KVM: x86 emulator: Allow PM/VM86 switch during task switch

Task switches can switch between Protected Mode and VM86. The current
mode must be updated during the task switch emulation so that the new
segment selectors are interpreted correctly.

In order to let privilege checks succeed, rflags needs to be updated in
the vcpu struct as this causes a CPL update.
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

arch/x86/include/asm/kvm_emulate.h

@@ -176,6 +176,7 @@ struct x86_emulate_ops {
 	void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
 	ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
 	int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+	void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val);
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);

arch/x86/kvm/emulate.c

@@ -2344,6 +2344,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 		return emulate_gp(ctxt, 0);
 	ctxt->_eip = tss->eip;
 	ctxt->eflags = tss->eflags | 2;
+
+	/* General purpose registers */
 	ctxt->regs[VCPU_REGS_RAX] = tss->eax;
 	ctxt->regs[VCPU_REGS_RCX] = tss->ecx;
 	ctxt->regs[VCPU_REGS_RDX] = tss->edx;
@@ -2365,6 +2367,24 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt,
 	set_segment_selector(ctxt, tss->fs, VCPU_SREG_FS);
 	set_segment_selector(ctxt, tss->gs, VCPU_SREG_GS);
 
+	/*
+	 * If we're switching between Protected Mode and VM86, we need to make
+	 * sure to update the mode before loading the segment descriptors so
+	 * that the selectors are interpreted correctly.
+	 *
+	 * Need to get rflags to the vcpu struct immediately because it
+	 * influences the CPL which is checked at least when loading the segment
+	 * descriptors and when pushing an error code to the new kernel stack.
+	 *
+	 * TODO Introduce a separate ctxt->ops->set_cpl callback
+	 */
+	if (ctxt->eflags & X86_EFLAGS_VM)
+		ctxt->mode = X86EMUL_MODE_VM86;
+	else
+		ctxt->mode = X86EMUL_MODE_PROT32;
+
+	ctxt->ops->set_rflags(ctxt, ctxt->eflags);
+
 	/*
 	 * Now load segment descriptors. If fault happenes at this stage
 	 * it is handled in a context of new task

arch/x86/kvm/svm.c

@@ -1354,7 +1354,11 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu)
 
 static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
 {
+	unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags;
+
 	to_svm(vcpu)->vmcb->save.rflags = rflags;
+	if ((old_rflags ^ rflags) & X86_EFLAGS_VM)
+		svm_update_cpl(vcpu);
 }
 
 static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)

arch/x86/kvm/x86.c

@@ -4129,6 +4129,11 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val)
 	return res;
 }
 
+static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val)
+{
+	kvm_set_rflags(emul_to_vcpu(ctxt), val);
+}
+
 static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt)
 {
 	return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt));
@@ -4310,6 +4315,7 @@ static struct x86_emulate_ops emulate_ops = {
 	.set_idt	     = emulator_set_idt,
 	.get_cr              = emulator_get_cr,
 	.set_cr              = emulator_set_cr,
+	.set_rflags          = emulator_set_rflags,
 	.cpl                 = emulator_get_cpl,
 	.get_dr              = emulator_get_dr,
 	.set_dr              = emulator_set_dr,