KVM: x86: get CPL from SS.DPL
CS.RPL is not equal to the CPL in the few instructions between
setting CR0.PE and reloading CS. And CS.DPL is also not equal
to the CPL for conforming code segments.
However, SS.DPL *is* always equal to the CPL except for the weird
case of SYSRET on AMD processors, which sets SS.DPL=SS.RPL from the
value in the STAR MSR, but force CPL=3 (Intel instead forces
SS.DPL=SS.RPL=CPL=3).
So this patch:
- modifies SVM to update the CPL from SS.DPL rather than CS.RPL;
the above case with SYSRET is not broken further, and the way
to fix it would be to pass the CPL to userspace and back
- modifies VMX to always return the CPL from SS.DPL (except
forcing it to 0 if we are emulating real mode via vm86 mode;
in vm86 mode all DPLs have to be 3, but real mode does allow
privileged instructions). It also removes the CPL cache,
which becomes a duplicate of the SS access rights cache.
This fixes doing KVM_IOCTL_SET_SREGS exactly after setting
CR0.PE=1 but before CS has been reloaded.
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 6f7463f..a267108 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -414,7 +414,6 @@
struct kvm_vcpu vcpu;
unsigned long host_rsp;
u8 fail;
- u8 cpl;
bool nmi_known_unmasked;
u32 exit_intr_info;
u32 idt_vectoring_info;
@@ -3150,10 +3149,6 @@
fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]);
fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]);
fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]);
-
- /* CPL is always 0 when CPU enters protected mode */
- __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
- vmx->cpl = 0;
}
static void fix_rmode_seg(int seg, struct kvm_segment *save)
@@ -3555,22 +3550,14 @@
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (!is_protmode(vcpu))
+ if (unlikely(vmx->rmode.vm86_active))
return 0;
-
- if (!is_long_mode(vcpu)
- && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */
- return 3;
-
- if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) {
- __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
- vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3;
+ else {
+ int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS);
+ return AR_DPL(ar);
}
-
- return vmx->cpl;
}
-
static u32 vmx_segment_access_rights(struct kvm_segment *var)
{
u32 ar;
@@ -3598,8 +3585,6 @@
const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg];
vmx_segment_cache_clear(vmx);
- if (seg == VCPU_SREG_CS)
- __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail);
if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) {
vmx->rmode.segs[seg] = *var;
@@ -7471,7 +7456,6 @@
vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP)
| (1 << VCPU_EXREG_RFLAGS)
- | (1 << VCPU_EXREG_CPL)
| (1 << VCPU_EXREG_PDPTR)
| (1 << VCPU_EXREG_SEGMENTS)
| (1 << VCPU_EXREG_CR3));