KVM: VMX: Fix ds/es corruption on i386 with preemption
Commit b2da15ac26a0c ("KVM: VMX: Optimize %ds, %es reload") broke i386
in the following scenario:
vcpu_load
...
vmx_save_host_state
vmx_vcpu_run
(ds.rpl, es.rpl cleared by hardware)
interrupt
push ds, es # pushes bad ds, es
schedule
vmx_vcpu_put
vmx_load_host_state
reload ds, es (with __USER_DS)
pop ds, es # of other thread's stack
iret
# other thread runs
interrupt
push ds, es
schedule # back in vcpu thread
pop ds, es # now with rpl=0
iret
...
vcpu_put
resume_userspace
iret # clears ds, es due to mismatched rpl
(instead of resume_userspace, we might return with SYSEXIT and then
take an exception; when the exception IRETs we end up with cleared
ds, es)
Fix by avoiding the optimization on i386 and reloading ds, es on the
lightweight exit path.
Reported-by: Chris Clayron <chris2553@googlemail.com>
Signed-off-by: Avi Kivity <avi@redhat.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index c39b607..c00f03d 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -1488,13 +1488,6 @@
loadsegment(ds, vmx->host_state.ds_sel);
loadsegment(es, vmx->host_state.es_sel);
}
-#else
- /*
- * The sysexit path does not restore ds/es, so we must set them to
- * a reasonable value ourselves.
- */
- loadsegment(ds, __USER_DS);
- loadsegment(es, __USER_DS);
#endif
reload_tss();
#ifdef CONFIG_X86_64
@@ -6370,6 +6363,19 @@
#endif
);
+#ifndef CONFIG_X86_64
+ /*
+ * The sysexit path does not restore ds/es, so we must set them to
+ * a reasonable value ourselves.
+ *
+ * We can't defer this to vmx_load_host_state() since that function
+ * may be executed in interrupt context, which saves and restore segments
+ * around it, nullifying its effect.
+ */
+ loadsegment(ds, __USER_DS);
+ loadsegment(es, __USER_DS);
+#endif
+
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_RFLAGS)
| (1 << VCPU_EXREG_CPL)