From: Sean Christopherson Start plumbing in guest_memfd support for in-place private<=>shared conversions by tracking attributes via a maple tree. KVM currently tracks private vs. shared attributes on a per-VM basis, which made sense when a guest_memfd _only_ supported private memory, but tracking per-VM simply can't work for in-place conversions as the shareability of a given page needs to be per-gmem_inode, not per-VM. Use the filemap invalidation lock to protect the maple tree, as taking the lock for read when faulting in memory (for userspace or the guest) isn't expected to result in meaningful contention, and using a separate lock would add significant complexity (avoid deadlock is quite difficult). Signed-off-by: Sean Christopherson Co-developed-by: Ackerley Tng Signed-off-by: Ackerley Tng Co-developed-by: Vishal Annapurve Signed-off-by: Vishal Annapurve Co-developed-by: Fuad Tabba Signed-off-by: Fuad Tabba --- virt/kvm/guest_memfd.c | 133 +++++++++++++++++++++++++++++++++++++++++++------ 1 file changed, 117 insertions(+), 16 deletions(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 69c9d6d546b28..5011d38820d0d 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -33,6 +34,13 @@ struct gmem_inode { struct list_head gmem_file_list; u64 flags; + /* + * Every index in this inode, whether memory is populated or + * not, is tracked in attributes. The entire range of indices, + * corresponding to the size of this inode, is represented in + * this maple tree. + */ + struct maple_tree attributes; }; static __always_inline struct gmem_inode *GMEM_I(struct inode *inode) @@ -60,6 +68,24 @@ static pgoff_t kvm_gmem_get_index(struct kvm_memory_slot *slot, gfn_t gfn) return gfn - slot->base_gfn + slot->gmem.pgoff; } +static u64 kvm_gmem_get_attributes(struct inode *inode, pgoff_t index) +{ + struct maple_tree *mt = &GMEM_I(inode)->attributes; + void *entry = mtree_load(mt, index); + + return WARN_ON_ONCE(!entry) ? 0 : xa_to_value(entry); +} + +static bool kvm_gmem_is_private_mem(struct inode *inode, pgoff_t index) +{ + return kvm_gmem_get_attributes(inode, index) & KVM_MEMORY_ATTRIBUTE_PRIVATE; +} + +static bool kvm_gmem_is_shared_mem(struct inode *inode, pgoff_t index) +{ + return !kvm_gmem_is_private_mem(inode, index); +} + static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, pgoff_t index, struct folio *folio) { @@ -397,10 +423,13 @@ static vm_fault_t kvm_gmem_fault_user_mapping(struct vm_fault *vmf) if (((loff_t)vmf->pgoff << PAGE_SHIFT) >= i_size_read(inode)) return VM_FAULT_SIGBUS; - if (!(GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED)) - return VM_FAULT_SIGBUS; + filemap_invalidate_lock_shared(inode->i_mapping); + if (kvm_gmem_is_shared_mem(inode, vmf->pgoff)) + folio = kvm_gmem_get_folio(inode, vmf->pgoff); + else + folio = ERR_PTR(-EACCES); + filemap_invalidate_unlock_shared(inode->i_mapping); - folio = kvm_gmem_get_folio(inode, vmf->pgoff); if (IS_ERR(folio)) { if (PTR_ERR(folio) == -EAGAIN) return VM_FAULT_RETRY; @@ -556,6 +585,51 @@ bool __weak kvm_arch_supports_gmem_init_shared(struct kvm *kvm) return true; } +static int kvm_gmem_init_inode(struct inode *inode, loff_t size, u64 flags) +{ + struct gmem_inode *gi = GMEM_I(inode); + MA_STATE(mas, &gi->attributes, 0, (size >> PAGE_SHIFT) - 1); + u64 attrs; + int r; + + inode->i_op = &kvm_gmem_iops; + inode->i_mapping->a_ops = &kvm_gmem_aops; + inode->i_mode |= S_IFREG; + inode->i_size = size; + mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); + + /* + * guest_memfd memory is neither migratable nor swappable: set + * inaccessible to gate off both. + */ + mapping_set_inaccessible(inode->i_mapping); + WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); + + gi->flags = flags; + + mt_set_external_lock(&gi->attributes, + &inode->i_mapping->invalidate_lock); + + /* + * Store default attributes for the entire gmem instance. Ensuring every + * index is represented in the maple tree at all times simplifies the + * conversion and merging logic. + */ + attrs = gi->flags & GUEST_MEMFD_FLAG_INIT_SHARED ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE; + + /* + * Acquire the invalidation lock purely to make lockdep happy. The + * maple tree library expects all stores to be protected via the lock, + * and the library can't know when the tree is reachable only by the + * caller, as is the case here. + */ + filemap_invalidate_lock(inode->i_mapping); + r = mas_store_gfp(&mas, xa_mk_value(attrs), GFP_KERNEL); + filemap_invalidate_unlock(inode->i_mapping); + + return r; +} + static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) { static const char *name = "[kvm-gmem]"; @@ -586,16 +660,9 @@ static int __kvm_gmem_create(struct kvm *kvm, loff_t size, u64 flags) goto err_fops; } - inode->i_op = &kvm_gmem_iops; - inode->i_mapping->a_ops = &kvm_gmem_aops; - inode->i_mode |= S_IFREG; - inode->i_size = size; - mapping_set_gfp_mask(inode->i_mapping, GFP_HIGHUSER); - mapping_set_inaccessible(inode->i_mapping); - /* Unmovable mappings are supposed to be marked unevictable as well. */ - WARN_ON_ONCE(!mapping_unevictable(inode->i_mapping)); - - GMEM_I(inode)->flags = flags; + err = kvm_gmem_init_inode(inode, size, flags); + if (err) + goto err_inode; file = alloc_file_pseudo(inode, kvm_gmem_mnt, name, O_RDWR, &kvm_gmem_fops); if (IS_ERR(file)) { @@ -797,9 +864,13 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, if (!file) return -EFAULT; + filemap_invalidate_lock_shared(file_inode(file)->i_mapping); + folio = __kvm_gmem_get_pfn(file, slot, index, pfn, max_order); - if (IS_ERR(folio)) - return PTR_ERR(folio); + if (IS_ERR(folio)) { + r = PTR_ERR(folio); + goto out; + } if (!folio_test_uptodate(folio)) { clear_highpage(folio_page(folio, 0)); @@ -815,6 +886,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, else folio_put(folio); +out: + filemap_invalidate_unlock_shared(file_inode(file)->i_mapping); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); @@ -944,6 +1017,15 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) mpol_shared_policy_init(&gi->policy, NULL); + /* + * Memory attributes are protected by the filemap invalidation lock, but + * the lock structure isn't available at this time. Immediately mark + * maple tree as using external locking so that accessing the tree + * before it's fully initialized results in NULL pointer dereferences + * and not more subtle bugs. + */ + mt_init_flags(&gi->attributes, MT_FLAGS_LOCK_EXTERN | MT_FLAGS_USE_RCU); + gi->flags = 0; INIT_LIST_HEAD(&gi->gmem_file_list); return &gi->vfs_inode; @@ -951,7 +1033,26 @@ static struct inode *kvm_gmem_alloc_inode(struct super_block *sb) static void kvm_gmem_destroy_inode(struct inode *inode) { - mpol_free_shared_policy(&GMEM_I(inode)->policy); + struct gmem_inode *gi = GMEM_I(inode); + + mpol_free_shared_policy(&gi->policy); + + /* + * Note! Checking for an empty tree is functionally necessary + * to avoid explosions if the tree hasn't been fully + * initialized, i.e. if the inode is being destroyed before + * guest_memfd can set the external lock, lockdep would find + * that the tree's internal ma_lock was not held. + */ + if (!mtree_empty(&gi->attributes)) { + /* + * Acquire the invalidation lock purely to make lockdep happy, + * the inode is unreachable at this point. + */ + filemap_invalidate_lock(inode->i_mapping); + __mt_destroy(&gi->attributes); + filemap_invalidate_unlock(inode->i_mapping); + } } static void kvm_gmem_free_inode(struct inode *inode) -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Rename the per-VM memory attributes Kconfig to make it explicitly about per-VM attributes in anticipation of adding memory attributes support to guest_memfd, at which point it will be possible (and desirable) to have memory attributes without the per-VM support, even in x86. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/include/asm/kvm_host.h | 2 +- arch/x86/kvm/Kconfig | 6 +++--- arch/x86/kvm/mmu/mmu.c | 2 +- arch/x86/kvm/x86.c | 2 +- include/linux/kvm_host.h | 8 ++++---- include/trace/events/kvm.h | 4 ++-- virt/kvm/Kconfig | 2 +- virt/kvm/kvm_main.c | 14 +++++++------- 8 files changed, 20 insertions(+), 20 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index c470e40a00aa4..60b997764beef 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2369,7 +2369,7 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES #define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) #endif diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 801bf9e520db3..26f6afd51bbdc 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -84,7 +84,7 @@ config KVM_SW_PROTECTED_VM bool "Enable support for KVM software-protected VMs" depends on EXPERT depends on KVM_X86 && X86_64 - select KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_VM_MEMORY_ATTRIBUTES help Enable support for KVM software-protected VMs. Currently, software- protected VMs are purely a development and testing vehicle for @@ -135,7 +135,7 @@ config KVM_INTEL_TDX bool "Intel Trust Domain Extensions (TDX) support" default y depends on INTEL_TDX_HOST - select KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_VM_MEMORY_ATTRIBUTES select HAVE_KVM_ARCH_GMEM_POPULATE help Provides support for launching Intel Trust Domain Extensions (TDX) @@ -159,7 +159,7 @@ config KVM_AMD_SEV depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) select ARCH_HAS_CC_PLATFORM - select KVM_GENERIC_MEMORY_ATTRIBUTES + select KVM_VM_MEMORY_ATTRIBUTES select HAVE_KVM_ARCH_GMEM_PREPARE select HAVE_KVM_ARCH_GMEM_INVALIDATE select HAVE_KVM_ARCH_GMEM_POPULATE diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 892246204435c..a80a876ab4ad6 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7899,7 +7899,7 @@ void kvm_mmu_pre_destroy_vm(struct kvm *kvm) vhost_task_stop(kvm->arch.nx_huge_page_recovery_thread); } -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static bool hugepage_test_mixed(struct kvm_memory_slot *slot, gfn_t gfn, int level) { diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 0a1b63c63d1a9..1560de1e95be0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -13625,7 +13625,7 @@ static int kvm_alloc_memslot_metadata(struct kvm *kvm, } } -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES kvm_mmu_init_memslot_memory_attributes(kvm, slot); #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 4c14aee1fb063..7b9faa3545300 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -722,7 +722,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -#ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifndef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; @@ -871,7 +871,7 @@ struct kvm { #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER struct notifier_block pm_notifier; #endif -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES /* Protected by slots_lock (for writes) and RCU (for reads) */ struct xarray mem_attr_array; #endif @@ -2528,7 +2528,7 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot) return slot->flags & KVM_MEMSLOT_GMEM_ONLY; } -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) { return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); @@ -2550,7 +2550,7 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } -#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ +#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ #ifdef CONFIG_KVM_GUEST_MEMFD int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h index b282e3a867696..1ba72bd73ea2f 100644 --- a/include/trace/events/kvm.h +++ b/include/trace/events/kvm.h @@ -358,7 +358,7 @@ TRACE_EVENT(kvm_dirty_ring_exit, TP_printk("vcpu %d", __entry->vcpu_id) ); -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES /* * @start: Starting address of guest memory range * @end: End address of guest memory range @@ -383,7 +383,7 @@ TRACE_EVENT(kvm_vm_set_mem_attributes, TP_printk("%#016llx -- %#016llx [0x%lx]", __entry->start, __entry->end, __entry->attr) ); -#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ +#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 794976b88c6f9..5119cb37145fc 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -100,7 +100,7 @@ config KVM_ELIDE_TLB_FLUSH_IF_YOUNG config KVM_MMU_LOCKLESS_AGING bool -config KVM_GENERIC_MEMORY_ATTRIBUTES +config KVM_VM_MEMORY_ATTRIBUTES bool config KVM_GUEST_MEMFD diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 89489996fbc1e..306153abbafa5 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1115,7 +1115,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES xa_init(&kvm->mem_attr_array); #endif @@ -1300,7 +1300,7 @@ static void kvm_destroy_vm(struct kvm *kvm) cleanup_srcu_struct(&kvm->irq_srcu); srcu_barrier(&kvm->srcu); cleanup_srcu_struct(&kvm->srcu); -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES xa_destroy(&kvm->mem_attr_array); #endif kvm_arch_free_vm(kvm); @@ -2418,7 +2418,7 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static u64 kvm_supported_mem_attributes(struct kvm *kvm) { if (!kvm || kvm_arch_has_private_mem(kvm)) @@ -2623,7 +2623,7 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); } -#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ +#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { @@ -4921,7 +4921,7 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_SYSTEM_EVENT_DATA: case KVM_CAP_DEVICE_CTRL: return 1; -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); #endif @@ -5325,7 +5325,7 @@ static long kvm_vm_ioctl(struct file *filp, break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ -#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES case KVM_SET_MEMORY_ATTRIBUTES: { struct kvm_memory_attributes attrs; @@ -5336,7 +5336,7 @@ static long kvm_vm_ioctl(struct file *filp, r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); break; } -#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ +#endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Explicitly guard reporting support for KVM_MEMORY_ATTRIBUTE_PRIVATE based on kvm_arch_has_private_mem being #defined in anticipation of decoupling kvm_supported_mem_attributes() from CONFIG_KVM_VM_MEMORY_ATTRIBUTES. guest_memfd support for memory attributes will be unconditional to avoid yet more macros (all architectures that support guest_memfd are expected to use per-gmem attributes at some point), at which point enumerating support KVM_MEMORY_ATTRIBUTE_PRIVATE based solely on memory attributes being supported _somewhere_ would result in KVM over-reporting support on arm64. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- include/linux/kvm_host.h | 2 +- virt/kvm/kvm_main.c | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7b9faa3545300..7d079f9701346 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -722,7 +722,7 @@ static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu) } #endif -#ifndef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +#ifndef kvm_arch_has_private_mem static inline bool kvm_arch_has_private_mem(struct kvm *kvm) { return false; diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 306153abbafa5..abb9cfa3eb04d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2421,8 +2421,10 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static u64 kvm_supported_mem_attributes(struct kvm *kvm) { +#ifdef kvm_arch_has_private_mem if (!kvm || kvm_arch_has_private_mem(kvm)) return KVM_MEMORY_ATTRIBUTE_PRIVATE; +#endif return 0; } -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Introduce the basic infrastructure to allow per-VM memory attribute tracking to be disabled. This will be built-upon in a later patch, where a module param can disable per-VM memory attribute tracking. Split the Kconfig option into a base KVM_MEMORY_ATTRIBUTES and the existing KVM_VM_MEMORY_ATTRIBUTES. The base option provides the core plumbing, while the latter enables the full per-VM tracking via an xarray and the associated ioctls. kvm_get_memory_attributes() now performs a static call that either looks up kvm->mem_attr_array with CONFIG_KVM_VM_MEMORY_ATTRIBUTES is enabled, or just returns 0 otherwise. The static call can be patched depending on whether per-VM tracking is enabled by the CONFIG. No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/include/asm/kvm_host.h | 2 +- include/linux/kvm_host.h | 23 ++++++++++++--------- virt/kvm/Kconfig | 4 ++++ virt/kvm/kvm_main.c | 44 ++++++++++++++++++++++++++++++++++++++++- 4 files changed, 62 insertions(+), 11 deletions(-) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 60b997764beef..c9aa50bcdac2d 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -2369,7 +2369,7 @@ void kvm_configure_mmu(bool enable_tdp, int tdp_forced_root_level, int tdp_max_root_level, int tdp_huge_page_level); -#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES #define kvm_arch_has_private_mem(kvm) ((kvm)->arch.has_private_mem) #endif diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 7d079f9701346..c5ba2cb34e45c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2528,19 +2528,15 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot) return slot->flags & KVM_MEMSLOT_GMEM_ONLY; } -#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES +typedef unsigned long (kvm_get_memory_attributes_t)(struct kvm *kvm, gfn_t gfn); +DECLARE_STATIC_CALL(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); + static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn) { - return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); + return static_call(__kvm_get_memory_attributes)(kvm, gfn); } -bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, - unsigned long mask, unsigned long attrs); -bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, - struct kvm_gfn_range *range); -bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, - struct kvm_gfn_range *range); - static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE; @@ -2550,6 +2546,15 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) { return false; } +#endif + +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, + unsigned long mask, unsigned long attrs); +bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); +bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, + struct