commit 47b0c2e4c220f2251fd8dcfbb44479819c715e15 upstream.
make_mmu_pages_available() must be called with mmu_lock held for write. However, if the TDP MMU is used, it will be called with mmu_lock held for read. This function does nothing unless shadow pages are used, so there is no race unless nested TDP is used. Since nested TDP uses shadow pages, old shadow pages may be zapped by this function even when the TDP MMU is enabled. Since shadow pages are never allocated by kvm_tdp_mmu_map(), a race condition can be avoided by not calling make_mmu_pages_available() if the TDP MMU is currently in use.
I encountered this when repeatedly starting and stopping nested VM. It can be artificially caused by allocating a large number of nested TDP SPTEs.
For example, the following BUG and general protection fault are caused in the host kernel.
pte_list_remove: 00000000cd54fc10 many->many ------------[ cut here ]------------ kernel BUG at arch/x86/kvm/mmu/mmu.c:963! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI RIP: 0010:pte_list_remove.cold+0x16/0x48 [kvm] Call Trace: <TASK> drop_spte+0xe0/0x180 [kvm] mmu_page_zap_pte+0x4f/0x140 [kvm] __kvm_mmu_prepare_zap_page+0x62/0x3e0 [kvm] kvm_mmu_zap_oldest_mmu_pages+0x7d/0xf0 [kvm] direct_page_fault+0x3cb/0x9b0 [kvm] kvm_tdp_page_fault+0x2c/0xa0 [kvm] kvm_mmu_page_fault+0x207/0x930 [kvm] npf_interception+0x47/0xb0 [kvm_amd] svm_invoke_exit_handler+0x13c/0x1a0 [kvm_amd] svm_handle_exit+0xfc/0x2c0 [kvm_amd] kvm_arch_vcpu_ioctl_run+0xa79/0x1780 [kvm] kvm_vcpu_ioctl+0x29b/0x6f0 [kvm] __x64_sys_ioctl+0x95/0xd0 do_syscall_64+0x5c/0x90
general protection fault, probably for non-canonical address 0xdead000000000122: 0000 [#1] PREEMPT SMP NOPTI RIP: 0010:kvm_mmu_commit_zap_page.part.0+0x4b/0xe0 [kvm] Call Trace: <TASK> kvm_mmu_zap_oldest_mmu_pages+0xae/0xf0 [kvm] direct_page_fault+0x3cb/0x9b0 [kvm] kvm_tdp_page_fault+0x2c/0xa0 [kvm] kvm_mmu_page_fault+0x207/0x930 [kvm] npf_interception+0x47/0xb0 [kvm_amd]
CVE: CVE-2022-45869 Fixes: a2855afc7ee8 ("KVM: x86/mmu: Allow parallel page faults for the TDP MMU") Signed-off-by: Kazuki Takiguchi takiguchi.kazuki171@gmail.com Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini pbonzini@redhat.com --- arch/x86/kvm/mmu/mmu.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index ba1749a770eb..4724289c8a7f 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -2357,6 +2357,7 @@ static bool __kvm_mmu_prepare_zap_page(struct kvm *kvm, { bool list_unstable;
+ lockdep_assert_held_write(&kvm->mmu_lock); trace_kvm_mmu_prepare_zap_page(sp); ++kvm->stat.mmu_shadow_zapped; *nr_zapped = mmu_zap_unsync_children(kvm, sp, invalid_list); @@ -4007,16 +4008,17 @@ static int direct_page_fault(struct kvm_vcpu *vcpu, gpa_t gpa, u32 error_code,
if (!is_noslot_pfn(pfn) && mmu_notifier_retry_hva(vcpu->kvm, mmu_seq, hva)) goto out_unlock; - r = make_mmu_pages_available(vcpu); - if (r) - goto out_unlock;
- if (is_tdp_mmu_fault) + if (is_tdp_mmu_fault) { r = kvm_tdp_mmu_map(vcpu, gpa, error_code, map_writable, max_level, pfn, prefault); - else + } else { + r = make_mmu_pages_available(vcpu); + if (r) + goto out_unlock; r = __direct_map(vcpu, gpa, error_code, map_writable, max_level, pfn, prefault, is_tdp); + }
out_unlock: if (is_tdp_mmu_fault)