KVM: x86: save/load state on SMM switch

The big ugly one.  This patch adds support for switching in and out of
system management mode, respectively upon receiving KVM_REQ_SMI and upon
executing a RSM instruction.  Both 32- and 64-bit formats are supported
for the SMM state save area.

Reviewed-by: Radim Krčmář <[email protected]>
Signed-off-by: Paolo Bonzini <[email protected]>

Author: bonzini

arch/x86/kvm/cpuid.h

@@ -70,6 +70,14 @@ static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_FSGSBASE));
 }
 
+static inline bool guest_cpuid_has_longmode(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0);
+	return best && (best->edx & bit(X86_FEATURE_LM));
+}
+
 static inline bool guest_cpuid_has_osvw(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;

arch/x86/kvm/emulate.c

@@ -2259,12 +2259,258 @@ static int em_lseg(struct x86_emulate_ctxt *ctxt)
 	return rc;
 }
 
+static int emulator_has_longmode(struct x86_emulate_ctxt *ctxt)
+{
+	u32 eax, ebx, ecx, edx;
+
+	eax = 0x80000001;
+	ecx = 0;
+	ctxt->ops->get_cpuid(ctxt, &eax, &ebx, &ecx, &edx);
+	return edx & bit(X86_FEATURE_LM);
+}
+
+#define GET_SMSTATE(type, smbase, offset)				  \
+	({								  \
+	 type __val;							  \
+	 int r = ctxt->ops->read_std(ctxt, smbase + offset, &__val,       \
+				     sizeof(__val), NULL);		  \
+	 if (r != X86EMUL_CONTINUE)					  \
+		 return X86EMUL_UNHANDLEABLE;				  \
+	 __val;								  \
+	})
+
+static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
+{
+	desc->g    = (flags >> 23) & 1;
+	desc->d    = (flags >> 22) & 1;
+	desc->l    = (flags >> 21) & 1;
+	desc->avl  = (flags >> 20) & 1;
+	desc->p    = (flags >> 15) & 1;
+	desc->dpl  = (flags >> 13) & 3;
+	desc->s    = (flags >> 12) & 1;
+	desc->type = (flags >>  8) & 15;
+}
+
+static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+
+	selector = GET_SMSTATE(u32, smbase, 0x7fa8 + n * 4);
+
+	if (n < 3)
+		offset = 0x7f84 + n * 12;
+	else
+		offset = 0x7f2c + (n - 3) * 12;
+
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smbase, offset));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, u64 smbase, int n)
+{
+	struct desc_struct desc;
+	int offset;
+	u16 selector;
+	u32 base3;
+
+	offset = 0x7e00 + n * 16;
+
+	selector =                GET_SMSTATE(u16, smbase, offset);
+	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smbase, offset + 2) << 8);
+	set_desc_limit(&desc,     GET_SMSTATE(u32, smbase, offset + 4));
+	set_desc_base(&desc,      GET_SMSTATE(u32, smbase, offset + 8));
+	base3 =                   GET_SMSTATE(u32, smbase, offset + 12);
+
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
+				     u64 cr0, u64 cr4)
+{
+	int bad;
+
+	/*
+	 * First enable PAE, long mode needs it before CR0.PG = 1 is set.
+	 * Then enable protected mode.	However, PCID cannot be enabled
+	 * if EFER.LMA=0, so set it separately.
+	 */
+	bad = ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PCIDE);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	bad = ctxt->ops->set_cr(ctxt, 0, cr0);
+	if (bad)
+		return X86EMUL_UNHANDLEABLE;
+
+	if (cr4 & X86_CR4_PCIDE) {
+		bad = ctxt->ops->set_cr(ctxt, 4, cr4);
+		if (bad)
+			return X86EMUL_UNHANDLEABLE;
+	}
+
+	return X86EMUL_CONTINUE;
+}
+
+static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u16 selector;
+	u32 val, cr0, cr4;
+	int i;
+
+	cr0 =                      GET_SMSTATE(u32, smbase, 0x7ffc);
+	ctxt->ops->set_cr(ctxt, 3, GET_SMSTATE(u32, smbase, 0x7ff8));
+	ctxt->eflags =             GET_SMSTATE(u32, smbase, 0x7ff4) | X86_EFLAGS_FIXED;
+	ctxt->_eip =               GET_SMSTATE(u32, smbase, 0x7ff0);
+
+	for (i = 0; i < 8; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u32, smbase, 0x7fd0 + i * 4);
+
+	val = GET_SMSTATE(u32, smbase, 0x7fcc);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7fc8);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc4);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f64));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f60));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f5c));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+
+	selector =                 GET_SMSTATE(u32, smbase, 0x7fc0);
+	set_desc_base(&desc,       GET_SMSTATE(u32, smbase, 0x7f80));
+	set_desc_limit(&desc,      GET_SMSTATE(u32, smbase, 0x7f7c));
+	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smbase, 0x7f78));
+	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f74);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f70);
+	ctxt->ops->set_gdt(ctxt, &dt);
+
+	dt.address =               GET_SMSTATE(u32, smbase, 0x7f58);
+	dt.size =                  GET_SMSTATE(u32, smbase, 0x7f54);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	for (i = 0; i < 6; i++) {
+		int r = rsm_load_seg_32(ctxt, smbase, i);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
+	cr4 = GET_SMSTATE(u32, smbase, 0x7f14);
+
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7ef8));
+
+	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
+static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt, u64 smbase)
+{
+	struct desc_struct desc;
+	struct desc_ptr dt;
+	u64 val, cr0, cr4;
+	u32 base3;
+	u16 selector;
+	int i;
+
+	for (i = 0; i < 16; i++)
+		*reg_write(ctxt, i) = GET_SMSTATE(u64, smbase, 0x7ff8 - i * 8);
+
+	ctxt->_eip   = GET_SMSTATE(u64, smbase, 0x7f78);
+	ctxt->eflags = GET_SMSTATE(u32, smbase, 0x7f70) | X86_EFLAGS_FIXED;
+
+	val = GET_SMSTATE(u32, smbase, 0x7f68);
+	ctxt->ops->set_dr(ctxt, 6, (val & DR6_VOLATILE) | DR6_FIXED_1);
+	val = GET_SMSTATE(u32, smbase, 0x7f60);
+	ctxt->ops->set_dr(ctxt, 7, (val & DR7_VOLATILE) | DR7_FIXED_1);
+
+	cr0 =                       GET_SMSTATE(u64, smbase, 0x7f58);
+	ctxt->ops->set_cr(ctxt, 3,  GET_SMSTATE(u64, smbase, 0x7f50));
+	cr4 =                       GET_SMSTATE(u64, smbase, 0x7f48);
+	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smbase, 0x7f00));
+	val =                       GET_SMSTATE(u64, smbase, 0x7ed0);
+	ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e90);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e92) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e94));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e98));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e9c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+
+	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e84);
+	dt.address =                GET_SMSTATE(u64, smbase, 0x7e88);
+	ctxt->ops->set_idt(ctxt, &dt);
+
+	selector =                  GET_SMSTATE(u32, smbase, 0x7e70);
+	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smbase, 0x7e72) << 8);
+	set_desc_limit(&desc,       GET_SMSTATE(u32, smbase, 0x7e74));
+	set_desc_base(&desc,        GET_SMSTATE(u32, smbase, 0x7e78));
+	base3 =                     GET_SMSTATE(u32, smbase, 0x7e7c);
+	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+
+	dt.size =                   GET_SMSTATE(u32, smbase, 0x7e64);
+	dt.address =                GET_SMSTATE(u64, smbase, 0x7e68);
+	ctxt->ops->set_gdt(ctxt, &dt);
+
+	for (i = 0; i < 6; i++) {
+		int r = rsm_load_seg_64(ctxt, smbase, i);
+		if (r != X86EMUL_CONTINUE)
+			return r;
+	}
+
+	return rsm_enter_protected_mode(ctxt, cr0, cr4);
+}
+
 static int em_rsm(struct x86_emulate_ctxt *ctxt)
 {
+	unsigned long cr0, cr4, efer;
+	u64 smbase;
+	int ret;
+
 	if ((ctxt->emul_flags & X86EMUL_SMM_MASK) == 0)
 		return emulate_ud(ctxt);
 