kvm_gfn_range *range); #endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ #ifdef CONFIG_KVM_GUEST_MEMFD diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 5119cb37145fc..3fea89c45cfb4 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -100,7 +100,11 @@ config KVM_ELIDE_TLB_FLUSH_IF_YOUNG config KVM_MMU_LOCKLESS_AGING bool +config KVM_MEMORY_ATTRIBUTES + bool + config KVM_VM_MEMORY_ATTRIBUTES + select KVM_MEMORY_ATTRIBUTES bool config KVM_GUEST_MEMFD diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index abb9cfa3eb04d..ee26f1d9b5fda 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -101,6 +101,17 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(halt_poll_ns_shrink); static bool __ro_after_init allow_unsafe_mappings; module_param(allow_unsafe_mappings, bool, 0444); +#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +static bool vm_memory_attributes = true; +#else +#define vm_memory_attributes false +#endif +DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes)); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_TRAMP(__kvm_get_memory_attributes)); +#endif + /* * Ordering of locks: * @@ -2418,7 +2429,7 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ -#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +#ifdef CONFIG_KVM_MEMORY_ATTRIBUTES static u64 kvm_supported_mem_attributes(struct kvm *kvm) { #ifdef kvm_arch_has_private_mem @@ -2429,6 +2440,12 @@ static u64 kvm_supported_mem_attributes(struct kvm *kvm) return 0; } +#ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES +static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + return xa_to_value(xa_load(&kvm->mem_attr_array, gfn)); +} + /* * Returns true if _all_ gfns in the range [@start, @end) have attributes * such that the bits in @mask match @attrs. @@ -2625,7 +2642,24 @@ static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); } +#else /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ +static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + BUILD_BUG_ON(1); +} #endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ +static void kvm_init_memory_attributes(void) +{ + if (vm_memory_attributes) + static_call_update(__kvm_get_memory_attributes, + kvm_get_vm_memory_attributes); + else + static_call_update(__kvm_get_memory_attributes, + (void *)__static_call_return0); +} +#else /* CONFIG_KVM_MEMORY_ATTRIBUTES */ +static void kvm_init_memory_attributes(void) { } +#endif /* CONFIG_KVM_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { @@ -4925,6 +4959,9 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return 1; #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: + if (!vm_memory_attributes) + return 0; + return kvm_supported_mem_attributes(kvm); #endif #ifdef CONFIG_KVM_GUEST_MEMFD @@ -5331,6 +5368,10 @@ static long kvm_vm_ioctl(struct file *filp, case KVM_SET_MEMORY_ATTRIBUTES: { struct kvm_memory_attributes attrs; + r = -ENOTTY; + if (!vm_memory_attributes) + goto out; + r = -EFAULT; if (copy_from_user(&attrs, argp, sizeof(attrs))) goto out; @@ -6527,6 +6568,7 @@ int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; + kvm_init_memory_attributes(); kvm_init_debug(); r = kvm_vfio_ops_init(); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Implement kvm_gmem_get_memory_attributes() for guest_memfd to allow the KVM core and architecture code to query per-GFN memory attributes. kvm_gmem_get_memory_attributes() finds the memory slot for a given GFN and queries the guest_memfd file's to determine if the page is marked as private. If vm_memory_attributes is not enabled, there is no shared/private tracking at the VM level. Install the guest_memfd implementation as long as guest_memfd is enabled to give guest_memfd a chance to respond on attributes. guest_memfd should look up attributes regardless of whether this memslot is gmem-only since attributes are now tracked by gmem regardless of whether mmap() is enabled. Signed-off-by: Sean Christopherson Co-developed-by: Ackerley Tng Signed-off-by: Ackerley Tng --- include/linux/kvm_host.h | 2 ++ virt/kvm/guest_memfd.c | 31 +++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 3 +++ 3 files changed, 36 insertions(+) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index c5ba2cb34e45c..28a54298d27db 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2557,6 +2557,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); #endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ +unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn); + #ifdef CONFIG_KVM_GUEST_MEMFD int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn, kvm_pfn_t *pfn, struct page **page, diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 5011d38820d0d..f055e058a3f28 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -509,6 +509,37 @@ static int kvm_gmem_mmap(struct file *file, struct vm_area_struct *vma) return 0; } +unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + struct inode *inode; + + /* + * If this gfn has no associated memslot, there's no chance of the gfn + * being backed by private memory, since guest_memfd must be used for + * private memory, and guest_memfd must be associated with some memslot. + */ + if (!slot) + return 0; + + CLASS(gmem_get_file, file)(slot); + if (!file) + return 0; + + inode = file_inode(file); + + /* + * Rely on the maple tree's internal RCU lock to ensure a + * stable result. This result can become stale as soon as the + * lock is dropped, so the caller _must_ still protect + * consumption of private vs. shared by checking + * mmu_invalidate_retry_gfn() under mmu_lock to serialize + * against ongoing attribute updates. + */ + return kvm_gmem_get_attributes(inode, kvm_gmem_get_index(slot, gfn)); +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes); + static struct file_operations kvm_gmem_fops = { .mmap = kvm_gmem_mmap, .open = generic_file_open, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ee26f1d9b5fda..4139e903f756a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2653,6 +2653,9 @@ static void kvm_init_memory_attributes(void) if (vm_memory_attributes) static_call_update(__kvm_get_memory_attributes, kvm_get_vm_memory_attributes); + else if (IS_ENABLED(CONFIG_KVM_GUEST_MEMFD)) + static_call_update(__kvm_get_memory_attributes, + kvm_gmem_get_memory_attributes); else static_call_update(__kvm_get_memory_attributes, (void *)__static_call_return0); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng When the maximum mapping level is queried, KVM's MMU lock is held, and while the MMU lock is held, guest_memfd cannot take the filemap_invalidate_lock() to look up the current shared/private state of the gfn, for these reasons: + The MMU lock is a spinlock or rwlock and cannot be held while taking a lock that can sleep. + In guest_memfd's code paths (such as truncate), the filemap_invalidate_lock() is held while taking the MMU lock, and taking the locks in reverse order would introduce a AB-BA deadlock. Currently, the maximum mapping level is only queried from guest_memfd in the process of recovering huge pages, if dirty logging is disabled on a memslot. Dirty logging is not currently supported for guest_memfd, and guest_memfd memslots also cannot be updated. For now, bug the VM if guest_memfd needs to be queried to determine the maximum mapping level. This guard can be removed if/when support is added. Signed-off-by: Ackerley Tng --- arch/x86/kvm/mmu/mmu.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index a80a876ab4ad6..153bcc5369985 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -3357,6 +3357,15 @@ int kvm_mmu_max_mapping_level(struct kvm *kvm, struct kvm_page_fault *fault, max_level = fault->max_level; is_private = fault->is_private; } else { + /* + * Memory attributes cannot be obtained from guest_memfd while + * the MMU lock is held. + */ + if (KVM_BUG_ON(static_call_query(__kvm_get_memory_attributes) == + kvm_gmem_get_memory_attributes, kvm)) { + return 0; + } + max_level = PG_LEVEL_NUM; is_private = kvm_mem_is_private(kvm, gfn); } -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Update the guest_memfd populate() flow to pull memory attributes from the gmem instance instead of the VM when KVM is not configured to track shared/private status in the VM. Rename the per-VM API to make it clear that it retrieves per-VM attributes, i.e. is not suitable for use outside of flows that are specific to generic per-VM attributes. Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/kvm/mmu/mmu.c | 2 +- include/linux/kvm_host.h | 14 +++++++++++++- virt/kvm/guest_memfd.c | 24 +++++++++++++++++++++--- virt/kvm/kvm_main.c | 8 +++----- 4 files changed, 38 insertions(+), 10 deletions(-) diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 153bcc5369985..bfcf9be25598e 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -7997,7 +7997,7 @@ static bool hugepage_has_attrs(struct kvm *kvm, struct kvm_memory_slot *slot, const unsigned long end = start + KVM_PAGES_PER_HPAGE(level); if (level == PG_LEVEL_2M) - return kvm_range_has_memory_attributes(kvm, start, end, ~0, attrs); + return kvm_range_has_vm_memory_attributes(kvm, start, end, ~0, attrs); for (gfn = start; gfn < end; gfn += KVM_PAGES_PER_HPAGE(level - 1)) { if (hugepage_test_mixed(slot, gfn, level - 1) || diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 28a54298d27db..1deab76dc0a2c 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2549,12 +2549,24 @@ static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn) #endif #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES -bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, +extern bool vm_memory_attributes; +bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs); bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range); +#else +#define vm_memory_attributes false +static inline bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, + gfn_t start, gfn_t end, + unsigned long mask, + unsigned long attrs) +{ + WARN_ONCE(1, "Unexpected call to kvm_range_has_vm_memory_attributes()"); + + return false; +} #endif /* CONFIG_KVM_VM_MEMORY_ATTRIBUTES */ unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index f055e058a3f28..9d025f518c025 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -924,12 +924,31 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE +static bool kvm_gmem_range_is_private(struct gmem_inode *gi, pgoff_t index, + size_t nr_pages, struct kvm *kvm, gfn_t gfn) +{ + pgoff_t end = index + nr_pages - 1; + void *entry; + + if (vm_memory_attributes) + return kvm_range_has_vm_memory_attributes(kvm, gfn, gfn + nr_pages, + KVM_MEMORY_ATTRIBUTE_PRIVATE, + KVM_MEMORY_ATTRIBUTE_PRIVATE); + + mt_for_each(&gi->attributes, entry, index, end) { + if (xa_to_value(entry) != KVM_MEMORY_ATTRIBUTE_PRIVATE) + return false; + } + + return true; +} static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot, struct file *file, gfn_t gfn, struct page *src_page, kvm_gmem_populate_cb post_populate, void *opaque) { pgoff_t index = kvm_gmem_get_index(slot, gfn); + struct gmem_inode *gi; struct folio *folio; kvm_pfn_t pfn; int ret; @@ -944,9 +963,8 @@ static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot, folio_unlock(folio); - if (!kvm_range_has_memory_attributes(kvm, gfn, gfn + 1, - KVM_MEMORY_ATTRIBUTE_PRIVATE, - KVM_MEMORY_ATTRIBUTE_PRIVATE)) { + gi = GMEM_I(file_inode(file)); + if (!kvm_gmem_range_is_private(gi, index, 1, kvm, gfn)) { ret = -EINVAL; goto out_put_folio; } diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4139e903f756a..0a4024948711a 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -103,9 +103,7 @@ module_param(allow_unsafe_mappings, bool, 0444); #ifdef CONFIG_KVM_MEMORY_ATTRIBUTES #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES -static bool vm_memory_attributes = true; -#else -#define vm_memory_attributes false +bool vm_memory_attributes = true; #endif DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes)); @@ -2450,7 +2448,7 @@ static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn) * Returns true if _all_ gfns in the range [@start, @end) have attributes * such that the bits in @mask match @attrs. */ -bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, +bool kvm_range_has_vm_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long mask, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); @@ -2584,7 +2582,7 @@ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range has the desired attributes. */ - if (kvm_range_has_memory_attributes(kvm, start, end, ~0, attributes)) + if (kvm_range_has_vm_memory_attributes(kvm, start, end, ~0, attributes)) goto out_unlock; /* -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng All-shared guest_memfd used to be only supported for non-CoCo VMs where preparation doesn't apply. INIT_SHARED is about to be supported for non-CoCo VMs in a later patch in this series. In addition, KVM_SET_MEMORY_ATTRIBUTES2 is about to be supported in guest_memfd in a later patch in this series. This means that the kvm fault handler may now call kvm_gmem_get_pfn() on a shared folio for a CoCo VM where preparation applies. Add a check to make sure that preparation is only performed for private folios. Preparation will be undone on freeing (see kvm_gmem_free_folio()) and on conversion to shared. Signed-off-by: Ackerley Tng --- virt/kvm/guest_memfd.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 9d025f518c025..4f7c4824c3a45 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -888,6 +888,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, int *max_order) { pgoff_t index = kvm_gmem_get_index(slot, gfn); + struct inode *inode; struct folio *folio; int r = 0; @@ -895,7 +896,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, if (!file) return -EFAULT; - filemap_invalidate_lock_shared(file_inode(file)->i_mapping); + inode = file_inode(file); + filemap_invalidate_lock_shared(inode->i_mapping); folio = __kvm_gmem_get_pfn(file, slot, index, pfn, max_order); if (IS_ERR(folio)) { @@ -908,7 +910,8 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, folio_mark_uptodate(folio); } - r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); + if (kvm_gmem_is_private_mem(inode, index)) + r = kvm_gmem_prepare_folio(kvm, slot, gfn, folio); folio_unlock(folio); @@ -918,7 +921,7 @@ int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot, folio_put(folio); out: - filemap_invalidate_unlock_shared(file_inode(file)->i_mapping); + filemap_invalidate_unlock_shared(inode->i_mapping); return r; } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Move kvm_supported_mem_attributes() from kvm_main.c to kvm_host.h and make it a static inline function. This allows the helper to be used in other parts of the KVM subsystem outside of kvm_main.c. This helper will be used later by guest_memfd. No functional change intended. Signed-off-by: Ackerley Tng --- include/linux/kvm_host.h | 10 ++++++++++ virt/kvm/kvm_main.c | 10 ---------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 1deab76dc0a2c..f9ea95e33d050 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -2529,6 +2529,16 @@ static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot) } #ifdef CONFIG_KVM_MEMORY_ATTRIBUTES +static inline u64 kvm_supported_mem_attributes(struct kvm *kvm) +{ +#ifdef kvm_arch_has_private_mem + if (!kvm || kvm_arch_has_private_mem(kvm)) + return KVM_MEMORY_ATTRIBUTE_PRIVATE; +#endif + + return 0; +} + typedef unsigned long (kvm_get_memory_attributes_t)(struct kvm *kvm, gfn_t gfn); DECLARE_STATIC_CALL(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 0a4024948711a..ff20e63143642 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -2428,16 +2428,6 @@ static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ #ifdef CONFIG_KVM_MEMORY_ATTRIBUTES -static u64 kvm_supported_mem_attributes(struct kvm *kvm) -{ -#ifdef kvm_arch_has_private_mem - if (!kvm || kvm_arch_has_private_mem(kvm)) - return KVM_MEMORY_ATTRIBUTE_PRIVATE; -#endif - - return 0; -} - #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES static unsigned long kvm_get_vm_memory_attributes(struct kvm *kvm, gfn_t gfn) { -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Introduce base support for KVM_SET_MEMORY_ATTRIBUTES2 in guest_memfd, which just updates attributes tracked by guest_memfd. Validate input fields in general. Guard usage of KVM_SET_MEMORY_ATTRIBUTES2 by making sure requested attributes are supported for this instance of kvm. A new KVM_SET_MEMORY_ATTRIBUTES2 is defined to support writes (unlike KVM_SET_MEMORY_ATTRIBUTES) in addition to reads so it can provide error details to userspace. This will be used in a later patch. The two ioctls use their corresponding structs with no overlap, but backward compatibility is baked in for future support of KVM_SET_MEMORY_ATTRIBUTES2 and struct kvm_memory_attributes2 in the VM ioctl. The process of setting memory attributes is set up such that the later half will not fail due to allocation. Any necessary checks are performed before the point of no return. Signed-off-by: Ackerley Tng Co-developed-by: Vishal Annapurve Signed-off-by: Vishal Annapurve Co-developed-by: Sean Christoperson Signed-off-by: Sean Christoperson --- include/uapi/linux/kvm.h | 13 ++++++ virt/kvm/Kconfig | 1 + virt/kvm/guest_memfd.c | 114 +++++++++++++++++++++++++++++++++++++++++++++++ virt/kvm/kvm_main.c | 12 +++++ 4 files changed, 140 insertions(+) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6c8afa2047bf3..e6bbf68a83813 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1648,6 +1648,19 @@ struct kvm_memory_attributes { __u64 flags; }; +#define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd2, struct kvm_memory_attributes2) + +struct kvm_memory_attributes2 { + union { + __u64 address; + __u64 offset; + }; + __u64 size; + __u64 attributes; + __u64 flags; + __u64 reserved[12]; +}; + #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index 3fea89c45cfb4..e371e079e2c50 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -109,6 +109,7 @@ config KVM_VM_MEMORY_ATTRIBUTES config KVM_GUEST_MEMFD