From: Mingwei Zhang mizhang@google.com

commit 683412ccf61294d727ead4a73d97397396e69a6b upstream.

Flush the CPU caches when memory is reclaimed from an SEV guest (where reclaim also includes it being unmapped from KVM's memslots). Due to lack of coherency for SEV encrypted memory, failure to flush results in silent data corruption if userspace is malicious/broken and doesn't ensure SEV guest memory is properly pinned and unpinned.

Cache coherency is not enforced across the VM boundary in SEV (AMD APM vol.2 Section 15.34.7). Confidential cachelines, generated by confidential VM guests have to be explicitly flushed on the host side. If a memory page containing dirty confidential cachelines was released by VM and reallocated to another user, the cachelines may corrupt the new user at a later time.

KVM takes a shortcut by assuming all confidential memory remain pinned until the end of VM lifetime. Therefore, KVM does not flush cache at mmu_notifier invalidation events. Because of this incorrect assumption and the lack of cache flushing, malicous userspace can crash the host kernel: creating a malicious VM and continuously allocates/releases unpinned confidential memory pages when the VM is running.

Add cache flush operations to mmu_notifier operations to ensure that any physical memory leaving the guest VM get flushed. In particular, hook mmu_notifier_invalidate_range_start and mmu_notifier_release events and flush cache accordingly. The hook after releasing the mmu lock to avoid contention with other vCPUs.

Cc: stable@vger.kernel.org Suggested-by: Sean Christpherson seanjc@google.com Reported-by: Mingwei Zhang mizhang@google.com Signed-off-by: Mingwei Zhang mizhang@google.com Message-Id: 20220421031407.2516575-4-mizhang@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com [OP: adjusted KVM_X86_OP_OPTIONAL() -> KVM_X86_OP_NULL, applied kvm_arch_guest_memory_reclaimed() call in kvm_set_memslot()] Signed-off-by: Ovidiu Panait ovidiu.panait@windriver.com --- This fixes CVE-2022-0171.

arch/x86/include/asm/kvm-x86-ops.h | 1 + arch/x86/include/asm/kvm_host.h | 1 + arch/x86/kvm/svm/sev.c | 8 ++++++++ arch/x86/kvm/svm/svm.c | 1 + arch/x86/kvm/svm/svm.h | 2 ++ arch/x86/kvm/x86.c | 5 +++++ include/linux/kvm_host.h | 2 ++ virt/kvm/kvm_main.c | 27 ++++++++++++++++++++++++--- 8 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h index 9e50da3ed01a..23ea8a25cbbe 100644 --- a/arch/x86/include/asm/kvm-x86-ops.h +++ b/arch/x86/include/asm/kvm-x86-ops.h @@ -115,6 +115,7 @@ KVM_X86_OP(enable_smi_window) KVM_X86_OP_NULL(mem_enc_op) KVM_X86_OP_NULL(mem_enc_reg_region) KVM_X86_OP_NULL(mem_enc_unreg_region) +KVM_X86_OP_NULL(guest_memory_reclaimed) KVM_X86_OP(get_msr_feature) KVM_X86_OP(can_emulate_instruction) KVM_X86_OP(apic_init_signal_blocked) diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 74b5819120da..9e800d4d323c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -1476,6 +1476,7 @@ struct kvm_x86_ops { int (*mem_enc_reg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*mem_enc_unreg_region)(struct kvm *kvm, struct kvm_enc_region *argp); int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd); + void (*guest_memory_reclaimed)(struct kvm *kvm);

int (*get_msr_feature)(struct kvm_msr_entry *entry);

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 86f3096f042f..eeedcb3d40e8 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -2037,6 +2037,14 @@ static void sev_flush_guest_memory(struct vcpu_svm *svm, void *va, wbinvd_on_all_cpus(); }

