From: Chao Gao <chao.gao@xxxxxxxxx>
At init time, KVM does compatibility checks to ensure that all online
CPUs support hardware virtualization and a common set of features. But
KVM uses hotplugged CPUs without such compatibility checks. On Intel
CPUs, this leads to #GP if the hotplugged CPU doesn't support VMX or
vmentry failure if the hotplugged CPU doesn't meet minimal feature
requirements.
Do compatibility checks when onlining a CPU and abort the online process
if the hotplugged CPU is incompatible with online CPUs.
CPU hotplug is disabled during hardware_enable_all() to prevent the corner
case as shown below. A hotplugged CPU marks itself online in
cpu_online_mask (1) and enables interrupt (2) before invoking callbacks
registered in ONLINE section (3). So, if hardware_enable_all() is invoked
on another CPU right after (2), then on_each_cpu() in hardware_enable_all()
invokes hardware_enable_nolock() on the hotplugged CPU before
kvm_online_cpu() is called. This makes the CPU escape from compatibility
checks, which is risky.
start_secondary { ...
set_cpu_online(smp_processor_id(), true); <- 1
...
local_irq_enable(); <- 2
...
cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); <- 3
}
Keep compatibility checks at KVM init time. It can help to find
incompatibility issues earlier and refuse to load arch KVM module
(e.g., kvm-intel).
Loosen the WARN_ON in kvm_arch_check_processor_compat so that it
can be invoked from KVM's CPU hotplug callback (i.e., kvm_online_cpu).
Other arch doesn't depends on prohibiting of preemption because powerpc
has "strcmp(cur_cpu_spec->cpu_name, "model name")" and other arch has
"return 0". Only x86 kvm_arch_check_processor_compat() has issue.
Opportunistically, add a pr_err() for setup_vmcs_config() path in
vmx_check_processor_compatibility() so that each possible error path has
its own error message. Convert printk(KERN_ERR ... to pr_err to please
checkpatch.pl
Signed-off-by: Chao Gao <chao.gao@xxxxxxxxx>
Reviewed-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20220216031528.92558-7-chao.gao@xxxxxxxxx
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
Reviewed-by: Yuan Yao <yuan.yao@xxxxxxxxx>
---
arch/x86/kvm/vmx/vmx.c | 10 ++++++----
arch/x86/kvm/x86.c | 11 +++++++++--
virt/kvm/kvm_main.c | 18 +++++++++++++++++-
3 files changed, 32 insertions(+), 7 deletions(-)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 3cf7f18a4115..2a1ab6495299 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -7421,20 +7421,22 @@ static int vmx_check_processor_compatibility(void)
{
struct vmcs_config vmcs_conf;
struct vmx_capability vmx_cap;
+ int cpu = smp_processor_id();
if (!this_cpu_has(X86_FEATURE_MSR_IA32_FEAT_CTL) ||
!this_cpu_has(X86_FEATURE_VMX)) {
- pr_err("kvm: VMX is disabled on CPU %d\n", smp_processor_id());
+ pr_err("kvm: VMX is disabled on CPU %d\n", cpu);
return -EIO;
}
- if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0)
+ if (setup_vmcs_config(&vmcs_conf, &vmx_cap) < 0) {
+ pr_err("kvm: failed to setup vmcs config on CPU %d\n", cpu);
return -EIO;
+ }
if (nested)
nested_vmx_setup_ctls_msrs(&vmcs_conf.nested, vmx_cap.ept);
if (memcmp(&vmcs_config, &vmcs_conf, sizeof(struct vmcs_config)) != 0) {
- printk(KERN_ERR "kvm: CPU %d feature inconsistency!\n",
- smp_processor_id());
+ pr_err("kvm: CPU %d feature inconsistency!\n", cpu);
return -EIO;
}
return 0;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index f6f014e78ab9..0ab8db07fa0e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12000,9 +12000,16 @@ void kvm_arch_hardware_unsetup(void)
int kvm_arch_check_processor_compat(void)
{
- struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+ int cpu = smp_processor_id();
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
- WARN_ON(!irqs_disabled());
+ /*
+ * Compatibility checks are done when loading KVM or in KVM's CPU
+ * hotplug callback. It ensures all online CPUs are compatible to run
+ * vCPUs. For other cases, compatibility checks are unnecessary or
+ * even problematic. Try to detect improper usages here.
+ */
+ WARN_ON(!irqs_disabled() && cpu_active(cpu));
if (__cr4_reserved_bits(cpu_has, c) !=
__cr4_reserved_bits(cpu_has, &boot_cpu_data))
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index db1303e2abc9..0ac00c711384 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -5013,7 +5013,11 @@ static void hardware_enable_nolock(void *caller_name)
static int kvm_online_cpu(unsigned int cpu)
{
- int ret = 0;
+ int ret;
+
+ ret = kvm_arch_check_processor_compat();
+ if (ret)
+ return ret;
raw_spin_lock(&kvm_count_lock);
/*
@@ -5073,6 +5077,17 @@ static int hardware_enable_all(void)
{
int r = 0;
+ /*
+ * During onlining a CPU, cpu_online_mask is set before kvm_online_cpu()
+ * is called. on_each_cpu() between them includes the CPU. As a result,
+ * hardware_enable_nolock() may get invoked before kvm_online_cpu().
+ * This would enable hardware virtualization on that cpu without
+ * compatibility checks, which can potentially crash system or break
+ * running VMs.
+ *
+ * Disable CPU hotplug to prevent this case from happening.
+ */
+ cpus_read_lock();
raw_spin_lock(&kvm_count_lock);
kvm_usage_count++;
@@ -5087,6 +5102,7 @@ static int hardware_enable_all(void)
}
raw_spin_unlock(&kvm_count_lock);
+ cpus_read_unlock();
return r;
}
--
2.25.1