select XARRAY_MULTI + select KVM_MEMORY_ATTRIBUTES bool config HAVE_KVM_ARCH_GMEM_PREPARE diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 4f7c4824c3a45..91e89b188f583 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -540,11 +540,125 @@ unsigned long kvm_gmem_get_memory_attributes(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_memory_attributes); +/* + * Preallocate memory for attributes to be stored on a maple tree, pointed to + * by mas. Adjacent ranges with attributes identical to the new attributes + * will be merged. Also sets mas's bounds up for storing attributes. + * + * This maintains the invariant that ranges with the same attributes will + * always be merged. + */ +static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes, + pgoff_t start, size_t nr_pages) +{ + pgoff_t end = start + nr_pages; + pgoff_t last = end - 1; + void *entry; + + /* Try extending range. entry is NULL on overflow/wrap-around. */ + mas_set(mas, end); + entry = mas_find(mas, end); + if (entry && xa_to_value(entry) == attributes) + last = mas->last; + + if (start > 0) { + mas_set(mas, start - 1); + entry = mas_find(mas, start - 1); + if (entry && xa_to_value(entry) == attributes) + start = mas->index; + } + + mas_set_range(mas, start, last); + return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL); +} + +static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, + size_t nr_pages, uint64_t attrs) +{ + struct address_space *mapping = inode->i_mapping; + struct gmem_inode *gi = GMEM_I(inode); + pgoff_t end = start + nr_pages; + struct maple_tree *mt; + struct ma_state mas; + int r; + + mt = &gi->attributes; + + filemap_invalidate_lock(mapping); + + mas_init(&mas, mt, start); + r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages); + if (r) + goto out; + + /* + * From this point on guest_memfd has performed necessary + * checks and can proceed to do guest-breaking changes. + */ + + kvm_gmem_invalidate_begin(inode, start, end); + mas_store_prealloc(&mas, xa_mk_value(attrs)); + kvm_gmem_invalidate_end(inode, start, end); +out: + filemap_invalidate_unlock(mapping); + return r; +} + +static long kvm_gmem_set_attributes(struct file *file, void __user *argp) +{ + struct gmem_file *f = file->private_data; + struct inode *inode = file_inode(file); + struct kvm_memory_attributes2 attrs; + size_t nr_pages; + pgoff_t index; + int i; + + if (copy_from_user(&attrs, argp, sizeof(attrs))) + return -EFAULT; + + if (attrs.flags) + return -EINVAL; + for (i = 0; i < ARRAY_SIZE(attrs.reserved); i++) { + if (attrs.reserved[i]) + return -EINVAL; + } + if (attrs.attributes & ~kvm_supported_mem_attributes(f->kvm)) + return -EINVAL; + if (attrs.size == 0 || attrs.offset + attrs.size < attrs.offset) + return -EINVAL; + if (!PAGE_ALIGNED(attrs.offset) || !PAGE_ALIGNED(attrs.size)) + return -EINVAL; + + if (attrs.offset >= i_size_read(inode) || + attrs.offset + attrs.size > i_size_read(inode)) + return -EINVAL; + + nr_pages = attrs.size >> PAGE_SHIFT; + index = attrs.offset >> PAGE_SHIFT; + return __kvm_gmem_set_attributes(inode, index, nr_pages, + attrs.attributes); +} + +static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl, + unsigned long arg) +{ + switch (ioctl) { + case KVM_SET_MEMORY_ATTRIBUTES2: + if (vm_memory_attributes) + return -ENOTTY; + + return kvm_gmem_set_attributes(file, (void __user *)arg); + default: + return -ENOTTY; + } +} + static struct file_operations kvm_gmem_fops = { .mmap = kvm_gmem_mmap, .open = generic_file_open, .release = kvm_gmem_release, .fallocate = kvm_gmem_fallocate, + .unlocked_ioctl = kvm_gmem_ioctl, }; static int kvm_gmem_migrate_folio(struct address_space *mapping, diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ff20e63143642..4d7bf52b7b717 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -110,6 +110,18 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes)); EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_TRAMP(__kvm_get_memory_attributes)); #endif +#define MEMORY_ATTRIBUTES_MATCH(one, two) \ + static_assert(offsetof(struct kvm_memory_attributes, one) == \ + offsetof(struct kvm_memory_attributes2, two)); \ + static_assert(sizeof_field(struct kvm_memory_attributes, one) ==\ + sizeof_field(struct kvm_memory_attributes2, two)) + +/* Ensure the common parts of the two structs are identical. */ +MEMORY_ATTRIBUTES_MATCH(address, address); +MEMORY_ATTRIBUTES_MATCH(size, size); +MEMORY_ATTRIBUTES_MATCH(attributes, attributes); +MEMORY_ATTRIBUTES_MATCH(flags, flags); + /* * Ordering of locks: * -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng When converting memory to private in guest_memfd, it is necessary to ensure that the pages are not currently being accessed by any other part of the kernel or userspace to avoid any current user writing to guest private memory. guest_memfd checks for unexpected refcounts to determine whether a page is still in use. The only expected refcounts after unmapping the range requested for conversion are those that are held by guest_memfd itself. Update the kvm_memory_attributes2 structure to include an error_offset field. This allows KVM to report the exact offset where a conversion failed to userspace. If the safety check fails, return -EAGAIN and copy the error_offset back to userspace so that it can potentially retry the operation or handle the failure gracefully. Suggested-by: David Hildenbrand Signed-off-by: Ackerley Tng Co-developed-by: Vishal Annapurve Signed-off-by: Vishal Annapurve --- include/uapi/linux/kvm.h | 3 ++- virt/kvm/guest_memfd.c | 65 ++++++++++++++++++++++++++++++++++++++++++++---- 2 files changed, 62 insertions(+), 6 deletions(-) diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index e6bbf68a83813..0b55258573d3d 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -1658,7 +1658,8 @@ struct kvm_memory_attributes2 { __u64 size; __u64 attributes; __u64 flags; - __u64 reserved[12]; + __u64 error_offset; + __u64 reserved[11]; }; #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 91e89b188f583..9d82642a025e9 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -572,9 +572,42 @@ static int kvm_gmem_mas_preallocate(struct ma_state *mas, u64 attributes, return mas_preallocate(mas, xa_mk_value(attributes), GFP_KERNEL); } +static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start, + size_t nr_pages, pgoff_t *err_index) +{ + struct address_space *mapping = inode->i_mapping; + const int filemap_get_folios_refcount = 1; + pgoff_t last = start + nr_pages - 1; + struct folio_batch fbatch; + bool safe = true; + int i; + + folio_batch_init(&fbatch); + while (safe && filemap_get_folios(mapping, &start, last, &fbatch)) { + + for (i = 0; i < folio_batch_count(&fbatch); ++i) { + struct folio *folio = fbatch.folios[i]; + + if (folio_ref_count(folio) != + folio_nr_pages(folio) + filemap_get_folios_refcount) { + safe = false; + *err_index = folio->index; + break; + } + } + + folio_batch_release(&fbatch); + cond_resched(); + } + + return safe; +} + static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, - size_t nr_pages, uint64_t attrs) + size_t nr_pages, uint64_t attrs, + pgoff_t *err_index) { + bool to_private = attrs & KVM_MEMORY_ATTRIBUTE_PRIVATE; struct address_space *mapping = inode->i_mapping; struct gmem_inode *gi = GMEM_I(inode); pgoff_t end = start + nr_pages; @@ -588,8 +621,21 @@ static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, mas_init(&mas, mt, start); r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages); - if (r) + if (r) { + *err_index = start; goto out; + } + + if (to_private) { + unmap_mapping_pages(mapping, start, nr_pages, false); + + if (!kvm_gmem_is_safe_for_conversion(inode, start, nr_pages, + err_index)) { + mas_destroy(&mas); + r = -EAGAIN; + goto out; + } + } /* * From this point on guest_memfd has performed necessary @@ -609,9 +655,10 @@ static long kvm_gmem_set_attributes(struct file *file, void __user *argp) struct gmem_file *f = file->private_data; struct inode *inode = file_inode(file); struct kvm_memory_attributes2 attrs; + pgoff_t err_index; size_t nr_pages; pgoff_t index; - int i; + int i, r; if (copy_from_user(&attrs, argp, sizeof(attrs))) return -EFAULT; @@ -635,8 +682,16 @@ static long kvm_gmem_set_attributes(struct file *file, void __user *argp) nr_pages = attrs.size >> PAGE_SHIFT; index = attrs.offset >> PAGE_SHIFT; - return __kvm_gmem_set_attributes(inode, index, nr_pages, - attrs.attributes); + r = __kvm_gmem_set_attributes(inode, index, nr_pages, attrs.attributes, + &err_index); + if (r) { + attrs.error_offset = ((uint64_t)err_index) << PAGE_SHIFT; + + if (copy_to_user(argp, &attrs, sizeof(attrs))) + return -EFAULT; + } + + return r; } static long kvm_gmem_ioctl(struct file *file, unsigned int ioctl, -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng When memory in guest_memfd is converted from private to shared, the platform-specific state associated with the guest-private pages must be invalidated or cleaned up. Iterate over the folios in the affected range and call the kvm_arch_gmem_invalidate() hook for each PFN range. This allows architectures to perform necessary teardown, such as updating hardware metadata or encryption states, before the pages are transitioned to the shared state. Invoke this helper after indicating to KVM's mmu code that an invalidation is in progress to stop in-flight page faults from succeeding. Signed-off-by: Ackerley Tng --- virt/kvm/guest_memfd.c | 41 +++++++++++++++++++++++++++++++++++++++++ 1 file changed, 41 insertions(+) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 9d82642a025e9..baf4b88dead1f 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -603,6 +603,42 @@ static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start, return safe; } +#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE +static void kvm_gmem_invalidate(struct inode *inode, pgoff_t start, pgoff_t end) +{ + struct folio_batch fbatch; + pgoff_t next = start; + int i; + + folio_batch_init(&fbatch); + while (filemap_get_folios(inode->i_mapping, &next, end - 1, &fbatch)) { + for (i = 0; i < folio_batch_count(&fbatch); ++i) { + struct folio *folio = fbatch.folios[i]; + pgoff_t start_index, end_index; + kvm_pfn_t start_pfn, end_pfn; + + start_index = max(start, folio->index); + end_index = min(end, folio_next_index(folio)); + /* + * end_index is either in folio or points to + * the first page of the next folio. Hence, + * all pages in range [start_index, end_index) + * are contiguous. + */ + start_pfn = folio_file_pfn(folio, start_index); + end_pfn = start_pfn + end_index - start_index; + + kvm_arch_gmem_invalidate(start_pfn, end_pfn); + } + + folio_batch_release(&fbatch); + cond_resched(); + } +} +#else +static void kvm_gmem_invalidate(struct inode *inode, pgoff_t start, pgoff_t end) {} +#endif + static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, size_t nr_pages, uint64_t attrs, pgoff_t *err_index) @@ -643,7 +679,12 @@ static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, */ kvm_gmem_invalidate_begin(inode, start, end); + + if (!to_private) + kvm_gmem_invalidate(inode, start, end); + mas_store_prealloc(&mas, xa_mk_value(attrs)); + kvm_gmem_invalidate_end(inode, start, end); out: filemap_invalidate_unlock(mapping); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Extract a helper out of kvm_gmem_range_is_private() that checks that a range has given attributes. Optimize setting memory attributes by returning early if all pages in the requested range already has the requested attributes. Signed-off-by: Ackerley Tng --- virt/kvm/guest_memfd.c | 33 +++++++++++++++++++++++---------- 1 file changed, 23 insertions(+), 10 deletions(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index baf4b88dead1f..034b72b4947fb 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -86,6 +86,23 @@ static bool kvm_gmem_is_shared_mem(struct inode *inode, pgoff_t index) return !kvm_gmem_is_private_mem(inode, index); } +static bool kvm_gmem_range_has_attributes(struct maple_tree *mt, + pgoff_t index, size_t nr_pages, + u64 attributes) +{ + pgoff_t end = index + nr_pages - 1; + void *entry; + + lockdep_assert(mt_lock_is_held(mt)); + + mt_for_each(mt, entry, index, end) { + if (xa_to_value(entry) != attributes) + return false; + } + + return true; +} + static int __kvm_gmem_prepare_folio(struct kvm *kvm, struct kvm_memory_slot *slot, pgoff_t index, struct folio *folio) { @@ -649,12 +666,15 @@ static int __kvm_gmem_set_attributes(struct inode *inode, pgoff_t start, pgoff_t end = start + nr_pages; struct maple_tree *mt; struct ma_state mas; - int r; + int r = 0; mt = &gi->attributes; filemap_invalidate_lock(mapping); + if (kvm_gmem_range_has_attributes(mt, start, nr_pages, attrs)) + goto out; + mas_init(&mas, mt, start); r = kvm_gmem_mas_preallocate(&mas, attrs, start, nr_pages); if (r) { @@ -1140,20 +1160,13 @@ EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_gmem_get_pfn); static bool kvm_gmem_range_is_private(struct gmem_inode *gi, pgoff_t index, size_t nr_pages, struct kvm *kvm, gfn_t gfn) { - pgoff_t end = index + nr_pages - 1; - void *entry; - if (vm_memory_attributes) return kvm_range_has_vm_memory_attributes(kvm, gfn, gfn + nr_pages, KVM_MEMORY_ATTRIBUTE_PRIVATE, KVM_MEMORY_ATTRIBUTE_PRIVATE); - mt_for_each(&gi->attributes, entry, index, end) { - if (xa_to_value(entry) != KVM_MEMORY_ATTRIBUTE_PRIVATE) - return false; - } - - return true; + return kvm_gmem_range_has_attributes(&gi->attributes, index, nr_pages, + KVM_MEMORY_ATTRIBUTE_PRIVATE); } static long __kvm_gmem_populate(struct kvm *kvm, struct kvm_memory_slot *slot, -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Introduce KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES to advertise the availability of the KVM_SET_MEMORY_ATTRIBUTES2 ioctl. KVM_SET_MEMORY_ATTRIBUTES2 is a guest_memfd-scoped version of the existing KVM_SET_MEMORY_ATTRIBUTES VM ioctl. It allows userspace to manage memory attributes, such as KVM_MEMORY_ATTRIBUTE_PRIVATE, directly on a guest_memfd file descriptor. This new version uses struct kvm_memory_attributes2, which adds an error_offset field to the output. This allows KVM to return the specific offset that triggered an error, which is especially useful for handling EAGAIN results caused by transient page reference counts during attribute conversions. Update the KVM API documentation to define the new ioctl and its behavior, and add the necessary UAPI definitions and capability checks. Suggested-by: Sean Christopherson Suggested-by: Michael Roth Signed-off-by: Ackerley Tng --- Documentation/virt/kvm/api.rst | 78 +++++++++++++++++++++++++++++++++++++++++- include/uapi/linux/kvm.h | 2 ++ virt/kvm/kvm_main.c | 5 +++ 3 files changed, 84 insertions(+), 1 deletion(-) diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst index 52bbbb553ce10..55c2701d9ed49 100644 --- a/Documentation/virt/kvm/api.rst +++ b/Documentation/virt/kvm/api.rst @@ -117,7 +117,7 @@ description: x86 includes both i386 and x86_64. Type: - system, vm, or vcpu. + system, vm, vcpu or guest_memfd. Parameters: what parameters are accepted by the ioctl. @@ -6361,6 +6361,8 @@ S390: Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set. Returns -EINVAL if called on a protected VM. +.. _KVM_SET_MEMORY_ATTRIBUTES: + 4.141 KVM_SET_MEMORY_ATTRIBUTES ------------------------------- @@ -6553,6 +6555,80 @@ KVM_S390_KEYOP_SSKE Sets the storage key for the guest address ``guest_addr`` to the key specified in ``key``, returning the previous value in ``key``. +4.145 KVM_SET_MEMORY_ATTRIBUTES2 +--------------------------------- + +:Capability: KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES +:Architectures: all +:Type: guest_memfd ioctl +:Parameters: struct kvm_memory_attributes2 (in/out) +:Returns: 0 on success, <0 on error + +Errors: + + ========== =============================================================== + EINVAL The specified `offset` or `size` were invalid (e.g. not + page aligned, causes an overflow, or size is zero). + EFAULT The parameter address was invalid. + EAGAIN Some page within requested range had unexpected refcounts. The + offset of the page will be returned in `error_offset`. + ENOMEM Ran out of memory trying to track private/shared state + ========== =============================================================== + +KVM_SET_MEMORY_ATTRIBUTES2 is an extension to +KVM_SET_MEMORY_ATTRIBUTES that supports returning (writing) values to +userspace. The original (pre-extension) fields are shared with +KVM_SET_MEMORY_ATTRIBUTES identically. + +Attribute values are shared with KVM_SET_MEMORY_ATTRIBUTES. + +:: + + struct kvm_memory_attributes2 { + /* in */ + union { + __u64 address; + __u64 offset; + }; + __u64 size; + __u64 attributes; + __u64 flags; + /* out */ + __u64 error_offset; + __u64 reserved[11]; + }; + + #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) + +Set attributes for a range of offsets within a guest_memfd to +KVM_MEMORY_ATTRIBUTE_PRIVATE to limit the specified guest_memfd backed +memory range for guest_use. Even if KVM_CAP_GUEST_MEMFD_MMAP is +supported, after a successful call to set +KVM_MEMORY_ATTRIBUTE_PRIVATE, the requested range will not be mappable +into host userspace and will only be mappable by the guest. + +To allow the range to be mappable into host userspace again, call +KVM_SET_MEMORY_ATTRIBUTES2 on the guest_memfd again with +KVM_MEMORY_ATTRIBUTE_PRIVATE unset. + +KVM does not directly manipulate the memory contents of pages during +attribute updates. However, the process of setting these attributes, +which includes operations such as unmapping pages from the host or +stage-2 page tables, may result in side effects on memory contents +that vary across different trusted firmware implementations. + +If this ioctl returns -EAGAIN, the offset of the page with unexpected +refcounts will be returned in `error_offset`. This can occur if there +are transient refcounts on the pages, taken by other parts of the +kernel. + +Userspace is expected to figure out how to remove all known refcounts +on the shared pages, such as refcounts taken