The patch below does not apply to the 4.19-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to stable@vger.kernel.org.
To reproduce the conflict and resubmit, you may use the following commands:
git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-4.19.y git checkout FETCH_HEAD git cherry-pick -x e32b120071ea114efc0b4ddd439547750b85f618 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to 'stable@vger.kernel.org' --in-reply-to '16781189523792@kroah.com' --subject-prefix 'PATCH 4.19.y' HEAD^..
Possible dependencies:
e32b120071ea ("KVM: VMX: Do _all_ initialization before exposing /dev/kvm to userspace") 4f8396b96a9f ("KVM: x86: Move guts of kvm_arch_init() to standalone helper") da66de44b01e ("KVM: VMX: Don't bother disabling eVMCS static key on module exit") 2916b70fc342 ("KVM: VMX: Reset eVMCS controls in VP assist page during hardware disabling") 94bda2f4cd86 ("KVM: x86: Reject loading KVM if host.PAT[0] != WB") fdc298da8661 ("KVM: x86: Move kvm_ops_static_call_update() to x86.c") 5e17b2ee45b9 ("kvm: x86: Require const tsc for RT") 925088781eed ("KVM: x86: Fix pointer mistmatch warning when patching RET0 static calls") 5be2226f417d ("KVM: x86: allow defining return-0 static calls") abb6d479e226 ("KVM: x86: make several APIC virtualization callbacks optional") dd2319c61888 ("KVM: x86: warn on incorrectly NULL members of kvm_x86_ops") e4fc23bad813 ("KVM: x86: remove KVM_X86_OP_NULL and mark optional kvm_x86_ops") 8a2897853c53 ("KVM: x86: return 1 unconditionally for availability of KVM_CAP_VAPIC") db6e7adf8de9 ("KVM: SVM: Rename AVIC helpers to use "avic" prefix instead of "svm"") 4e71cad31c62 ("Merge remote-tracking branch 'kvm/master' into HEAD")
thanks,
greg k-h
------------------ original commit in Linus's tree ------------------
From e32b120071ea114efc0b4ddd439547750b85f618 Mon Sep 17 00:00:00 2001 From: Sean Christopherson seanjc@google.com Date: Wed, 30 Nov 2022 23:08:58 +0000 Subject: [PATCH] KVM: VMX: Do _all_ initialization before exposing /dev/kvm to userspace
Call kvm_init() only after _all_ setup is complete, as kvm_init() exposes /dev/kvm to userspace and thus allows userspace to create VMs (and call other ioctls). E.g. KVM will encounter a NULL pointer when attempting to add a vCPU to the per-CPU loaded_vmcss_on_cpu list if userspace is able to create a VM before vmx_init() configures said list.
BUG: kernel NULL pointer dereference, address: 0000000000000008 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] SMP CPU: 6 PID: 1143 Comm: stable Not tainted 6.0.0-rc7+ #988 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 RIP: 0010:vmx_vcpu_load_vmcs+0x68/0x230 [kvm_intel] <TASK> vmx_vcpu_load+0x16/0x60 [kvm_intel] kvm_arch_vcpu_load+0x32/0x1f0 [kvm] vcpu_load+0x2f/0x40 [kvm] kvm_arch_vcpu_create+0x231/0x310 [kvm] kvm_vm_ioctl+0x79f/0xe10 [kvm] ? handle_mm_fault+0xb1/0x220 __x64_sys_ioctl+0x80/0xb0 do_syscall_64+0x2b/0x50 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f5a6b05743b </TASK> Modules linked in: vhost_net vhost vhost_iotlb tap kvm_intel(+) kvm irqbypass
Cc: stable@vger.kernel.org Signed-off-by: Sean Christopherson seanjc@google.com Message-Id: 20221130230934.1014142-15-seanjc@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index 1e2eab6bda16..e0e3f2c1f681 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -8564,19 +8564,23 @@ static void vmx_cleanup_l1d_flush(void) l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; }
-static void vmx_exit(void) +static void __vmx_exit(void) { + allow_smaller_maxphyaddr = false; + #ifdef CONFIG_KEXEC_CORE RCU_INIT_POINTER(crash_vmclear_loaded_vmcss, NULL); synchronize_rcu(); #endif + vmx_cleanup_l1d_flush(); +}
+static void vmx_exit(void) +{ kvm_exit(); kvm_x86_vendor_exit();
- vmx_cleanup_l1d_flush(); - - allow_smaller_maxphyaddr = false; + __vmx_exit(); } module_exit(vmx_exit);
@@ -8594,11 +8598,6 @@ static int __init vmx_init(void) if (r) return r;
- r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), - __alignof__(struct vcpu_vmx), THIS_MODULE); - if (r) - goto err_kvm_init; - /* * Must be called after common x86 init so enable_ept is properly set * up. Hand the parameter mitigation value in which was stored in @@ -8632,11 +8631,20 @@ static int __init vmx_init(void) if (!enable_ept) allow_smaller_maxphyaddr = true;
+ /* + * Common KVM initialization _must_ come last, after this, /dev/kvm is + * exposed to userspace! + */ + r = kvm_init(&vmx_init_ops, sizeof(struct vcpu_vmx), + __alignof__(struct vcpu_vmx), THIS_MODULE); + if (r) + goto err_kvm_init; + return 0;
-err_l1d_flush: - vmx_exit(); err_kvm_init: + __vmx_exit(); +err_l1d_flush: kvm_x86_vendor_exit(); return r; }