VMX: fix VMCS race on context-switch paths

When __context_switch() is being bypassed during original context
switch handling, the vCPU "owning" the VMCS partially loses control of
it: It will appear non-running to remote CPUs, and hence their attempt
to pause the owning vCPU will have no effect on it (as it already
looks to be paused). At the same time the "owning" CPU will re-enable
interrupts eventually (the lastest when entering the idle loop) and
hence becomes subject to IPIs from other CPUs requesting access to the
VMCS. As a result, when __context_switch() finally gets run, the CPU
may no longer have the VMCS loaded, and hence any accesses to it would
fail. Hence we may need to re-load the VMCS in vmx_ctxt_switch_from().

For consistency use the new function also in vmx_do_resume(), to
avoid leaving an open-coded incarnation of it around.

Reported-by: Kevin Mayer <Kevin.Mayer@gdata.de>
Reported-by: Anshul Makkar <anshul.makkar@citrix.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Sergey Dyasli <sergey.dyasli@citrix.com>
Tested-by: Sergey Dyasli <sergey.dyasli@citrix.com>

diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index 92c5867a7e821092cdd1fe7fb89b54ec838fe163..5306a48bd8b8c8ef4722335697b8f0e5c5bd8144 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -551,6 +551,20 @@ static void vmx_load_vmcs(struct vcpu *v)
     local_irq_restore(flags);
 }
 
+void vmx_vmcs_reload(struct vcpu *v)
+{
+    /*
+     * As we may be running with interrupts disabled, we can't acquire
+     * v->arch.hvm_vmx.vmcs_lock here. However, with interrupts disabled
+     * the VMCS can't be taken away from us anymore if we still own it.
+     */
+    ASSERT(v->is_running || !local_irq_is_enabled());
+    if ( v->arch.hvm_vmx.vmcs_pa == this_cpu(current_vmcs) )
+        return;
+
+    vmx_load_vmcs(v);
+}
+
 int vmx_cpu_up_prepare(unsigned int cpu)
 {
     /*
@@ -1677,10 +1691,7 @@ void vmx_do_resume(struct vcpu *v)
     bool_t debug_state;
 
     if ( v->arch.hvm_vmx.active_cpu == smp_processor_id() )
-    {
-        if ( v->arch.hvm_vmx.vmcs_pa != this_cpu(current_vmcs) )
-            vmx_load_vmcs(v);
-    }
+        vmx_vmcs_reload(v);
     else
     {
         /*

diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index 580895394443ca32b65702442886fd23f20b650a..074939edf23a499821e21f62a9a59f1ab8206862 100644 (file)
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -935,6 +935,18 @@ static void vmx_ctxt_switch_from(struct vcpu *v)
     if ( unlikely(!this_cpu(vmxon)) )
         return;
 
+    if ( !v->is_running )
+    {
+        /*
+         * When this vCPU isn't marked as running anymore, a remote pCPU's
+         * attempt to pause us (from vmx_vmcs_enter()) won't have a reason
+         * to spin in vcpu_sleep_sync(), and hence that pCPU might have taken
+         * away the VMCS from us. As we're running with interrupts disabled,
+         * we also can't call vmx_vmcs_enter().
+         */
+        vmx_vmcs_reload(v);
+    }
+
     vmx_fpu_leave(v);
     vmx_save_guest_msrs(v);
     vmx_restore_host_msrs();

diff --git a/xen/include/asm-x86/hvm/vmx/vmcs.h b/xen/include/asm-x86/hvm/vmx/vmcs.h
index c30aab6142cbe22b34639f5fdcdb6e75baf0bc1f..4ee01dab9b354cbc71818a554ad15893a35df4a4 100644 (file)
--- a/xen/include/asm-x86/hvm/vmx/vmcs.h
+++ b/xen/include/asm-x86/hvm/vmx/vmcs.h
@@ -174,6 +174,7 @@ void vmx_destroy_vmcs(struct vcpu *v);
 void vmx_vmcs_enter(struct vcpu *v);
 bool_t __must_check vmx_vmcs_try_enter(struct vcpu *v);
 void vmx_vmcs_exit(struct vcpu *v);
+void vmx_vmcs_reload(struct vcpu *v);
 
 #define CPU_BASED_VIRTUAL_INTR_PENDING        0x00000004
 #define CPU_BASED_USE_TSC_OFFSETING           0x00000008