by get_user_pages(), and +try the ioctl again. A possible source of these long term refcounts is +if the guest_memfd memory was pinned in IOMMU page tables. + +See also: :ref: `KVM_SET_MEMORY_ATTRIBUTES`. + .. _kvm_run: 5. The kvm_run structure diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 0b55258573d3d..f437fd0f1350c 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -996,6 +996,7 @@ struct kvm_enable_cap { #define KVM_CAP_S390_USER_OPEREXEC 246 #define KVM_CAP_S390_KEYOP 247 #define KVM_CAP_S390_VSIE_ESAMODE 248 +#define KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES 249 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1648,6 +1649,7 @@ struct kvm_memory_attributes { __u64 flags; }; +/* Available with KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES */ #define KVM_SET_MEMORY_ATTRIBUTES2 _IOWR(KVMIO, 0xd2, struct kvm_memory_attributes2) struct kvm_memory_attributes2 { diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 4d7bf52b7b717..cec02d68d7039 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -4972,6 +4972,11 @@ static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) return 1; case KVM_CAP_GUEST_MEMFD_FLAGS: return kvm_gmem_get_supported_flags(kvm); + case KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES: + if (vm_memory_attributes) + return 0; + + return kvm_supported_mem_attributes(kvm); #endif default: break; -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng When checking if a guest_memfd folio is safe for conversion, its refcount is examined. A folio may be present in a per-CPU lru_add fbatch, which temporarily increases its refcount. This can lead to a false positive, incorrectly indicating that the folio is in use and preventing the conversion, even if it is otherwise safe. The conversion process might not be on the same CPU that holds the folio in its fbatch, making a simple per-CPU check insufficient. To address this, drain all CPUs' lru_add fbatches if an unexpectedly high refcount is encountered during the safety check. This is performed at most once per conversion request. Draining only if the folio in question may be lru cached. guest_memfd folios are unevictable, so they can only reside in the lru_add fbatch. If the folio's refcount is still unsafe after draining, then the conversion is truly deemed unsafe. Signed-off-by: Ackerley Tng --- mm/swap.c | 2 ++ virt/kvm/guest_memfd.c | 18 ++++++++++++++---- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/mm/swap.c b/mm/swap.c index 5cc44f0de9877..3134d9d3d7c30 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "internal.h" @@ -904,6 +905,7 @@ void lru_add_drain_all(void) lru_add_drain(); } #endif /* CONFIG_SMP */ +EXPORT_SYMBOL_FOR_KVM(lru_add_drain_all); atomic_t lru_disable_count = ATOMIC_INIT(0); diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 034b72b4947fb..050a8c092b1a3 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -8,6 +8,7 @@ #include #include #include +#include #include "kvm_mm.h" @@ -596,18 +597,27 @@ static bool kvm_gmem_is_safe_for_conversion(struct inode *inode, pgoff_t start, const int filemap_get_folios_refcount = 1; pgoff_t last = start + nr_pages - 1; struct folio_batch fbatch; + bool lru_drained = false; bool safe = true; int i; folio_batch_init(&fbatch); while (safe && filemap_get_folios(mapping, &start, last, &fbatch)) { - for (i = 0; i < folio_batch_count(&fbatch); ++i) { + for (i = 0; i < folio_batch_count(&fbatch);) { struct folio *folio = fbatch.folios[i]; - if (folio_ref_count(folio) != - folio_nr_pages(folio) + filemap_get_folios_refcount) { - safe = false; + safe = (folio_ref_count(folio) == + folio_nr_pages(folio) + + filemap_get_folios_refcount); + + if (safe) { + ++i; + } else if (folio_may_be_lru_cached(folio) && + !lru_drained) { + lru_add_drain_all(); + lru_drained = true; + } else { *err_index = folio->index; break; } -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng __kvm_gmem_invalidate_begin() and __kvm_gmem_invalidate_end() actually do not specially handle -1ul. -1ul is used as a huge number, which legal indices do not exceed, and hence the invalidation works as expected. Since a later patch is going to make use of the exact range, calculate the size of the guest_memfd inode and use it as the end range for invalidating SPTEs. Signed-off-by: Ackerley Tng --- virt/kvm/guest_memfd.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 050a8c092b1a3..9f6eebfb68f6b 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -370,6 +370,7 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) struct kvm_memory_slot *slot; struct kvm *kvm = f->kvm; unsigned long index; + pgoff_t end; /* * Prevent concurrent attempts to *unbind* a memslot. This is the last @@ -396,9 +397,10 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) * Zap all SPTEs pointed at by this file. Do not free the backing * memory, as its lifetime is associated with the inode, not the file. */ - __kvm_gmem_invalidate_begin(f, 0, -1ul, + end = i_size_read(inode) >> PAGE_SHIFT; + __kvm_gmem_invalidate_begin(f, 0, end, kvm_gmem_get_invalidate_filter(inode)); - __kvm_gmem_invalidate_end(f, 0, -1ul); + __kvm_gmem_invalidate_end(f, 0, end); list_del(&f->entry); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Before conversion, the range filter doesn't really matter: + For non-CoCo VMs that use guest_memfd, they have no mirrored tdp, so KVM_DIRECT_ROOTS would have been invalidated anyway. + CoCo VMs could not use INIT_SHARED, and there's no conversion support, so always using KVM_FILTER_PRIVATE would have worked. Now with conversion support, update kvm_gmem_get_invalidate_filter to inspect the memory attributes maple tree for a given range. Instead of determining the invalidation filter based on static inode flags, iterate through the attributes maple tree for the specific range being invalidated. This allows KVM to identify if the range contains private pages, shared pages, or both, and set the filter bits accordingly. Update kvm_gmem_invalidate_begin and kvm_gmem_release to pass the range parameters to the filter helper to ensure invalidation accurately targets the memory types present in the affected range. Signed-off-by: Ackerley Tng --- virt/kvm/guest_memfd.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-) diff --git a/virt/kvm/guest_memfd.c b/virt/kvm/guest_memfd.c index 9f6eebfb68f6b..c9f155c2dc5c5 100644 --- a/virt/kvm/guest_memfd.c +++ b/virt/kvm/guest_memfd.c @@ -193,12 +193,24 @@ static struct folio *kvm_gmem_get_folio(struct inode *inode, pgoff_t index) return folio; } -static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter(struct inode *inode) +static enum kvm_gfn_range_filter kvm_gmem_get_invalidate_filter( + struct inode *inode, pgoff_t start, pgoff_t end) { - if (GMEM_I(inode)->flags & GUEST_MEMFD_FLAG_INIT_SHARED) - return KVM_FILTER_SHARED; + struct gmem_inode *gi = GMEM_I(inode); + enum kvm_gfn_range_filter filter = 0; + void *entry; + + lockdep_assert(mt_lock_is_held(&gi->attributes)); + + mt_for_each(&gi->attributes, entry, start, end - 1) { + filter |= (xa_to_value(entry) & KVM_MEMORY_ATTRIBUTE_PRIVATE) ? + KVM_FILTER_PRIVATE : KVM_FILTER_SHARED; + + if (filter == (KVM_FILTER_PRIVATE | KVM_FILTER_SHARED)) + break; + } - return KVM_FILTER_PRIVATE; + return filter; } static void __kvm_gmem_invalidate_begin(struct gmem_file *f, pgoff_t start, @@ -244,7 +256,7 @@ static void kvm_gmem_invalidate_begin(struct inode *inode, pgoff_t start, enum kvm_gfn_range_filter attr_filter; struct gmem_file *f; - attr_filter = kvm_gmem_get_invalidate_filter(inode); + attr_filter = kvm_gmem_get_invalidate_filter(inode, start, end); kvm_gmem_for_each_file(f, inode) __kvm_gmem_invalidate_begin(f, start, end, attr_filter); @@ -367,6 +379,7 @@ static long kvm_gmem_fallocate(struct file *file, int mode, loff_t offset, static int kvm_gmem_release(struct inode *inode, struct file *file) { struct gmem_file *f = file->private_data; + enum kvm_gfn_range_filter filter; struct kvm_memory_slot *slot; struct kvm *kvm = f->kvm; unsigned long index; @@ -398,8 +411,8 @@ static int kvm_gmem_release(struct inode *inode, struct file *file) * memory, as its lifetime is associated with the inode, not the file. */ end = i_size_read(inode) >> PAGE_SHIFT; - __kvm_gmem_invalidate_begin(f, 0, end, - kvm_gmem_get_invalidate_filter(inode)); + filter = kvm_gmem_get_invalidate_filter(inode, 0, end); + __kvm_gmem_invalidate_begin(f, 0, end, filter); __kvm_gmem_invalidate_end(f, 0, end); list_del(&f->entry); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Bury KVM_VM_MEMORY_ATTRIBUTES in x86 to discourage other architectures from adding support for per-VM memory attributes, because tracking private vs. shared memory on a per-VM basis is now deprecated in favor of tracking on a per-guest_memfd basis, and no other memory attributes are on the horizon. This will also allow modifying KVM_VM_MEMORY_ATTRIBUTES to be user-selectable (in x86) without creating weirdness in KVM's Kconfigs. Now that guest_memfd support memory attributes, it's entirely possible to run x86 CoCo VMs without support for KVM_VM_MEMORY_ATTRIBUTES. Leave the code itself in common KVM so that it's trivial to undo this change if new per-VM attributes do come along. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/kvm/Kconfig | 4 ++++ virt/kvm/Kconfig | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index 26f6afd51bbdc..b6d65ee664d0f 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -80,6 +80,10 @@ config KVM_WERROR If in doubt, say "N". +config KVM_VM_MEMORY_ATTRIBUTES + select KVM_MEMORY_ATTRIBUTES + bool + config KVM_SW_PROTECTED_VM bool "Enable support for KVM software-protected VMs" depends on EXPERT diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig index e371e079e2c50..663de6421eda2 100644 --- a/virt/kvm/Kconfig +++ b/virt/kvm/Kconfig @@ -103,10 +103,6 @@ config KVM_MMU_LOCKLESS_AGING config KVM_MEMORY_ATTRIBUTES bool -config KVM_VM_MEMORY_ATTRIBUTES - select KVM_MEMORY_ATTRIBUTES - bool - config KVM_GUEST_MEMFD select XARRAY_MULTI select KVM_MEMORY_ATTRIBUTES -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Make vm_memory_attributes a module parameter so that userspace can disable the use of memory attributes on the VM level. To avoid inconsistencies in the way memory attributes are tracked in KVM and guest_memfd, the vm_memory_attributes module_param is made read-only (0444). Make CONFIG_KVM_VM_MEMORY_ATTRIBUTES selectable, only for (CoCo) VM types that might use vm_memory_attributes. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/kvm/Kconfig | 13 +++++++++---- virt/kvm/kvm_main.c | 1 + 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig index b6d65ee664d0f..8b97d341bd33f 100644 --- a/arch/x86/kvm/Kconfig +++ b/arch/x86/kvm/Kconfig @@ -82,13 +82,20 @@ config KVM_WERROR config KVM_VM_MEMORY_ATTRIBUTES select KVM_MEMORY_ATTRIBUTES - bool + depends on KVM_SW_PROTECTED_VM || KVM_INTEL_TDX || KVM_AMD_SEV + bool "Enable per-VM memory attributes (for CoCo VMs)" + help + Enable support for per-VM memory attributes, which are deprecated in + favor of tracking memory attributes in guest_memfd. Select this if + you need to run CoCo VMs using a VMM that doesn't support guest_memfd + memory attributes. + + If unsure, say N. config KVM_SW_PROTECTED_VM bool "Enable support for KVM software-protected VMs" depends on EXPERT depends on KVM_X86 && X86_64 - select KVM_VM_MEMORY_ATTRIBUTES help Enable support for KVM software-protected VMs. Currently, software- protected VMs are purely a development and testing vehicle for @@ -139,7 +146,6 @@ config KVM_INTEL_TDX bool "Intel Trust Domain Extensions (TDX) support" default y depends on INTEL_TDX_HOST - select KVM_VM_MEMORY_ATTRIBUTES select HAVE_KVM_ARCH_GMEM_POPULATE help Provides support for launching Intel Trust Domain Extensions (TDX) @@ -163,7 +169,6 @@ config KVM_AMD_SEV depends on KVM_AMD && X86_64 depends on CRYPTO_DEV_SP_PSP && !(KVM_AMD=y && CRYPTO_DEV_CCP_DD=m) select ARCH_HAS_CC_PLATFORM - select KVM_VM_MEMORY_ATTRIBUTES select HAVE_KVM_ARCH_GMEM_PREPARE select HAVE_KVM_ARCH_GMEM_INVALIDATE select HAVE_KVM_ARCH_GMEM_POPULATE diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index cec02d68d7039..ba195bb239aaa 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -104,6 +104,7 @@ module_param(allow_unsafe_mappings, bool, 0444); #ifdef CONFIG_KVM_MEMORY_ATTRIBUTES #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES bool vm_memory_attributes = true; +module_param(vm_memory_attributes, bool, 0444); #endif DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes)); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Now that guest_memfd supports tracking private vs. shared within gmem itself, allow userspace to specify INIT_SHARED on a guest_memfd instance for x86 Confidential Computing (CoCo) VMs, so long as per-VM attributes are disabled, i.e. when it's actually possible for a guest_memfd instance to contain shared memory. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- arch/x86/kvm/x86.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1560de1e95be0..6609957ecfea3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -14172,14 +14172,13 @@ bool kvm_arch_no_poll(struct kvm_vcpu *vcpu) } #ifdef CONFIG_KVM_GUEST_MEMFD -/* - * KVM doesn't yet support initializing guest_memfd memory as shared for VMs - * with private memory (the private vs. shared tracking needs to be moved into - * guest_memfd). - */ bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm) { - return !kvm_arch_has_private_mem(kvm); + /* + * INIT_SHARED isn't supported if the memory attributes are per-VM, + * in which case guest_memfd can _only_ be used for private memory. + */ + return !vm_memory_attributes || !kvm_arch_has_private_mem(kvm); } #ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE -- 2.54.0.563.g4f69b47b94-goog From: Michael Roth For vm_memory_attributes=1, in-place conversion/population is not supported, so the initial contents necessarily must need to come from a separate src address, which is enforced by the current implementation. However, for vm_memory_attributes=0, it is possible for guest memory to be initialized directly from userspace by mmap()'ing the guest_memfd and writing to it while the corresponding GPA ranges are in a 'shared' state before converting them to the 'private' state expected by KVM_SEV_SNP_LAUNCH_UPDATE. Update the handling/documentation for KVM_SEV_SNP_LAUNCH_UPDATE to allow for 'uaddr' to be set to NULL when vm_memory_attributes=0, which SNP_LAUNCH_UPDATE will then use to determine when it should/shouldn't copy in data from a separate memory location. Continue to enforce non-NULL for the original vm_memory_attributes=1 case. Signed-off-by: Michael Roth [Added src_page check in error handling path when the firmware command fails] [Dropped ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES] Signed-off-by: Ackerley Tng --- Documentation/virt/kvm/x86/amd-memory-encryption.rst | 15 +++++++++++---- arch/x86/kvm/svm/sev.c | 18 +++++++++++++----- virt/kvm/kvm_main.c | 1 + 3 files changed, 25 insertions(+), 9 deletions(-) diff --git a/Documentation/virt/kvm/x86/amd-memory-encryption.rst b/Documentation/virt/kvm/x86/amd-memory-encryption.rst index b2395dd4769de..43085f65b2d85 100644 --- a/Documentation/virt/kvm/x86/amd-memory-encryption.rst +++ b/Documentation/virt/kvm/x86/amd-memory-encryption.rst @@ -503,7 +503,8 @@ secrets. It is required that the GPA ranges initialized by this command have had the KVM_MEMORY_ATTRIBUTE_PRIVATE attribute set in advance. See the documentation -for KVM_SET_MEMORY_ATTRIBUTES for more details on this aspect. +for KVM_SET_MEMORY_ATTRIBUTES/KVM_SET_MEMORY_ATTRIBUTES2 for more details on +this aspect. Upon success, this command is not guaranteed to have processed the entire range requested. Instead, the ``gfn_start``, ``uaddr``, and ``len`` fields of @@ -511,9 +512,15 @@ range requested. Instead, the ``gfn_start``, ``uaddr``, and ``len`` fields of remaining range that has yet to be processed. The caller should continue calling this command until those fields indicate the entire range has been processed, e.g. ``len`` is 0, ``gfn_start`` is equal to the last GFN in the -range plus 1, and ``uaddr`` is the last byte of the userspace-provided source -buffer address plus 1. In the case where ``type`` is KVM_SEV_SNP_PAGE_TYPE_ZERO, -``uaddr`` will be ignored completely. +range plus 1, and ``uaddr`` (if specified) is the last byte of the +userspace-provided source buffer address plus 1. + +In the case where ``type`` is KVM_SEV_SNP_PAGE_TYPE_ZERO, ``uaddr`` will be +ignored completely. Otherwise, ``uaddr`` is required if +kvm.vm_memory_attributes=1 and optional if kvm.vm_memory_attributes=0, since +in the latter case guest memory can be initialized directly from userspace +prior to converting it to private and passing the GPA range on to this +interface. Parameters (in): struct kvm_sev_snp_launch_update diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index c2126b3c30724..bf10d24907a00 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2343,7 +2343,15 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int level; int ret; - if (WARN_ON_ONCE(sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src_page)) + /* + * For vm_memory_attributes=1, in-place conversion/population is not + * supported, so the initial contents necessarily need to come from a + * separate src address. For vm_memory_attributes=0, this isn't + * necessarily the case, since the pages may have been populated + * directly from userspace before calling KVM_SEV_SNP_LAUNCH_UPDATE. + */ + if (vm_memory_attributes && + sev_populate_args->type != KVM_SEV_SNP_PAGE_TYPE_ZERO && !src_page) return -EINVAL; ret = snp_lookup_rmpentry((u64)pfn, &assigned, &level); @@ -2390,7 +2398,7 @@ static int sev_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, */ if (ret && !snp_page_reclaim(kvm, pfn) && sev_populate_args->type == KVM_SEV_SNP_PAGE_TYPE_CPUID && - sev_populate_args->fw_error == SEV_RET_INVALID_PARAM) { + sev_populate_args->fw_error == SEV_RET_INVALID_PARAM && src_page) { void *src_vaddr = kmap_local_page(src_page); void *dst_vaddr = kmap_local_pfn(pfn); @@ -2422,8 +2430,8 @@ static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp) if (copy_from_user(¶ms, u64_to_user_ptr(argp->data), sizeof(params))) return -EFAULT; - pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d\n", __func__, - params.gfn_start, params.len, params.type, params.flags); + pr_debug("%s: GFN start 0x%llx length 0x%llx type %d flags %d src %llx\n", __func__, + params.gfn_start, params.len, params.type, params.flags, params.uaddr); if (!params.len || !PAGE_ALIGNED(params.len) || params.flags || (params.type != KVM_SEV_SNP_PAGE_TYPE_NORMAL && @@ -2479,7 +2487,7 @@ static int snp_launch_update(struct kvm *kvm, struct kvm_sev_cmd *argp) params.gfn_start += count; params.len -= count * PAGE_SIZE; - if (params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO) + if (src && params.type != KVM_SEV_SNP_PAGE_TYPE_ZERO) params.uaddr += count * PAGE_SIZE; if (copy_to_user(u64_to_user_ptr(argp->data), ¶ms, sizeof(params))) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index ba195bb239aaa..3bf212fd99193 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -105,6 +105,7 @@ module_param(allow_unsafe_mappings, bool, 0444); #ifdef CONFIG_KVM_VM_MEMORY_ATTRIBUTES bool vm_memory_attributes = true; module_param(vm_memory_attributes, bool, 0444); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(vm_memory_attributes); #endif DEFINE_STATIC_CALL_RET0(__kvm_get_memory_attributes, kvm_get_memory_attributes_t); EXPORT_SYMBOL_FOR_KVM_INTERNAL(STATIC_CALL_KEY(__kvm_get_memory_attributes)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Update tdx_gmem_post_populate() to handle cases where a source page is not explicitly provided. Instead of returning -EOPNOTSUPP when src_page is NULL, default to using the page associated with the destination PFN. This change allows for in-place memory conversion where the data is already present in the target PFN, ensuring the TDX module has a valid source page reference for the TDH.MEM.PAGE.ADD operation. Signed-off-by: Ackerley Tng --- Documentation/virt/kvm/x86/intel-tdx.rst | 4 ++++ arch/x86/kvm/vmx/tdx.c | 11 ++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/Documentation/virt/kvm/x86/intel-tdx.rst b/Documentation/virt/kvm/x86/intel-tdx.rst index 6a222e9d09541..fbc0f179dc750 100644 --- a/Documentation/virt/kvm/x86/intel-tdx.rst +++ b/Documentation/virt/kvm/x86/intel-tdx.rst @@ -158,6 +158,10 @@ KVM_TDX_INIT_MEM_REGION Initialize @nr_pages TDX guest private memory starting from @gpa with userspace provided data from @source_addr. @source_addr must be PAGE_SIZE-aligned. +If memory attributes are tracked in guest_memfd, pass NULL for +@source_addr to initialize the memory region using memory contents +already populated in guest_memfd memory. + Note, before calling this sub command, memory attribute of the range [gpa, gpa + nr_pages] needs to be private. Userspace can use KVM_SET_MEMORY_ATTRIBUTES to set the attribute. diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c index 04ce321ebdf39..887896e42509d 100644 --- a/arch/x86/kvm/vmx/tdx.c +++ b/arch/x86/kvm/vmx/tdx.c @@ -3116,8 +3116,12 @@ static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, if (KVM_BUG_ON(kvm_tdx->page_add_src, kvm)) return -EIO; - if (!src_page) - return -EOPNOTSUPP; + if (!src_page) { + if (vm_memory_attributes) + return -EOPNOTSUPP; + + src_page = pfn_to_page(pfn); + } kvm_tdx->page_add_src = src_page; ret = kvm_tdp_mmu_map_private_pfn(arg->vcpu, gfn, pfn); @@ -3196,7 +3200,8 @@ static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *c break; } - region.source_addr += PAGE_SIZE; + if (region.source_addr) + region.source_addr += PAGE_SIZE; region.gpa += PAGE_SIZE; region.nr_pages--; -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson When adding a memslot associated a guest_memfd instance, create/dup the guest_memfd before creating the "normal" backing file. This will allow dup'ing the gmem fd as the normal fd when guest_memfd supports mmap(), i.e. to make guest_memfd the _only_ backing source for the memslot. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/lib/kvm_util.c | 45 +++++++++++++++--------------- 1 file changed, 23 insertions(+), 22 deletions(-) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 2a76eca7029d3..df73b23a4c66a 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1054,6 +1054,29 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, if (alignment > 1) region->mmap_size += alignment; + if (flags & KVM_MEM_GUEST_MEMFD) { + if (guest_memfd < 0) { + u32 guest_memfd_flags = 0; + + TEST_ASSERT(!guest_memfd_offset, + "Offset must be zero when creating new guest_memfd"); + guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); + } else { + /* + * Install a unique fd for each memslot so that the fd + * can be closed when the region is deleted without + * needing to track if the fd is owned by the framework + * or by the caller. + */ + guest_memfd = kvm_dup(guest_memfd); + } + + region->region.guest_memfd = guest_memfd; + region->region.guest_memfd_offset = guest_memfd_offset; + } else { + region->region.guest_memfd = -1; + } + region->fd = -1; if (backing_src_is_shared(src_type)) region->fd = kvm_memfd_alloc(region->mmap_size, @@ -1083,28 +1106,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, region->backing_src_type = src_type; - if (flags & KVM_MEM_GUEST_MEMFD) { - if (guest_memfd < 0) { - u32 guest_memfd_flags = 0; - TEST_ASSERT(!guest_memfd_offset, - "Offset must be zero when creating new guest_memfd"); - guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); - } else { - /* - * Install a unique fd for each memslot so that the fd - * can be closed when the region is deleted without - * needing to track if the fd is owned by the framework - * or by the caller. - */ - guest_memfd = kvm_dup(guest_memfd); - } - - region->region.guest_memfd = guest_memfd; - region->region.guest_memfd_offset = guest_memfd_offset; - } else { - region->region.guest_memfd = -1; - } - region->unused_phy_pages = sparsebit_alloc(); if (vm_arch_has_protected_memory(vm)) region->protected_phy_pages = sparsebit_alloc(); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Rename local variables and function parameters for the guest memory file descriptor and its offset to use a "gmem_" prefix instead of "guest_memfd_". No functional change intended. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/kvm_util.h | 6 +++--- tools/testing/selftests/kvm/lib/kvm_util.c | 26 +++++++++++++------------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 2ecaaa0e99654..f19383376ee8e 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -690,17 +690,17 @@ int __vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, gpa_t gpa, u64 size, void *hva); void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, gpa_t gpa, u64 size, void *hva, - u32 guest_memfd, u64 guest_memfd_offset); + u32 gmem_fd, u64 gmem_offset); int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, gpa_t gpa, u64 size, void *hva, - u32 guest_memfd, u64 guest_memfd_offset); + u32 gmem_fd, u64 gmem_offset); void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags); void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags, - int guest_memfd_fd, u64 guest_memfd_offset); + int gmem_fd, u64 gmem_offset); #ifndef vm_arch_has_protected_memory static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index df73b23a4c66a..11da9b7546d03 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -947,7 +947,7 @@ void vm_set_user_memory_region(struct kvm_vm *vm, u32 slot, u32 flags, int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, gpa_t gpa, u64 size, void *hva, - u32 guest_memfd, u64 guest_memfd_offset) + u32 gmem_fd, u64 gmem_offset) { struct kvm_userspace_memory_region2 region = { .slot = slot, @@ -955,8 +955,8 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, .guest_phys_addr = gpa, .memory_size = size, .userspace_addr = (uintptr_t)hva, - .guest_memfd = guest_memfd, - .guest_memfd_offset = guest_memfd_offset, + .guest_memfd = gmem_fd, + .guest_memfd_offset = gmem_offset, }; TEST_REQUIRE_SET_USER_MEMORY_REGION2(); @@ -966,10 +966,10 @@ int __vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, gpa_t gpa, u64 size, void *hva, - u32 guest_memfd, u64 guest_memfd_offset) + u32 gmem_fd, u64 gmem_offset) { int ret = __vm_set_user_memory_region2(vm, slot, flags, gpa, size, hva, - guest_memfd, guest_memfd_offset); + gmem_fd, gmem_offset); TEST_ASSERT(!ret, "KVM_SET_USER_MEMORY_REGION2 failed, errno = %d (%s)", errno, strerror(errno)); @@ -979,7 +979,7 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, /* FIXME: This thing needs to be ripped apart and rewritten. */ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags, - int guest_memfd, u64 guest_memfd_offset) + int gmem_fd, u64 gmem_offset) { int ret; struct userspace_mem_region *region; @@ -1055,12 +1055,12 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, region->mmap_size += alignment; if (flags & KVM_MEM_GUEST_MEMFD) { - if (guest_memfd < 0) { - u32 guest_memfd_flags = 0; + if (gmem_fd < 0) { + u32 gmem_flags = 0; - TEST_ASSERT(!guest_memfd_offset, + TEST_ASSERT(!gmem_offset, "Offset must be zero when creating new guest_memfd"); - guest_memfd = vm_create_guest_memfd(vm, mem_size, guest_memfd_flags); + gmem_fd = vm_create_guest_memfd(vm, mem_size, gmem_flags); } else { /* * Install a unique fd for each memslot so that the fd @@ -1068,11 +1068,11 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, * needing to track if the fd is owned by the framework * or by the caller. */ - guest_memfd = kvm_dup(guest_memfd); + gmem_fd = kvm_dup(gmem_fd); } - region->region.guest_memfd = guest_memfd; - region->region.guest_memfd_offset = guest_memfd_offset; + region->region.guest_memfd = gmem_fd; + region->region.guest_memfd_offset = gmem_offset; } else { region->region.guest_memfd = -1; } -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Accept gmem_flags in vm_mem_add() to be able to create a guest_memfd within vm_mem_add(). When vm_mem_add() is used to set up a guest_memfd for a memslot, set up the provided (or created) gmem_fd as the fd for the user memory region. This makes it available to be mmap()-ed from just like fds from other memory sources. mmap() from guest_memfd using the provided gmem_flags and gmem_offset. Add a kvm_slot_to_fd() helper to provide convenient access to the file descriptor of a memslot. Update existing callers of vm_mem_add() to pass 0 for gmem_flags to preserve existing behavior. Signed-off-by: Sean Christopherson [For guest_memfds, mmap() using gmem_offset instead of 0 all the time.] Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/kvm_util.h | 7 ++++++- tools/testing/selftests/kvm/lib/kvm_util.c | 19 +++++++++++-------- .../selftests/kvm/x86/private_mem_conversions_test.c | 2 +- 3 files changed, 18 insertions(+), 10 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index f19383376ee8e..fb54694e6568b 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -700,7 +700,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, gpa_t gpa, u32 slot, u64 npages, u32 flags); void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags, - int gmem_fd, u64 gmem_offset); + int gmem_fd, u64 gmem_offset, u64 gmem_flags); #ifndef vm_arch_has_protected_memory static inline bool vm_arch_has_protected_memory(struct kvm_vm *vm) @@ -732,6 +732,11 @@ void *addr_gva2hva(struct kvm_vm *vm, gva_t gva); gpa_t addr_hva2gpa(struct kvm_vm *vm, void *hva); void *addr_gpa2alias(struct kvm_vm *vm, gpa_t gpa); +static inline int kvm_slot_to_fd(struct kvm_vm *vm, u32 slot) +{ + return memslot2region(vm, slot)->fd; +} + #ifndef vcpu_arch_put_guest #define vcpu_arch_put_guest(mem, val) do { (mem) = (val); } while (0) #endif diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 11da9b7546d03..ff301e7c22b2f 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -979,12 +979,13 @@ void vm_set_user_memory_region2(struct kvm_vm *vm, u32 slot, u32 flags, /* FIXME: This thing needs to be ripped apart and rewritten. */ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags, - int gmem_fd, u64 gmem_offset) + int gmem_fd, u64 gmem_offset, u64 gmem_flags) { int ret; struct userspace_mem_region *region; size_t backing_src_pagesz = get_backing_src_pagesz(src_type); size_t mem_size = npages * vm->page_size; + off_t mmap_offset = 0; size_t alignment = 1; TEST_REQUIRE_SET_USER_MEMORY_REGION2(); @@ -1056,8 +1057,6 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, if (flags & KVM_MEM_GUEST_MEMFD) { if (gmem_fd < 0) { - u32 gmem_flags = 0; - TEST_ASSERT(!gmem_offset, "Offset must be zero when creating new guest_memfd"); gmem_fd = vm_create_guest_memfd(vm, mem_size, gmem_flags); @@ -1078,13 +1077,17 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, } region->fd = -1; - if (backing_src_is_shared(src_type)) + if (flags & KVM_MEM_GUEST_MEMFD && gmem_flags & GUEST_MEMFD_FLAG_MMAP) { + region->fd = kvm_dup(gmem_fd); + mmap_offset = gmem_offset; + } else if (backing_src_is_shared(src_type)) { region->fd = kvm_memfd_alloc(region->mmap_size, src_type == VM_MEM_SRC_SHARED_HUGETLB); + } - region->mmap_start = kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE, - vm_mem_backing_src_alias(src_type)->flag, - region->fd); + region->mmap_start = __kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE, + vm_mem_backing_src_alias(src_type)->flag, + region->fd, mmap_offset); TEST_ASSERT(!is_backing_src_hugetlb(src_type) || region->mmap_start == align_ptr_up(region->mmap_start, backing_src_pagesz), @@ -1144,7 +1147,7 @@ void vm_userspace_mem_region_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, gpa_t gpa, u32 slot, u64 npages, u32 flags) { - vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0); + vm_mem_add(vm, src_type, gpa, slot, npages, flags, -1, 0, 0); } /* diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 1d2f5d4fd45d7..861baff201e78 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c @@ -399,7 +399,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, u32 nr_v for (i = 0; i < nr_memslots; i++) vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i, BASE_DATA_SLOT + i, slot_size / vm->page_size, - KVM_MEM_GUEST_MEMFD, memfd, slot_size * i); + KVM_MEM_GUEST_MEMFD, memfd, slot_size * i, 0); for (i = 0; i < nr_vcpus; i++) { gpa_t gpa = BASE_DATA_GPA + i * per_cpu_size; -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Add a global variable, kvm_has_gmem_attributes, to make the result of checking for KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES available to all tests. kvm_has_gmem_attributes is true if guest_memfd tracks memory attributes, as opposed to VM-level tracking. This global variable is synced to the guest for testing convenience, to avoid introducing subtle bugs when host/guest state is desynced. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/test_util.h | 2 ++ tools/testing/selftests/kvm/lib/kvm_util.c | 5 +++++ 2 files changed, 7 insertions(+) diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index d9b433b834f1b..c280c3233f502 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -115,6 +115,8 @@ struct guest_random_state { extern u32 guest_random_seed; extern struct guest_random_state guest_rng; +extern bool kvm_has_gmem_attributes; + struct guest_random_state new_guest_random_state(u32 seed); u32 guest_random_u32(struct guest_random_state *state); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index ff301e7c22b2f..5e34593ad79c4 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -24,6 +24,8 @@ u32 guest_random_seed; struct guest_random_state guest_rng; static u32 last_guest_seed; +bool kvm_has_gmem_attributes; + static size_t vcpu_mmap_sz(void); int __open_path_or_exit(const char *path, int flags, const char *enoent_help) @@ -521,6 +523,7 @@ struct kvm_vm *__vm_create(struct vm_shape shape, u32 nr_runnable_vcpus, } guest_rng = new_guest_random_state(guest_random_seed); sync_global_to_guest(vm, guest_rng); + sync_global_to_guest(vm, kvm_has_gmem_attributes); kvm_arch_vm_post_create(vm, nr_runnable_vcpus); @@ -2287,6 +2290,8 @@ void __attribute((constructor)) kvm_selftest_init(void) guest_random_seed = last_guest_seed = random(); pr_info("Random seed: 0x%x\n", guest_random_seed); + kvm_has_gmem_attributes = kvm_has_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES); + kvm_selftest_arch_init(); } -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Add helper functions to kvm_util.h to support calling ioctls, specifically KVM_SET_MEMORY_ATTRIBUTES2, on a guest_memfd file descriptor. Introduce gmem_ioctl() and __gmem_ioctl() macros, modeled after the existing vm_ioctl() helpers, to provide a standard way to call ioctls on a guest_memfd. Add gmem_set_memory_attributes() and its derivatives (gmem_set_private(), gmem_set_shared()) to set memory attributes on a guest_memfd region. Also provide "__" variants that return the ioctl error code instead of aborting the test. These helpers will be used by upcoming guest_memfd tests. To avoid code duplication, factor out the check for supported memory attributes into a new macro, TEST_ASSERT_SUPPORTED_ATTRIBUTES, and use it in both the existing vm_set_memory_attributes() and the new gmem_set_memory_attributes() helpers. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/kvm_util.h | 96 +++++++++++++++++++++++--- 1 file changed, 88 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index fb54694e6568b..f7c49739e97b4 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -392,6 +392,16 @@ static __always_inline void static_assert_is_vcpu(struct kvm_vcpu *vcpu) { } __TEST_ASSERT_VM_VCPU_IOCTL(!ret, #cmd, ret, (vcpu)->vm); \ }) +#define __gmem_ioctl(gmem_fd, cmd, arg) \ + kvm_do_ioctl(gmem_fd, cmd, arg) + +#define gmem_ioctl(gmem_fd, cmd, arg) \ +({ \ + int ret = __gmem_ioctl(gmem_fd, cmd, arg); \ + \ + TEST_ASSERT(!ret, __KVM_IOCTL_ERROR(#cmd, ret)); \ +}) + /* * Looks up and returns the value corresponding to the capability * (KVM_CAP_*) given by cap. @@ -418,8 +428,16 @@ static inline void vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } +/* + * KVM_SET_MEMORY_ATTRIBUTES{,2} overwrites _all_ attributes. These + * flows need significant enhancements to support multiple attributes. + */ +#define TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes) \ + TEST_ASSERT(!