+void sev_guest_memory_reclaimed(struct kvm *kvm) +{ + if (!sev_guest(kvm)) + return; + + wbinvd_on_all_cpus(); +} + void sev_free_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm; diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index 2947e3c965e3..49bb3db2761a 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -4678,6 +4678,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = { .mem_enc_op = svm_mem_enc_op, .mem_enc_reg_region = svm_register_enc_region, .mem_enc_unreg_region = svm_unregister_enc_region, + .guest_memory_reclaimed = sev_guest_memory_reclaimed,

.vm_copy_enc_context_from = svm_vm_copy_asid_from,

diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index cf2d8365aeb4..7004f356edf9 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -555,6 +555,8 @@ int svm_register_enc_region(struct kvm *kvm, int svm_unregister_enc_region(struct kvm *kvm, struct kvm_enc_region *range); int svm_vm_copy_asid_from(struct kvm *kvm, unsigned int source_fd); +void sev_guest_memory_reclaimed(struct kvm *kvm); + void pre_sev_run(struct vcpu_svm *svm, int cpu); void __init sev_set_cpu_caps(void); void __init sev_hardware_setup(void); diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 9109e5589b42..11e73d02fb3a 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -9557,6 +9557,11 @@ void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD); }

+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ + static_call_cond(kvm_x86_guest_memory_reclaimed)(kvm); +} + void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu) { if (!lapic_in_kernel(vcpu)) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 38b7e9ab48b8..725f8f13adb5 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -1912,6 +1912,8 @@ static inline long kvm_arch_vcpu_async_ioctl(struct file *filp, void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end);

+void kvm_arch_guest_memory_reclaimed(struct kvm *kvm); + #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu); #else diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 86fc429a0e43..3ae5f6a3eae4 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -162,6 +162,10 @@ __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, { }

+__weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) +{ +} + bool kvm_is_zone_device_pfn(kvm_pfn_t pfn) { /* @@ -353,6 +357,12 @@ void kvm_reload_remote_mmus(struct kvm *kvm) kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); }

+static void kvm_flush_shadow_all(struct kvm *kvm) +{ + kvm_arch_flush_shadow_all(kvm); + kvm_arch_guest_memory_reclaimed(kvm); +} + #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) @@ -469,12 +479,15 @@ typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start, unsigned long end);

+typedef void (*on_unlock_fn_t)(struct kvm *kvm); + struct kvm_hva_range { unsigned long start; unsigned long end; pte_t pte; hva_handler_t handler; on_lock_fn_t on_lock; + on_unlock_fn_t on_unlock; bool flush_on_ret; bool may_block; }; @@ -551,8 +564,11 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm);

- if (locked) + if (locked) { KVM_MMU_UNLOCK(kvm); + if (!IS_KVM_NULL_FN(range->on_unlock)) + range->on_unlock(kvm); + }

srcu_read_unlock(&kvm->srcu, idx);

@@ -573,6 +589,7 @@ static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, .pte = pte, .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; @@ -592,6 +609,7 @@ static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn .pte = __pte(0), .handler = handler, .on_lock = (void *)kvm_null_fn, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; @@ -660,6 +678,7 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, .pte = __pte(0), .handler = kvm_unmap_gfn_range, .on_lock = kvm_inc_notifier_count, + .on_unlock = kvm_arch_guest_memory_reclaimed, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; @@ -711,6 +730,7 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, .pte = __pte(0), .handler = (void *)kvm_null_fn, .on_lock = kvm_dec_notifier_count, + .on_unlock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; @@ -783,7 +803,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, int idx;

idx = srcu_read_lock(&kvm->srcu); - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); }

@@ -1188,7 +1208,7 @@ static void kvm_destroy_vm(struct kvm *kvm) WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); kvm->mn_active_invalidate_count = 0; #else - kvm_arch_flush_shadow_all(kvm); + kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); @@ -1588,6 +1608,7 @@ static int kvm_set_memslot(struct kvm *kvm, * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, slot); + kvm_arch_guest_memory_reclaimed(kvm);

/* Released in install_new_memslots. */ mutex_lock(&kvm->slots_arch_lock);