-	return X86EMUL_UNHANDLEABLE;
+	/*
+	 * Get back to real mode, to prepare a safe state in which to load
+	 * CR0/CR3/CR4/EFER.  Also this will ensure that addresses passed
+	 * to read_std/write_std are not virtual.
+	 *
+	 * CR4.PCIDE must be zero, because it is a 64-bit mode only feature.
+	 */
+	cr0 = ctxt->ops->get_cr(ctxt, 0);
+	if (cr0 & X86_CR0_PE)
+		ctxt->ops->set_cr(ctxt, 0, cr0 & ~(X86_CR0_PG | X86_CR0_PE));
+	cr4 = ctxt->ops->get_cr(ctxt, 4);
+	if (cr4 & X86_CR4_PAE)
+		ctxt->ops->set_cr(ctxt, 4, cr4 & ~X86_CR4_PAE);
+	efer = 0;
+	ctxt->ops->set_msr(ctxt, MSR_EFER, efer);
+
+	smbase = ctxt->ops->get_smbase(ctxt);
+	if (emulator_has_longmode(ctxt))
+		ret = rsm_load_state_64(ctxt, smbase + 0x8000);
+	else
+		ret = rsm_load_state_32(ctxt, smbase + 0x8000);
+
+	if (ret != X86EMUL_CONTINUE) {
+		/* FIXME: should triple fault */
+		return X86EMUL_UNHANDLEABLE;
+	}
+
+	if ((ctxt->emul_flags & X86EMUL_SMM_INSIDE_NMI_MASK) == 0)
+		ctxt->ops->set_nmi_mask(ctxt, false);
+
+	ctxt->emul_flags &= ~X86EMUL_SMM_INSIDE_NMI_MASK;
+	ctxt->emul_flags &= ~X86EMUL_SMM_MASK;
+	return X86EMUL_CONTINUE;
 }
 
 static void

arch/x86/kvm/trace.h

@@ -952,6 +952,28 @@ TRACE_EVENT(kvm_wait_lapic_expire,
 		  __entry->delta < 0 ? "early" : "late")
 );
 
+TRACE_EVENT(kvm_enter_smm,
+	TP_PROTO(unsigned int vcpu_id, u64 smbase, bool entering),
+	TP_ARGS(vcpu_id, smbase, entering),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	vcpu_id		)
+		__field(	u64,		smbase		)
+		__field(	bool,		entering	)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_id	= vcpu_id;
+		__entry->smbase		= smbase;
+		__entry->entering	= entering;
+	),
+
+	TP_printk("vcpu %u: %s SMM, smbase 0x%llx",
+		  __entry->vcpu_id,
+		  __entry->entering ? "entering" : "leaving",
+		  __entry->smbase)
+);
+
 #endif /* _TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH