diff options
| -rw-r--r-- | arch/x86/include/asm/kvm-x86-ops.h | 4 | ||||
| -rw-r--r-- | arch/x86/include/asm/kvm_host.h | 31 | ||||
| -rw-r--r-- | arch/x86/include/uapi/asm/kvm.h | 1 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu.h | 31 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu.c | 60 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/mmu_internal.h | 76 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/spte.h | 5 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_iter.c | 10 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_iter.h | 21 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.c | 325 | ||||
| -rw-r--r-- | arch/x86/kvm/mmu/tdp_mmu.h | 51 | ||||
| -rw-r--r-- | arch/x86/kvm/x86.c | 3 | ||||
| -rw-r--r-- | include/linux/kvm_host.h | 13 | ||||
| -rw-r--r-- | virt/kvm/guest_memfd.c | 36 | ||||
| -rw-r--r-- | virt/kvm/kvm_main.c | 14 |
15 files changed, 554 insertions, 127 deletions
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 7b4536ff3834..c35550581da0 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -93,6 +93,10 @@ 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_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 9f8c319fe67e..2f442701dc75 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 @@ -457,6 +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; @@ -830,6 +833,11 @@ 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. @@ -1549,6 +1557,8 @@ 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 { @@ -1761,6 +1771,21 @@ 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); + + /* 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/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 */ diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index caec3d11638d..050a0e229a4d 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; @@ -287,4 +296,26 @@ 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; +} + +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); +} + +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 74fa38ebddbf..26b4ba7e7cb5 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); } @@ -3656,8 +3663,13 @@ 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) { + 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; + } write_lock(&vcpu->kvm->mmu_lock); r = make_mmu_pages_available(vcpu); @@ -4379,8 +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 @@ -4394,7 +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; } @@ -4456,7 +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); @@ -4476,7 +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; } @@ -6095,8 +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, @@ -6272,6 +6296,7 @@ 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; @@ -6441,8 +6466,13 @@ 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. @@ -6467,7 +6497,7 @@ 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) @@ -7220,6 +7250,12 @@ 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); @@ -7452,6 +7488,12 @@ 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/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h index 72de71f4bc8b..75f00598289d 100644 --- a/arch/x86/kvm/mmu/mmu_internal.h +++ b/arch/x86/kvm/mmu/mmu_internal.h @@ -6,6 +6,8 @@ #include <linux/kvm_host.h> #include <asm/kvm_host.h> +#include "mmu.h" + #ifdef CONFIG_KVM_PROVE_MMU #define KVM_MMU_WARN_ON(x) WARN_ON_ONCE(x) #else @@ -101,7 +103,22 @@ 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 +141,6 @@ 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 +159,34 @@ 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) +{ + /* + * 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 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) { /* @@ -229,7 +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. */ @@ -268,9 +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, @@ -282,6 +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) { @@ -317,7 +370,12 @@ 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/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 && 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 2880fd392e0c..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 */ @@ -122,18 +124,23 @@ 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) \ - for (tdp_iter_start(&iter, root, min_level, start); \ - iter.valid && iter.gfn < end; \ +#define for_each_tdp_pte_min_level(iter, kvm, root, min_level, start, 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(iter, root, start, end) \ - for_each_tdp_pte_min_level(iter, root, PG_LEVEL_4K, start, end) +#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 2f15e0e33903..046b6ba31197 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -37,8 +37,8 @@ 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_zap_invalidated_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)); WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots)); @@ -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); } @@ -91,19 +92,33 @@ 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, + enum kvm_tdp_mmu_root_types types) +{ + if (WARN_ON_ONCE(!(types & KVM_VALID_ROOTS))) + return false; + + if (root->role.invalid && !(types & KVM_INVALID_ROOTS)) + return false; + + if (likely(!is_mirror_sp(root))) + return types & KVM_DIRECT_ROOTS; + return types & KVM_MIRROR_ROOTS; +} + /* * 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; @@ -124,7 +139,7 @@ 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, types) && kvm_tdp_mmu_get_root(next_root)) break; @@ -149,20 +164,20 @@ 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, @@ -171,18 +186,15 @@ 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) || \ - ((_only_valid) && (_root)->role.invalid))) { \ + !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) - #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) { @@ -223,7 +235,7 @@ 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, bool mirror) { struct kvm_mmu *mmu = vcpu->arch.mmu; union kvm_mmu_page_role role = mmu->root_role; @@ -231,6 +243,9 @@ int 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. @@ -282,9 +297,12 @@ 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; - return 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, @@ -322,6 +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 * @@ -417,11 +458,81 @@ 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); } +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 @@ -522,11 +633,10 @@ 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, @@ -535,15 +645,34 @@ 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; + + /* + * 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) + 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; } @@ -573,7 +702,7 @@ 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; @@ -613,6 +742,16 @@ 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); + remove_external_spte(kvm, gfn, old_spte, level); + } + return old_spte; } @@ -625,18 +764,18 @@ 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, _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) @@ -705,10 +844,7 @@ 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, 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; @@ -812,7 +948,7 @@ 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; @@ -863,19 +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); } @@ -883,11 +1021,14 @@ 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 +1046,7 @@ 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 +1056,10 @@ 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); } /* @@ -928,11 +1072,19 @@ void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm) * 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 * there are active readers may or may not be problematic in practice, @@ -953,6 +1105,9 @@ 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, @@ -1068,7 +1223,7 @@ 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_mmu_page *root = tdp_mmu_get_root_for_fault(vcpu, fault); struct kvm *kvm = vcpu->kvm; struct tdp_iter iter; struct kvm_mmu_page *sp; @@ -1080,7 +1235,7 @@ 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, root, fault->gfn, fault->gfn + 1) { int r; if (fault->nx_huge_page_workaround_enabled) @@ -1107,13 +1262,18 @@ 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 @@ -1148,12 +1308,16 @@ 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, false) + 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); @@ -1193,20 +1357,24 @@ 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, 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; @@ -1247,7 +1415,7 @@ 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; @@ -1366,7 +1534,7 @@ 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; @@ -1464,7 +1632,7 @@ 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)) @@ -1512,7 +1680,7 @@ 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; @@ -1566,7 +1734,7 @@ 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. @@ -1600,7 +1768,7 @@ 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; @@ -1681,7 +1849,7 @@ 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; @@ -1729,14 +1897,14 @@ 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, mmu, gfn, gfn + 1) { + tdp_mmu_for_each_pte(iter, vcpu->kvm, root, gfn, gfn + 1) { leaf = iter.level; sptes[leaf] = iter.old_spte; } @@ -1758,11 +1926,12 @@ 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) { + /* 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; - 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, root, gfn, gfn + 1) { *spte = iter.old_spte; sptep = iter.sptep; } diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h index f03ca0dd13d9..52acf99d40a0 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, bool private); __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root) { @@ -19,11 +19,56 @@ __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_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); -void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm); -void kvm_tdp_mmu_zap_invalidated_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); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index f56d9ccc54e1..6e248152fa13 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13034,6 +13034,9 @@ 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); } diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 9df590e8f3da..3cb9a32a6330 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); @@ -596,7 +602,12 @@ 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..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) { @@ -259,15 +261,19 @@ 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 +302,7 @@ 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 +513,11 @@ 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 +553,12 @@ 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 +570,12 @@ 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); } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index e0b9d6dd6a85..faf10671eed2 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)} = @@ -2403,6 +2408,14 @@ 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); @@ -2459,6 +2472,7 @@ 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, |