..4fde91cade1b 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -315,9 +315,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault); * tracepoints via TRACE_DEFINE_ENUM() in mmutrace.h * * Note, all values must be greater than or equal to zero so as not to encroach - * on -errno return values. Somewhat arbitrarily use '0' for CONTINUE, which - * will allow for efficient machine code when checking for CONTINUE, e.g. - * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero. + * on -errno return values. */ enum { RET_PF_CONTINUE = 0, @@ -329,6 +327,14 @@ enum { RET_PF_SPURIOUS, }; +/* + * Define RET_PF_CONTINUE as 0 to allow for + * - efficient machine code when checking for CONTINUE, e.g. + * "TEST %rax, %rax, JNZ", as all "stop!" values are non-zero, + * - kvm_mmu_do_page_fault() to return other RET_PF_* as a positive value. + */ +static_assert(RET_PF_CONTINUE == 0); + static inline void kvm_mmu_prepare_memory_fault_exit(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault) {