(attributes) || (attributes) == KVM_MEMORY_ATTRIBUTE_PRIVATE, \ + "Update me to support multiple attributes!") + static inline void vm_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, - u64 size, u64 attributes) + size_t size, u64 attributes) { struct kvm_memory_attributes attr = { .attributes = attributes, @@ -428,17 +446,11 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, .flags = 0, }; - /* - * KVM_SET_MEMORY_ATTRIBUTES overwrites _all_ attributes. These flows - * need significant enhancements to support multiple attributes. - */ - TEST_ASSERT(!attributes || attributes == KVM_MEMORY_ATTRIBUTE_PRIVATE, - "Update me to support multiple attributes!"); + TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes); vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); } - static inline void vm_mem_set_private(struct kvm_vm *vm, gpa_t gpa, u64 size) { @@ -451,6 +463,74 @@ static inline void vm_mem_set_shared(struct kvm_vm *vm, gpa_t gpa, vm_set_memory_attributes(vm, gpa, size, 0); } +static inline int __gmem_set_memory_attributes(int fd, loff_t offset, + size_t size, u64 attributes, + loff_t *error_offset) +{ + struct kvm_memory_attributes2 attr = { + .attributes = attributes, + .offset = offset, + .size = size, + .flags = 0, + .error_offset = error_offset ? *error_offset : 0, + }; + int r; + + TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes); + + r = __gmem_ioctl(fd, KVM_SET_MEMORY_ATTRIBUTES2, &attr); + + /* Copy error_offset regardless of r so caller can check. */ + if (error_offset) + *error_offset = attr.error_offset; + + return r; +} + +static inline int __gmem_set_private(int fd, loff_t offset, size_t size, + loff_t *error_offset) +{ + return __gmem_set_memory_attributes(fd, offset, size, + KVM_MEMORY_ATTRIBUTE_PRIVATE, + error_offset); +} + +static inline int __gmem_set_shared(int fd, loff_t offset, size_t size, + loff_t *error_offset) +{ + return __gmem_set_memory_attributes(fd, offset, size, 0, + error_offset); +} + +static inline void gmem_set_memory_attributes(int fd, loff_t offset, + size_t size, u64 attributes) +{ + struct kvm_memory_attributes2 attr = { + .attributes = attributes, + .offset = offset, + .size = size, + .flags = 0, + }; + + TEST_ASSERT_SUPPORTED_ATTRIBUTES(attributes); + + __TEST_REQUIRE(kvm_check_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES) > 0, + "No valid attributes for guest_memfd ioctl!"); + + gmem_ioctl(fd, KVM_SET_MEMORY_ATTRIBUTES2, &attr); +} + +static inline void gmem_set_private(int fd, loff_t offset, size_t size) +{ + gmem_set_memory_attributes(fd, offset, size, + KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void gmem_set_shared(int fd, loff_t offset, size_t size) +{ + gmem_set_memory_attributes(fd, offset, size, 0); +} + void vm_guest_mem_fallocate(struct kvm_vm *vm, gpa_t gpa, u64 size, bool punch_hole); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a selftest for the guest_memfd memory attribute conversion ioctls. The test starts the guest_memfd as all-private (the default state), and verifies the basic flow of converting a single page to shared and then back to private. Add infrastructure that supports extensions to other conversion flow tests. This infrastructure will be used in upcoming patches for other conversion tests. Add test as an x86-specific test since guest_memfd's testing vehicle (KVM_X86_SW_PROTECTED_VM) is x86-specific. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/Makefile.kvm | 1 + .../kvm/x86/guest_memfd_conversions_test.c | 199 +++++++++++++++++++++ 2 files changed, 200 insertions(+) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 9118a5a51b89f..6232881be500a 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -148,6 +148,7 @@ TEST_GEN_PROGS_x86 += x86/max_vcpuid_cap_test TEST_GEN_PROGS_x86 += x86/triple_fault_event_test TEST_GEN_PROGS_x86 += x86/recalc_apic_map_test TEST_GEN_PROGS_x86 += x86/aperfmperf_test +TEST_GEN_PROGS_x86 += x86/guest_memfd_conversions_test TEST_GEN_PROGS_x86 += access_tracking_perf_test TEST_GEN_PROGS_x86 += coalesced_io_test TEST_GEN_PROGS_x86 += dirty_log_perf_test diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c new file mode 100644 index 0000000000000..81cf13e399c83 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -0,0 +1,199 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024, Google LLC. + */ +#include +#include + +#include +#include +#include + +#include "kvm_util.h" +#include "kselftest_harness.h" +#include "test_util.h" +#include "ucall_common.h" + +FIXTURE(gmem_conversions) { + struct kvm_vcpu *vcpu; + int gmem_fd; + /* HVA of the first byte of the memory mmap()-ed from gmem_fd. */ + char *mem; +}; + +typedef FIXTURE_DATA(gmem_conversions) test_data_t; + +FIXTURE_SETUP(gmem_conversions) { } + +static size_t page_size; + +static void guest_do_rmw(void); +#define GUEST_MEMFD_SHARING_TEST_GVA 0x90000000ULL + +/* + * Defer setup until the individual test is invoked so that tests can specify + * the number of pages and flags for the guest_memfd instance. + */ +static void gmem_conversions_do_setup(test_data_t *t, int nr_pages, + int gmem_flags) +{ + const struct vm_shape shape = { + .mode = VM_MODE_DEFAULT, + .type = KVM_X86_SW_PROTECTED_VM, + }; + /* + * Use high GPA above APIC_DEFAULT_PHYS_BASE to avoid clashing with + * APIC_DEFAULT_PHYS_BASE. + */ + const gpa_t gpa = SZ_4G; + const u32 slot = 1; + struct kvm_vm *vm; + + vm = __vm_create_shape_with_one_vcpu(shape, &t->vcpu, nr_pages, guest_do_rmw); + + vm_mem_add(vm, VM_MEM_SRC_SHMEM, gpa, slot, nr_pages, + KVM_MEM_GUEST_MEMFD, -1, 0, gmem_flags); + + t->gmem_fd = kvm_slot_to_fd(vm, slot); + t->mem = addr_gpa2hva(vm, gpa); + virt_map(vm, GUEST_MEMFD_SHARING_TEST_GVA, gpa, nr_pages); +} + +static void gmem_conversions_do_teardown(test_data_t *t) +{ + /* No need to close gmem_fd, it's owned by the VM structure. */ + kvm_vm_free(t->vcpu->vm); +} + +FIXTURE_TEARDOWN(gmem_conversions) +{ + gmem_conversions_do_teardown(self); +} + +/* + * In these test definition macros, __nr_pages and nr_pages is used to set up + * the total number of pages in the guest_memfd under test. This will be + * available in the test definitions as nr_pages. + */ + +#define __GMEM_CONVERSION_TEST(test, __nr_pages, flags) \ +static void __gmem_conversions_##test(test_data_t *t, int nr_pages); \ + \ +TEST_F(gmem_conversions, test) \ +{ \ + gmem_conversions_do_setup(self, __nr_pages, flags); \ + __gmem_conversions_##test(self, __nr_pages); \ +} \ +static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \ + +#define GMEM_CONVERSION_TEST(test, __nr_pages, flags) \ + __GMEM_CONVERSION_TEST(test, __nr_pages, (flags) | GUEST_MEMFD_FLAG_MMAP) + +#define __GMEM_CONVERSION_TEST_INIT_PRIVATE(test, __nr_pages) \ + GMEM_CONVERSION_TEST(test, __nr_pages, 0) + +#define GMEM_CONVERSION_TEST_INIT_PRIVATE(test) \ + __GMEM_CONVERSION_TEST_INIT_PRIVATE(test, 1) + +struct guest_check_data { + void *mem; + char expected_val; + char write_val; +}; +static struct guest_check_data guest_data; + +static void guest_do_rmw(void) +{ + for (;;) { + char *mem = READ_ONCE(guest_data.mem); + + GUEST_ASSERT_EQ(READ_ONCE(*mem), READ_ONCE(guest_data.expected_val)); + WRITE_ONCE(*mem, READ_ONCE(guest_data.write_val)); + + GUEST_SYNC(0); + } +} + +static void run_guest_do_rmw(struct kvm_vcpu *vcpu, loff_t pgoff, + char expected_val, char write_val) +{ + struct ucall uc; + int r; + + guest_data.mem = (void *)GUEST_MEMFD_SHARING_TEST_GVA + pgoff * page_size; + guest_data.expected_val = expected_val; + guest_data.write_val = write_val; + sync_global_to_guest(vcpu->vm, guest_data); + + do { + r = __vcpu_run(vcpu); + } while (r == -1 && errno == EINTR); + + TEST_ASSERT_EQ(r, 0); + + switch (get_ucall(vcpu, &uc)) { + case UCALL_ABORT: + REPORT_GUEST_ASSERT(uc); + case UCALL_SYNC: + break; + default: + TEST_FAIL("Unexpected ucall %lu", uc.cmd); + } +} + +static void host_do_rmw(char *mem, loff_t pgoff, char expected_val, + char write_val) +{ + TEST_ASSERT_EQ(READ_ONCE(mem[pgoff * page_size]), expected_val); + WRITE_ONCE(mem[pgoff * page_size], write_val); +} + +static void test_private(test_data_t *t, loff_t pgoff, char starting_val, + char write_val) +{ + TEST_EXPECT_SIGBUS(WRITE_ONCE(t->mem[pgoff * page_size], write_val)); + run_guest_do_rmw(t->vcpu, pgoff, starting_val, write_val); + TEST_EXPECT_SIGBUS(READ_ONCE(t->mem[pgoff * page_size])); +} + +static void test_convert_to_private(test_data_t *t, loff_t pgoff, + char starting_val, char write_val) +{ + gmem_set_private(t->gmem_fd, pgoff * page_size, page_size); + test_private(t, pgoff, starting_val, write_val); +} + +static void test_shared(test_data_t *t, loff_t pgoff, char starting_val, + char host_write_val, char write_val) +{ + host_do_rmw(t->mem, pgoff, starting_val, host_write_val); + run_guest_do_rmw(t->vcpu, pgoff, host_write_val, write_val); + TEST_ASSERT_EQ(READ_ONCE(t->mem[pgoff * page_size]), write_val); +} + +static void test_convert_to_shared(test_data_t *t, loff_t pgoff, + char starting_val, char host_write_val, + char write_val) +{ + gmem_set_shared(t->gmem_fd, pgoff * page_size, page_size); + test_shared(t, pgoff, starting_val, host_write_val, write_val); +} + +GMEM_CONVERSION_TEST_INIT_PRIVATE(init_private) +{ + test_private(t, 0, 0, 'A'); + test_convert_to_shared(t, 0, 'A', 'B', 'C'); + test_convert_to_private(t, 0, 'C', 'E'); +} + + +int main(int argc, char *argv[]) +{ + TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + TEST_REQUIRE(kvm_check_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES) & + KVM_MEMORY_ATTRIBUTE_PRIVATE); + + page_size = getpagesize(); + + return test_harness_run(argc, argv); +} -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a test case to verify that conversions between private and shared memory work correctly when the memory is initially created as shared. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../testing/selftests/kvm/x86/guest_memfd_conversions_test.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 81cf13e399c83..c524457148706 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -95,6 +95,12 @@ static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \ #define GMEM_CONVERSION_TEST_INIT_PRIVATE(test) \ __GMEM_CONVERSION_TEST_INIT_PRIVATE(test, 1) +#define __GMEM_CONVERSION_TEST_INIT_SHARED(test, __nr_pages) \ + GMEM_CONVERSION_TEST(test, __nr_pages, GUEST_MEMFD_FLAG_INIT_SHARED) + +#define GMEM_CONVERSION_TEST_INIT_SHARED(test) \ + __GMEM_CONVERSION_TEST_INIT_SHARED(test, 1) + struct guest_check_data { void *mem; char expected_val; @@ -186,6 +192,12 @@ GMEM_CONVERSION_TEST_INIT_PRIVATE(init_private) test_convert_to_private(t, 0, 'C', 'E'); } +GMEM_CONVERSION_TEST_INIT_SHARED(init_shared) +{ + test_shared(t, 0, 0, 'A', 'B'); + test_convert_to_private(t, 0, 'B', 'C'); + test_convert_to_shared(t, 0, 'C', 'D', 'E'); +} int main(int argc, char *argv[]) { -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng The existing guest_memfd conversion tests only use single-page memory regions. This provides no coverage for multi-page guest_memfd objects, specifically whether KVM correctly handles the page index for conversion operations. An incorrect implementation could, for example, always operate on the first page regardless of the index provided. Add a new test case to verify that conversions between private and shared memory correctly target the specified page within a multi-page guest_memfd. This test also verifies the precision of memory conversions by converting a single page an then iterating through all other pages ensure they remain in their original state. To support this test, add a new GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED macro that handles setting up and tearing down the VM for each page iteration. The teardown logic is adjusted to prevent a double-free in this new scenario. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../kvm/x86/guest_memfd_conversions_test.c | 66 ++++++++++++++++++++++ 1 file changed, 66 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index c524457148706..0cf1351e0e29d 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -61,8 +61,13 @@ static void gmem_conversions_do_setup(test_data_t *t, int nr_pages, static void gmem_conversions_do_teardown(test_data_t *t) { + /* Use NULL to avoid second free in FIXTURE_TEARDOWN (multipage tests). */ + if (!t->vcpu) + return; + /* No need to close gmem_fd, it's owned by the VM structure. */ kvm_vm_free(t->vcpu->vm); + t->vcpu = NULL; } FIXTURE_TEARDOWN(gmem_conversions) @@ -101,6 +106,29 @@ static void __gmem_conversions_##test(test_data_t *t, int nr_pages) \ #define GMEM_CONVERSION_TEST_INIT_SHARED(test) \ __GMEM_CONVERSION_TEST_INIT_SHARED(test, 1) +/* + * Repeats test over nr_pages in a guest_memfd of size nr_pages, providing each + * test iteration with test_page, the index of the page under test in + * guest_memfd. test_page takes values 0..(nr_pages - 1) inclusive. + */ +#define GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(test, __nr_pages) \ +static void __gmem_conversions_multipage_##test(test_data_t *t, int nr_pages, \ + const int test_page); \ + \ +TEST_F(gmem_conversions, test) \ +{ \ + const u64 flags = GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED; \ + int i; \ + \ + for (i = 0; i < __nr_pages; ++i) { \ + gmem_conversions_do_setup(self, __nr_pages, flags); \ + __gmem_conversions_multipage_##test(self, __nr_pages, i); \ + gmem_conversions_do_teardown(self); \ + } \ +} \ +static void __gmem_conversions_multipage_##test(test_data_t *t, int nr_pages, \ + const int test_page) + struct guest_check_data { void *mem; char expected_val; @@ -199,6 +227,44 @@ GMEM_CONVERSION_TEST_INIT_SHARED(init_shared) test_convert_to_shared(t, 0, 'C', 'D', 'E'); } +GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4) +{ + int i; + + /* Get a char that varies with both i and n. */ +#define combine(x, n) ((x << 4) + (n)) +#define i_(n) (combine(i, n)) +#define t_(n) (combine(test_page, n)) + + /* + * Start with the highest index, to catch any errors when, perhaps, the + * first page is returned even for the last index. + */ + for (i = nr_pages - 1; i >= 0; --i) + test_shared(t, i, 0, i_(0), i_(2)); + + test_convert_to_private(t, test_page, t_(2), t_(3)); + + for (i = 0; i < nr_pages; ++i) { + if (i == test_page) + test_private(t, test_page, t_(3), t_(4)); + else + test_shared(t, i, i_(2), i_(3), i_(4)); + } + + test_convert_to_shared(t, test_page, t_(4), t_(5), t_(6)); + + for (i = 0; i < nr_pages; ++i) { + char expected = i == test_page ? t_(6) : i_(4); + + test_shared(t, i, expected, i_(7), i_(8)); + } + +#undef t_ +#undef i_ +#undef combine +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add two test cases to the guest_memfd conversions selftest to cover the scenario where a conversion is requested before any memory has been allocated in the guest_memfd region. The KVM_SET_MEMORY_ATTRIBUTES2 ioctl can be called on a memory region at any time. If the guest had not yet faulted in any pages for that region, the kernel must record the conversion request and apply the requested state when the pages are eventually allocated. The new tests cover both conversion directions. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86/guest_memfd_conversions_test.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 0cf1351e0e29d..20abfdca1e030 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -265,6 +265,20 @@ GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(indexing, 4) #undef combine } +/* + * Test that even if there are no folios yet, conversion requests are recorded + * in guest_memfd. + */ +GMEM_CONVERSION_TEST_INIT_SHARED(before_allocation_shared) +{ + test_convert_to_private(t, 0, 0, 'A'); +} + +GMEM_CONVERSION_TEST_INIT_PRIVATE(before_allocation_private) +{ + test_convert_to_shared(t, 0, 0, 'A', 'B'); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a guest_memfd selftest to verify that memory conversions work correctly with allocated folios in different layouts. By iterating through which pages are initially faulted, the test covers various layouts of contiguous allocated and unallocated regions, exercising conversion with different range layouts. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../kvm/x86/guest_memfd_conversions_test.c | 30 ++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 20abfdca1e030..21d33e2814f9e 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -279,6 +279,36 @@ GMEM_CONVERSION_TEST_INIT_PRIVATE(before_allocation_private) test_convert_to_shared(t, 0, 0, 'A', 'B'); } +/* + * Test that when some of the folios in the conversion range are allocated, + * conversion requests are handled correctly in guest_memfd. Vary the ranges + * allocated before conversion, using test_page, to cover various layouts of + * contiguous allocated and unallocated regions. + */ +GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(unallocated_folios, 8) +{ + const int second_page_to_fault = 4; + int i; + + /* + * Fault 2 of the pages to test filemap range operations except when + * test_page == second_page_to_fault. + */ + host_do_rmw(t->mem, test_page, 0, 'A'); + if (test_page != second_page_to_fault) + host_do_rmw(t->mem, second_page_to_fault, 0, 'A'); + + gmem_set_private(t->gmem_fd, 0, nr_pages * page_size); + for (i = 0; i < nr_pages; ++i) { + char expected = (i == test_page || i == second_page_to_fault) ? 'A' : 0; + + test_private(t, i, expected, 'B'); + } + + for (i = 0; i < nr_pages; ++i) + test_convert_to_shared(t, i, 'B', 'C', 'D'); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a test to verify that deallocating a page in a guest memfd region via fallocate() with FALLOC_FL_PUNCH_HOLE does not alter the shared or private status of the corresponding memory range. When a page backing a guest memfd mapping is deallocated, e.g., by punching a hole or truncating the file, and then subsequently faulted back in, the new page must inherit the correct shared/private status tracked by guest_memfd. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../selftests/kvm/x86/guest_memfd_conversions_test.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 21d33e2814f9e..960b2da8dd16d 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -10,6 +10,7 @@ #include #include "kvm_util.h" +#include "kvm_syscalls.h" #include "kselftest_harness.h" #include "test_util.h" #include "ucall_common.h" @@ -309,6 +310,19 @@ GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(unallocated_folios, 8) test_convert_to_shared(t, i, 'B', 'C', 'D'); } +/* Truncation should not affect shared/private status. */ +GMEM_CONVERSION_TEST_INIT_SHARED(truncate) +{ + host_do_rmw(t->mem, 0, 0, 'A'); + kvm_fallocate(t->gmem_fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, page_size); + host_do_rmw(t->mem, 0, 0, 'A'); + + test_convert_to_private(t, 0, 'A', 'B'); + + kvm_fallocate(t->gmem_fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, page_size); + test_private(t, 0, 0, 'A'); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Add a test to verify that a guest_memfd's shared/private status is consistent across processes, and that any shared pages previously mapped in any process are unmapped from all processes. The test forks a child process after creating the shared guest_memfd region so that the second process exists alongside the main process for the entire test. The processes then take turns to access memory to check that the shared/private status is consistent across processes. Signed-off-by: Sean Christopherson Co-developed-by: Ackerley Tng Signed-off-by: Ackerley Tng --- .../kvm/x86/guest_memfd_conversions_test.c | 74 ++++++++++++++++++++++ 1 file changed, 74 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 960b2da8dd16d..4c33e21f04972 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -323,6 +323,80 @@ GMEM_CONVERSION_TEST_INIT_SHARED(truncate) test_private(t, 0, 0, 'A'); } +/* Test that shared/private memory protections work and are seen from any process. */ +GMEM_CONVERSION_TEST_INIT_SHARED(forked_accesses) +{ + /* + * No races are intended in this test, shared memory is only used to + * coordinate between processes. + */ + static enum { + STATE_INIT, + STATE_CHECK_SHARED, + STATE_DONE_CHECKING_SHARED, + STATE_CHECK_PRIVATE, + STATE_DONE_CHECKING_PRIVATE, + } *test_state; + pid_t child_pid; + + test_state = kvm_mmap(sizeof(*test_state), PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_ANONYMOUS, -1); + +#define TEST_STATE_AWAIT(__state) \ + while (READ_ONCE(*test_state) != __state) { \ + if (child_pid != 0) { \ + int status; \ + pid_t pid; \ + do { \ + pid = waitpid(child_pid, &status, WNOHANG); \ + } while (pid == -1 && errno == EINTR); \ + if (pid == -1) \ + TEST_FAIL("Couldn't check child status."); \ + else if (pid != 0) \ + TEST_FAIL("Child exited prematurely."); \ + } \ + } + +#define TEST_STATE_SET(__state) WRITE_ONCE(*test_state, __state) + + child_pid = fork(); + TEST_ASSERT(child_pid != -1, "fork failed"); + + if (child_pid == 0) { + const char inconsequential = 0xdd; + + TEST_STATE_AWAIT(STATE_CHECK_SHARED); + + /* + * This maps the pages into the child process as well, and tests + * that the conversion process will unmap the guest_memfd memory + * from all processes. + */ + host_do_rmw(t->mem, 0, 0xB, 0xC); + + TEST_STATE_SET(STATE_DONE_CHECKING_SHARED); + TEST_STATE_AWAIT(STATE_CHECK_PRIVATE); + + TEST_EXPECT_SIGBUS(READ_ONCE(t->mem[0])); + TEST_EXPECT_SIGBUS(WRITE_ONCE(t->mem[0], inconsequential)); + + TEST_STATE_SET(STATE_DONE_CHECKING_PRIVATE); + exit(0); + } + + test_shared(t, 0, 0, 0xA, 0xB); + + TEST_STATE_SET(STATE_CHECK_SHARED); + TEST_STATE_AWAIT(STATE_DONE_CHECKING_SHARED); + + test_convert_to_private(t, 0, 0xC, 0xD); + + TEST_STATE_SET(STATE_CHECK_PRIVATE); + TEST_STATE_AWAIT(STATE_DONE_CHECKING_PRIVATE); + + kvm_munmap(test_state, sizeof(*test_state)); +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a selftest to verify that converting a shared guest_memfd page to a private page fails if the page has an elevated reference count. When KVM converts a shared page to a private one, it expects the page to have a reference count equal to the reference counts taken by the filemap. If another kernel subsystem holds a reference to the page, for example via pin_user_pages(), the conversion must be aborted. This test uses vmsplice to increment the refcount of a specific page. The reference is kept on the page by not reading data out from vmsplice's destination pipe. It then attempts to convert a range of pages, including the page with elevated refcount, from shared to private. The test asserts that both bulk and single-page conversion attempts correctly fail with EAGAIN for the pinned page. After the page is unpinned, the test verifies that subsequent conversions succeed. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../kvm/x86/guest_memfd_conversions_test.c | 78 ++++++++++++++++++++++ 1 file changed, 78 insertions(+) diff --git a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c index 4c33e21f04972..00a200a3019ef 100644 --- a/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/guest_memfd_conversions_test.c @@ -397,6 +397,84 @@ GMEM_CONVERSION_TEST_INIT_SHARED(forked_accesses) kvm_munmap(test_state, sizeof(*test_state)); } +static int pin_pipe[2] = { -1, -1 }; + +static void pin_pages(void *vaddr, size_t size) +{ + struct iovec iov = { + .iov_base = vaddr, + .iov_len = size, + }; + + if (pin_pipe[1] < 0) + TEST_ASSERT_EQ(pipe(pin_pipe), 0); + + TEST_ASSERT_EQ(vmsplice(pin_pipe[1], &iov, 1, 0), size); +} + +static void unpin_pages(void) +{ + close(pin_pipe[1]); + pin_pipe[1] = -1; + close(pin_pipe[0]); + pin_pipe[0] = -1; +} + +static void test_convert_to_private_fails(test_data_t *t, loff_t pgoff, + size_t nr_pages, + loff_t expected_error_offset) +{ + loff_t offset = pgoff * page_size; + loff_t error_offset = 0; + int ret; + + do { + ret = __gmem_set_private(t->gmem_fd, offset, + nr_pages * page_size, &error_offset); + } while (ret == -1 && errno == EINTR); + TEST_ASSERT(ret == -1 && errno == EAGAIN, + "Wanted EAGAIN on page %lu, got %d (ret = %d)", pgoff, + errno, ret); + TEST_ASSERT_EQ(error_offset, expected_error_offset); +} + +GMEM_CONVERSION_MULTIPAGE_TEST_INIT_SHARED(elevated_refcount, 4) +{ + int i; + + pin_pages(t->mem + test_page * page_size, page_size); + + for (i = 0; i < nr_pages; i++) + test_shared(t, i, 0, 'A', 'B'); + + /* + * Converting in bulk should fail as long any page in the range has + * unexpected refcounts. + */ + test_convert_to_private_fails(t, 0, nr_pages, test_page * page_size); + + for (i = 0; i < nr_pages; i++) { + /* + * Converting page-wise should also fail as long any page in the + * range has unexpected refcounts. + */ + if (i == test_page) + test_convert_to_private_fails(t, i, 1, test_page * page_size); + else + test_convert_to_private(t, i, 'B', 'C'); + } + + unpin_pages(); + + gmem_set_private(t->gmem_fd, 0, nr_pages * page_size); + + for (i = 0; i < nr_pages; i++) { + char expected = i == test_page ? 'B' : 'C'; + + test_private(t, i, expected, 'D'); + } +} + int main(int argc, char *argv[]) { TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng private_mem_conversions_test used to reset the shared memory that was used for the test to an initial pattern at the end of each test iteration. Then, it would punch out the pages, which would zero memory. Without in-place conversion, the resetting would write shared memory, and hole-punching will zero private memory, hence resetting the test to the state at the beginning of the for loop. With in-place conversion, resetting writes memory as shared, and hole-punching zeroes the same physical memory, hence undoing the reset done before the hole punch. Move the resetting after the hole-punching, and reset the entire PER_CPU_DATA_SIZE instead of just the tested range. With in-place conversion, this zeroes and then resets the same physical memory. Without in-place conversion, the private memory is zeroed, and the shared memory is reset to init_p. This is sufficient since at each test stage, the memory is assumed to start as shared, and private memory is always assumed to start zeroed. Conversion zeroes memory, so the future test stages will work as expected. Fixes: 43f623f350ce1 ("KVM: selftests: Add x86-only selftest for private memory conversions") Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/x86/private_mem_conversions_test.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 861baff201e78..289ad10063fca 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c @@ -202,15 +202,18 @@ static void guest_test_explicit_conversion(u64 base_gpa, bool do_fallocate) guest_sync_shared(gpa, size, p3, p4); memcmp_g(gpa, p4, size); - /* Reset the shared memory back to the initial pattern. */ - memset((void *)gpa, init_p, size); - /* * Free (via PUNCH_HOLE) *all* private memory so that the next * iteration starts from a clean slate, e.g. with respect to * whether or not there are pages/folios in guest_mem. */ guest_map_shared(base_gpa, PER_CPU_DATA_SIZE, true); + + /* + * Hole-punching above zeroed private memory. Reset shared + * memory in preparation for the next GUEST_STAGE. + */ + memset((void *)base_gpa, init_p, PER_CPU_DATA_SIZE); } } -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Introduce a new helper, kvm_gpa_to_guest_memfd(), to find the guest_memfd-related details of a memory region that contains a given guest physical address (GPA). The function returns the file descriptor for the memfd, the offset into the file that corresponds to the GPA, and the number of bytes remaining in the region from that GPA. kvm_gpa_to_guest_memfd() was factored out from vm_guest_mem_fallocate(); refactor vm_guest_mem_fallocate() to use the new helper. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- tools/testing/selftests/kvm/include/kvm_util.h | 3 +++ tools/testing/selftests/kvm/lib/kvm_util.c | 37 ++++++++++++++++---------- 2 files changed, 26 insertions(+), 14 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index f7c49739e97b4..4ad184ce3df68 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -428,6 +428,9 @@ static inline void vm_enable_cap(struct kvm_vm *vm, u32 cap, u64 arg0) vm_ioctl(vm, KVM_ENABLE_CAP, &enable_cap); } +int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, gpa_t gpa, off_t *fd_offset, + size_t *nr_bytes); + /* * KVM_SET_MEMORY_ATTRIBUTES{,2} overwrites _all_ attributes. These * flows need significant enhancements to support multiple attributes. diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 5e34593ad79c4..8ff09e179ff5c 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1283,27 +1283,20 @@ void vm_guest_mem_fallocate(struct kvm_vm *vm, u64 base, u64 size, bool punch_hole) { const int mode = FALLOC_FL_KEEP_SIZE | (punch_hole ? FALLOC_FL_PUNCH_HOLE : 0); - struct userspace_mem_region *region; u64 end = base + size; - gpa_t gpa, len; off_t fd_offset; - int ret; + int fd, ret; + size_t len; + gpa_t gpa; for (gpa = base; gpa < end; gpa += len) { - u64 offset; - - region = userspace_mem_region_find(vm, gpa, gpa); - TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, - "Private memory region not found for GPA 0x%lx", gpa); + fd = kvm_gpa_to_guest_memfd(vm, gpa, &fd_offset, &len); + len = min(end - gpa, len); - offset = gpa - region->region.guest_phys_addr; - fd_offset = region->region.guest_memfd_offset + offset; - len = min_t(u64, end - gpa, region->region.memory_size - offset); - - ret = fallocate(region->region.guest_memfd, mode, fd_offset, len); + ret = fallocate(fd, mode, fd_offset, len); TEST_ASSERT(!ret, "fallocate() failed to %s at %lx (len = %lu), fd = %d, mode = %x, offset = %lx", punch_hole ? "punch hole" : "allocate", gpa, len, - region->region.guest_memfd, mode, fd_offset); + fd, mode, fd_offset); } } @@ -1640,6 +1633,22 @@ void *addr_gpa2alias(struct kvm_vm *vm, gpa_t gpa) return (void *) ((uintptr_t) region->host_alias + offset); } +int kvm_gpa_to_guest_memfd(struct kvm_vm *vm, gpa_t gpa, off_t *fd_offset, + size_t *nr_bytes) +{ + struct userspace_mem_region *region; + gpa_t gpa_offset; + + region = userspace_mem_region_find(vm, gpa, gpa); + TEST_ASSERT(region && region->region.flags & KVM_MEM_GUEST_MEMFD, + "guest_memfd memory region not found for GPA 0x%lx", gpa); + + gpa_offset = gpa - region->region.guest_phys_addr; + *fd_offset = region->region.guest_memfd_offset + gpa_offset; + *nr_bytes = region->region.memory_size - gpa_offset; + return region->region.guest_memfd; +} + /* Create an interrupt controller chip for the specified VM. */ void vm_create_irqchip(struct kvm_vm *vm) { -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Introduce vm_mem_set_memory_attributes(), which handles setting of memory attributes for a range of guest physical addresses, regardless of whether the attributes should be set via guest_memfd or via the memory attributes at the VM level. Refactor existing vm_mem_set_{shared,private} functions to use the new function. Opportunistically update the size parameter to use size_t instead of u64. Signed-off-by: Sean Christopherson Co-developed-by: Ackerley Tng Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/kvm_util.h | 46 +++++++++++++++++++------- 1 file changed, 34 insertions(+), 12 deletions(-) diff --git a/tools/testing/selftests/kvm/include/kvm_util.h b/tools/testing/selftests/kvm/include/kvm_util.h index 4ad184ce3df68..dc70c6da63fa9 100644 --- a/tools/testing/selftests/kvm/include/kvm_util.h +++ b/tools/testing/selftests/kvm/include/kvm_util.h @@ -454,18 +454,6 @@ static inline void vm_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, vm_ioctl(vm, KVM_SET_MEMORY_ATTRIBUTES, &attr); } -static inline void vm_mem_set_private(struct kvm_vm *vm, gpa_t gpa, - u64 size) -{ - vm_set_memory_attributes(vm, gpa, size, KVM_MEMORY_ATTRIBUTE_PRIVATE); -} - -static inline void vm_mem_set_shared(struct kvm_vm *vm, gpa_t gpa, - u64 size) -{ - vm_set_memory_attributes(vm, gpa, size, 0); -} - static inline int __gmem_set_memory_attributes(int fd, loff_t offset, size_t size, u64 attributes, loff_t *error_offset) @@ -534,6 +522,40 @@ static inline void gmem_set_shared(int fd, loff_t offset, size_t size) gmem_set_memory_attributes(fd, offset, size, 0); } +static inline void vm_mem_set_memory_attributes(struct kvm_vm *vm, gpa_t gpa, + size_t size, u64 attrs) +{ + if (kvm_has_gmem_attributes) { + gpa_t end = gpa + size; + off_t fd_offset; + gpa_t addr; + size_t len; + int fd; + + for (addr = gpa; addr < end; addr += len) { + fd = kvm_gpa_to_guest_memfd(vm, addr, &fd_offset, &len); + len = min(end - addr, len); + + gmem_set_memory_attributes(fd, fd_offset, len, attrs); + } + } else { + vm_set_memory_attributes(vm, gpa, size, attrs); + } +} + +static inline void vm_mem_set_private(struct kvm_vm *vm, gpa_t gpa, + size_t size) +{ + vm_mem_set_memory_attributes(vm, gpa, size, + KVM_MEMORY_ATTRIBUTE_PRIVATE); +} + +static inline void vm_mem_set_shared(struct kvm_vm *vm, gpa_t gpa, + size_t size) +{ + vm_mem_set_memory_attributes(vm, gpa, size, 0); +} + void vm_guest_mem_fallocate(struct kvm_vm *vm, gpa_t gpa, u64 size, bool punch_hole); -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Check that a valid fd provided to mmap() must be accompanied by MAP_SHARED. With an invalid fd (usually used for anonymous mappings), there are no constraints on mmap() flags. Add this check to make sure that when a guest_memfd is used as region->fd, the flag provided to mmap() will include MAP_SHARED. Signed-off-by: Sean Christopherson [Rephrase assertion message.] Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/lib/kvm_util.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index 8ff09e179ff5c..efad3e6b19f4b 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -1088,6 +1088,9 @@ void vm_mem_add(struct kvm_vm *vm, enum vm_mem_backing_src_type src_type, src_type == VM_MEM_SRC_SHARED_HUGETLB); } + TEST_ASSERT(region->fd == -1 || backing_src_is_shared(src_type), + "A valid fd provided to mmap() must be accompanied by MAP_SHARED."); + region->mmap_start = __kvm_mmap(region->mmap_size, PROT_READ | PROT_WRITE, vm_mem_backing_src_alias(src_type)->flag, region->fd, mmap_offset); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng The TEST_EXPECT_SIGBUS macro is not thread-safe as it uses a global sigjmp_buf and installs a global SIGBUS signal handler. If multiple threads execute the macro concurrently, they will race on installing the signal handler and stomp on other threads' jump buffers, leading to incorrect test behavior. Make TEST_EXPECT_SIGBUS thread-safe with the following changes: Share the KVM tests' global signal handler. sigaction() applies to all threads; without sharing a global signal handler, one thread may have removed the signal handler that another thread added, hence leading to unexpected signals. The alternative of layering signal handlers was considered, but calling sigaction() within TEST_EXPECT_SIGBUS() necessarily creates a race. To avoid adding new setup and teardown routines to do sigaction() and keep usage of TEST_EXPECT_SIGBUS() simple, share the KVM tests' global signal handler. Opportunistically rename report_unexpected_signal to catchall_signal_handler. To continue to only expect SIGBUS within specific regions of code, use a thread-specific variable, expecting_sigbus, to replace installing and removing signal handlers. Make the execution environment for the thread, sigjmp_buf, a thread-specific variable. As part of TEST_EXPECT_SIGBUS(), assert the prerequisite for this setup, that the current signal handler is the catchall_signal_handler. Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/include/test_util.h | 32 +++++++++++++------------ tools/testing/selftests/kvm/lib/kvm_util.c | 18 ++++++++++---- tools/testing/selftests/kvm/lib/test_util.c | 7 ------ 3 files changed, 30 insertions(+), 27 deletions(-) diff --git a/tools/testing/selftests/kvm/include/test_util.h b/tools/testing/selftests/kvm/include/test_util.h index c280c3233f502..c9ba4e010f0b8 100644 --- a/tools/testing/selftests/kvm/include/test_util.h +++ b/tools/testing/selftests/kvm/include/test_util.h @@ -82,21 +82,23 @@ do { \ __builtin_unreachable(); \ } while (0) -extern sigjmp_buf expect_sigbus_jmpbuf; -void expect_sigbus_handler(int signum); - -#define TEST_EXPECT_SIGBUS(action) \ -do { \ - struct sigaction sa_old, sa_new = { \ - .sa_handler = expect_sigbus_handler, \ - }; \ - \ - sigaction(SIGBUS, &sa_new, &sa_old); \ - if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \ - action; \ - TEST_FAIL("'%s' should have triggered SIGBUS", #action); \ - } \ - sigaction(SIGBUS, &sa_old, NULL); \ +extern __thread sigjmp_buf expect_sigbus_jmpbuf; +extern __thread volatile sig_atomic_t expecting_sigbus; +extern void catchall_signal_handler(int signum); + +#define TEST_EXPECT_SIGBUS(action) \ +do { \ + struct sigaction __sa = {}; \ + \ + TEST_ASSERT_EQ(sigaction(SIGBUS, NULL, &__sa), 0); \ + TEST_ASSERT_EQ(__sa.sa_handler, &catchall_signal_handler); \ + \ + expecting_sigbus = true; \ + if (sigsetjmp(expect_sigbus_jmpbuf, 1) == 0) { \ + action; \ + TEST_FAIL("'%s' should have triggered SIGBUS", #action);\ + } \ + expecting_sigbus = false; \ } while (0) size_t parse_size(const char *size); diff --git a/tools/testing/selftests/kvm/lib/kvm_util.c b/tools/testing/selftests/kvm/lib/kvm_util.c index efad3e6b19f4b..d1befa3f4b305 100644 --- a/tools/testing/selftests/kvm/lib/kvm_util.c +++ b/tools/testing/selftests/kvm/lib/kvm_util.c @@ -2270,13 +2270,20 @@ __weak void kvm_selftest_arch_init(void) { } -static void report_unexpected_signal(int signum) +__thread sigjmp_buf expect_sigbus_jmpbuf; +__thread volatile sig_atomic_t expecting_sigbus; + +void catchall_signal_handler(int signum) { + switch (signum) { + case SIGBUS: { + if (expecting_sigbus) + siglongjmp(expect_sigbus_jmpbuf, 1); + + TEST_FAIL("Unexpected SIGBUS (%d)\n", signum); + } #define KVM_CASE_SIGNUM(sig) \ case sig: TEST_FAIL("Unexpected " #sig " (%d)\n", signum) - - switch (signum) { - KVM_CASE_SIGNUM(SIGBUS); KVM_CASE_SIGNUM(SIGSEGV); KVM_CASE_SIGNUM(SIGILL); KVM_CASE_SIGNUM(SIGFPE); @@ -2288,12 +2295,13 @@ static void report_unexpected_signal(int signum) void __attribute((constructor)) kvm_selftest_init(void) { struct sigaction sig_sa = { - .sa_handler = report_unexpected_signal, + .sa_handler = catchall_signal_handler, }; /* Tell stdout not to buffer its content. */ setbuf(stdout, NULL); + expecting_sigbus = false; sigaction(SIGBUS, &sig_sa, NULL); sigaction(SIGSEGV, &sig_sa, NULL); sigaction(SIGILL, &sig_sa, NULL); diff --git a/tools/testing/selftests/kvm/lib/test_util.c b/tools/testing/selftests/kvm/lib/test_util.c index bab1bd2b775b6..30eb701e4becd 100644 --- a/tools/testing/selftests/kvm/lib/test_util.c +++ b/tools/testing/selftests/kvm/lib/test_util.c @@ -18,13 +18,6 @@ #include "test_util.h" -sigjmp_buf expect_sigbus_jmpbuf; - -void __attribute__((used)) expect_sigbus_handler(int signum) -{ - siglongjmp(expect_sigbus_jmpbuf, 1); -} - /* * Random number generator that is usable from guest code. This is the * Park-Miller LCG using standard constants. -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Update the private memory conversions selftest to also test conversions that are done "in-place" via per-guest_memfd memory attributes. In-place conversions require the host to be able to mmap() the guest_memfd so that the host and guest can share the same backing physical memory. This includes several updates, that are conditioned on the system supporting per-guest_memfd attributes (kvm_has_gmem_attributes): 1. Set up guest_memfd requesting MMAP and INIT_SHARED. 2. With in-place conversions, the host's mapping points directly to the guest's memory. When the guest converts a region to private, host access to that region is blocked. Update the test to expect a SIGBUS when attempting to access the host virtual address (HVA) of private memory. 3. Use vm_mem_set_memory_attributes(), which chooses how to set memory attributes based on whether kvm_has_gmem_attributes. Restrict the test to using VM_MEM_SRC_SHMEM because guest_memfd's required mmap() flags and page sizes happens to align with those of VM_MEM_SRC_SHMEM. As long as VM_MEM_SRC_SHMEM is used for src_type, vm_mem_add() works as intended. Signed-off-by: Ackerley Tng Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson --- .../kvm/x86/private_mem_conversions_test.c | 44 ++++++++++++++++++---- 1 file changed, 36 insertions(+), 8 deletions(-) diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c index 289ad10063fca..4308c67952310 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.c @@ -306,9 +306,12 @@ static void handle_exit_hypercall(struct kvm_vcpu *vcpu) if (do_fallocate) vm_guest_mem_fallocate(vm, gpa, size, map_shared); - if (set_attributes) - vm_set_memory_attributes(vm, gpa, size, - map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE); + if (set_attributes) { + u64 attrs = map_shared ? 0 : KVM_MEMORY_ATTRIBUTE_PRIVATE; + + vm_mem_set_memory_attributes(vm, gpa, size, attrs); + } + run->hypercall.ret = 0; } @@ -352,8 +355,20 @@ static void *__test_mem_conversions(void *__vcpu) size_t nr_bytes = min_t(size_t, vm->page_size, size - i); u8 *hva = addr_gpa2hva(vm, gpa + i); - /* In all cases, the host should observe the shared data. */ - memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); + /* + * When using per-guest_memfd memory attributes, + * i.e. in-place conversion, host accesses will + * point at guest memory and should SIGBUS when + * guest memory is private. When using per-VM + * attributes, i.e. separate backing for shared + * vs. private, the host should always observe + * the shared data. + */ + if (kvm_has_gmem_attributes && + uc.args[0] == SYNC_PRIVATE) + TEST_EXPECT_SIGBUS(READ_ONCE(*hva)); + else + memcmp_h(hva, gpa + i, uc.args[3], nr_bytes); /* For shared, write the new pattern to guest memory. */ if (uc.args[0] == SYNC_SHARED) @@ -382,6 +397,7 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, u32 nr_v const size_t slot_size = memfd_size / nr_memslots; struct kvm_vcpu *vcpus[KVM_MAX_VCPUS]; pthread_t threads[KVM_MAX_VCPUS]; + u64 gmem_flags; struct kvm_vm *vm; int memfd, i; @@ -397,12 +413,17 @@ static void test_mem_conversions(enum vm_mem_backing_src_type src_type, u32 nr_v vm_enable_cap(vm, KVM_CAP_EXIT_HYPERCALL, (1 << KVM_HC_MAP_GPA_RANGE)); - memfd = vm_create_guest_memfd(vm, memfd_size, 0); + if (kvm_has_gmem_attributes) + gmem_flags = GUEST_MEMFD_FLAG_MMAP | GUEST_MEMFD_FLAG_INIT_SHARED; + else + gmem_flags = 0; + + memfd = vm_create_guest_memfd(vm, memfd_size, gmem_flags); for (i = 0; i < nr_memslots; i++) vm_mem_add(vm, src_type, BASE_DATA_GPA + slot_size * i, BASE_DATA_SLOT + i, slot_size / vm->page_size, - KVM_MEM_GUEST_MEMFD, memfd, slot_size * i, 0); + KVM_MEM_GUEST_MEMFD, memfd, slot_size * i, gmem_flags); for (i = 0; i < nr_vcpus; i++) { gpa_t gpa = BASE_DATA_GPA + i * per_cpu_size; @@ -452,17 +473,24 @@ static void usage(const char *cmd) int main(int argc, char *argv[]) { - enum vm_mem_backing_src_type src_type = DEFAULT_VM_MEM_SRC; + enum vm_mem_backing_src_type src_type; u32 nr_memslots = 1; u32 nr_vcpus = 1; int opt; TEST_REQUIRE(kvm_check_cap(KVM_CAP_VM_TYPES) & BIT(KVM_X86_SW_PROTECTED_VM)); + src_type = kvm_has_gmem_attributes ? VM_MEM_SRC_SHMEM : + DEFAULT_VM_MEM_SRC; + while ((opt = getopt(argc, argv, "hm:s:n:")) != -1) { switch (opt) { case 's': src_type = parse_backing_src_type(optarg); + TEST_ASSERT(!kvm_has_gmem_attributes || + src_type == VM_MEM_SRC_SHMEM, + "Testing in-place conversions, only %s mem_type supported\n", + vm_mem_backing_src_alias(VM_MEM_SRC_SHMEM)->name); break; case 'n': nr_vcpus = atoi_positive("nr_vcpus", optarg); -- 2.54.0.563.g4f69b47b94-goog From: Ackerley Tng Add a wrapper script to simplify running the private_mem_conversions_test with a variety of configurations. Manually invoking the test for all supported memory backing source types is tedious. The script automatically detects the availability of 2MB and 1GB hugepages and builds a list of source types to test. It then iterates through the list, running the test for each type with both a single memslot and multiple memslots. This makes it easier to get comprehensive test coverage across different memory configurations. Add and use a helper program in C to be able to read KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES as defined in header files and then issue the ioctl to read the KVM CAP. Signed-off-by: Ackerley Tng --- tools/testing/selftests/kvm/Makefile.kvm | 4 + .../selftests/kvm/kvm_has_gmem_attributes.c | 17 +++ .../kvm/x86/private_mem_conversions_test.sh | 128 +++++++++++++++++++++ 3 files changed, 149 insertions(+) diff --git a/tools/testing/selftests/kvm/Makefile.kvm b/tools/testing/selftests/kvm/Makefile.kvm index 6232881be500a..e5769268936a7 100644 --- a/tools/testing/selftests/kvm/Makefile.kvm +++ b/tools/testing/selftests/kvm/Makefile.kvm @@ -54,6 +54,7 @@ LIBKVM_loongarch += lib/loongarch/exception.S # Non-compiled test targets TEST_PROGS_x86 += x86/nx_huge_pages_test.sh +TEST_PROGS_x86 += x86/private_mem_conversions_test.sh # Compiled test targets valid on all architectures with libkvm support TEST_GEN_PROGS_COMMON = demand_paging_test @@ -67,6 +68,8 @@ TEST_GEN_PROGS_COMMON += set_memory_region_test TEST_GEN_PROGS_COMMON += memslot_modification_stress_test TEST_GEN_PROGS_COMMON += memslot_perf_test +TEST_GEN_PROGS_EXTENDED_COMMON += kvm_has_gmem_attributes + # Compiled test targets TEST_GEN_PROGS_x86 = $(TEST_GEN_PROGS_COMMON) TEST_GEN_PROGS_x86 += x86/cpuid_test @@ -245,6 +248,7 @@ SPLIT_TESTS += get-reg-list TEST_PROGS += $(TEST_PROGS_$(ARCH)) TEST_GEN_PROGS += $(TEST_GEN_PROGS_$(ARCH)) +TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_COMMON) TEST_GEN_PROGS_EXTENDED += $(TEST_GEN_PROGS_EXTENDED_$(ARCH)) LIBKVM += $(LIBKVM_$(ARCH)) diff --git a/tools/testing/selftests/kvm/kvm_has_gmem_attributes.c b/tools/testing/selftests/kvm/kvm_has_gmem_attributes.c new file mode 100644 index 0000000000000..4f361349412fb --- /dev/null +++ b/tools/testing/selftests/kvm/kvm_has_gmem_attributes.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Utility to check if KVM supports guest_memfd attributes. + * + * Copyright (C) 2025, Google LLC. + */ + +#include + +#include "kvm_util.h" + +int main(void) +{ + printf("%u\n", kvm_check_cap(KVM_CAP_GUEST_MEMFD_MEMORY_ATTRIBUTES) > 0); + + return 0; +} diff --git a/tools/testing/selftests/kvm/x86/private_mem_conversions_test.sh b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.sh new file mode 100755 index 0000000000000..7179a4fcdd498 --- /dev/null +++ b/tools/testing/selftests/kvm/x86/private_mem_conversions_test.sh @@ -0,0 +1,128 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0-only +# +# Wrapper script which runs different test setups of +# private_mem_conversions_test. +# +# Copyright (C) 2025, Google LLC. + +NUM_VCPUS_TO_TEST=4 +NUM_MEMSLOTS_TO_TEST=$NUM_VCPUS_TO_TEST + +# Required pages are based on the test setup in the C code. +REQUIRED_NUM_2M_HUGEPAGES=$((1024 * NUM_VCPUS_TO_TEST)) +REQUIRED_NUM_1G_HUGEPAGES=$((2 * NUM_VCPUS_TO_TEST)) + +get_hugepage_count() { + local page_size_kb=$1 + local path="/sys/kernel/mm/hugepages/hugepages-${page_size_kb}kB/nr_hugepages" + if [ -f "$path" ]; then + cat "$path" + else + echo 0 + fi +} + +get_default_hugepage_size_in_kb() { + local size=$(grep "Hugepagesize:" /proc/meminfo | awk '{print $2}') + echo "$size" +} + +run_tests() { + local executable_path=$1 + local src_type=$2 + local num_memslots=$3 + local num_vcpus=$4 + + echo "$executable_path -s $src_type -m $num_memslots -n $num_vcpus" + "$executable_path" -s "$src_type" -m "$num_memslots" -n "$num_vcpus" +} + +script_dir=$(dirname "$(realpath "$0")") +test_executable="${script_dir}/private_mem_conversions_test" +kvm_has_gmem_attributes_tool="${script_dir}/../kvm_has_gmem_attributes" + +if [ ! -f "$test_executable" ]; then + echo "Error: Test executable not found at '$test_executable'" >&2 + exit 1 +fi + +if [ ! -f "$kvm_has_gmem_attributes_tool" ]; then + echo "Error: kvm_has_gmem_attributes utility not found at '$kvm_has_gmem_attributes_tool'" >&2 + exit 1 +fi + +kvm_has_gmem_attributes=$("$kvm_has_gmem_attributes_tool" | tail -n1) + +if [ "$kvm_has_gmem_attributes" -eq 1 ]; then + backing_src_types=("shmem") +else + hugepage_2mb_count=$(get_hugepage_count 2048) + hugepage_2mb_enabled=$((hugepage_2mb_count >= REQUIRED_NUM_2M_HUGEPAGES)) + hugepage_1gb_count=$(get_hugepage_count 1048576) + hugepage_1gb_enabled=$((hugepage_1gb_count >= REQUIRED_NUM_1G_HUGEPAGES)) + + default_hugepage_size_kb=$(get_default_hugepage_size_in_kb) + hugepage_default_enabled=0 + if [ "$default_hugepage_size_kb" -eq 2048 ]; then + hugepage_default_enabled=$hugepage_2mb_enabled + elif [ "$default_hugepage_size_kb" -eq 1048576 ]; then + hugepage_default_enabled=$hugepage_1gb_enabled + fi + + backing_src_types=("anonymous" "anonymous_thp") + + if [ "$hugepage_default_enabled" -eq 1 ]; then + backing_src_types+=("anonymous_hugetlb") + else + echo "skipping anonymous_hugetlb backing source type" + fi + + if [ "$hugepage_2mb_enabled" -eq 1 ]; then + backing_src_types+=("anonymous_hugetlb_2mb") + else + echo "skipping anonymous_hugetlb_2mb backing source type" + fi + + if [ "$hugepage_1gb_enabled" -eq 1 ]; then + backing_src_types+=("anonymous_hugetlb_1gb") + else + echo "skipping anonymous_hugetlb_1gb backing source type" + fi + + backing_src_types+=("shmem") + + if [ "$hugepage_default_enabled" -eq 1 ]; then + backing_src_types+=("shared_hugetlb") + else + echo "skipping shared_hugetlb backing source type" + fi +fi + +return_code=0 +for i in "${!backing_src_types[@]}"; do + src_type=${backing_src_types[$i]} + if [ "$i" -gt 0 ]; then + echo + fi + + if ! run_tests "$test_executable" "$src_type" 1 1; then + return_code=$? + echo "Test failed for source type '$src_type'. Arguments: -s $src_type -m 1 -n 1" >&2 + break + fi + + if ! run_tests "$test_executable" "$src_type" 1 "$NUM_VCPUS_TO_TEST"; then + return_code=$? + echo "Test failed for source type '$src_type'. Arguments: -s $src_type -m 1 -n $NUM_VCPUS_TO_TEST" >&2 + break + fi + + if ! run_tests "$test_executable" "$src_type" "$NUM_MEMSLOTS_TO_TEST" "$NUM_VCPUS_TO_TEST"; then + return_code=$? + echo "Test failed for source type '$src_type'. Arguments: -s $src_type -m $NUM_MEMSLOTS_TO_TEST -n $NUM_VCPUS_TO_TEST" >&2 + break + fi +done + +exit "$return_code" -- 2.54.0.563.g4f69b47b94-goog From: Sean Christopherson Skip setting memory to private in the private memory exits test when using per-gmem memory attributes, as memory is initialized to private by default for guest_memfd, and using vm_mem_set_private() on a guest_memfd instance requires creating guest_memfd with GUEST_MEMFD_FLAG_MMAP (which is totally doable, but would need to be conditional and is ultimately unnecessary). Expect an emulated MMIO instead of a memory fault exit when attributes are per-gmem, as deleting the memslot effectively drops the private status, i.e. the GPA becomes shared and thus supports emulated MMIO. Skip the "memslot not private" test entirely, as private vs. shared state for x86 software-protected VMs comes from the memory attributes themselves, and so when doing in-place conversions there can never be a disconnect between the expected and actual states. Signed-off-by: Sean Christopherson Signed-off-by: Ackerley Tng --- .../selftests/kvm/x86/private_mem_kvm_exits_test.c | 36 ++++++++++++++++++---- 1 file changed, 30 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c index 10db9fe6d9063..70ed16066c63e 100644 --- a/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c +++ b/tools/testing/selftests/kvm/x86/private_mem_kvm_exits_test.c @@ -62,8 +62,9 @@ static void test_private_access_memslot_deleted(void) virt_map(vm, EXITS_TEST_GVA, EXITS_TEST_GPA, EXITS_TEST_NPAGES); - /* Request to access page privately */ - vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); + /* Request to access page privately. */ + if (!kvm_has_gmem_attributes) + vm_mem_set_private(vm, EXITS_TEST_GPA, EXITS_TEST_SIZE); pthread_create(&vm_thread, NULL, (void *(*)(void *))run_vcpu_get_exit_reason, @@ -74,10 +75,26 @@ static void test_private_access_memslot_deleted(void) pthread_join(vm_thread, &thread_return); exit_reason = (u32)(u64)thread_return; - TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); - TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); - TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); - TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + /* + * If attributes are tracked per-gmem, deleting the memslot that points + * at the gmem instance effectively makes the memory shared, and so the + * read should trigger emulated MMIO. + * + * If attributes are tracked per-VM, deleting the memslot shouldn't + * affect the private attribute, and so KVM should generate a memory + * fault exit (emulated MMIO on private GPAs is disallowed). + */ + if (kvm_has_gmem_attributes) { + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MMIO); + TEST_ASSERT_EQ(vcpu->run->mmio.phys_addr, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->mmio.len, sizeof(u64)); + TEST_ASSERT_EQ(vcpu->run->mmio.is_write, false); + } else { + TEST_ASSERT_EQ(exit_reason, KVM_EXIT_MEMORY_FAULT); + TEST_ASSERT_EQ(vcpu->run->memory_fault.flags, KVM_MEMORY_EXIT_FLAG_PRIVATE); + TEST_ASSERT_EQ(vcpu->run->memory_fault.gpa, EXITS_TEST_GPA); + TEST_ASSERT_EQ(vcpu->run->memory_fault.size, EXITS_TEST_SIZE); + } kvm_vm_free(vm); } @@ -88,6 +105,13 @@ static void test_private_access_memslot_not_private(void) struct kvm_vcpu *vcpu; u32 exit_reason; + /* + * Accessing non-private memory as private with a software-protected VM + * isn't possible when doing in-place conversions. + */ + if (kvm_has_gmem_attributes) + return; + vm = vm_create_shape_with_one_vcpu(protected_vm_shape, &vcpu, guest_repeatedly_read); -- 2.54.0.563.g4f69b47b94-goog