KVM: x86: add SMM to the MMU role, support SMRAM address space

This is now very simple to do.  The only interesting part is a simple
trick to find the right memslot in gfn_to_rmap, retrieving the address
space from the spte role word.  The same trick is used in the auditing
code.

The comment on top of union kvm_mmu_page_role has been stale forever,
so remove it.  Speaking of stale code, remove pad_for_nice_hex_output
too: it was splitting the "access" bitfield across two bytes and thus
had effectively turned into pad_for_ugly_hex_output.
Reviewed-by: Radim Krčmář <rkrcmar@redhat.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/mmu.txt

@@ -173,6 +173,12 @@ Shadow pages contain the following information:
     Contains the value of cr4.smap && !cr0.wp for which the page is valid
     (pages for which this is true are different from other pages; see the
     treatment of cr0.wp=0 below).
+  role.smm:
+    Is 1 if the page is valid in system management mode.  This field
+    determines which of the kvm_memslots array was used to build this
+    shadow page; it is also used to go back from a struct kvm_mmu_page
+    to a memslot, through the kvm_memslots_for_spte_role macro and
+    __gfn_to_memslot.
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.

arch/x86/include/asm/kvm_host.h

@@ -184,23 +184,12 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
-/*
- * kvm_mmu_page_role, below, is defined as:
- *
- *   bits 0:3 - total guest paging levels (2-4, or zero for real mode)
- *   bits 4:7 - page table level for this shadow (1-4)
- *   bits 8:9 - page table quadrant for 2-level guests
- *   bit   16 - direct mapping of virtual to physical mapping at gfn
- *              used for real mode and two-dimensional paging
- *   bits 17:19 - common access permissions for all ptes in this shadow page
- */
 union kvm_mmu_page_role {
 	unsigned word;
 	struct {
 		unsigned level:4;
 		unsigned cr4_pae:1;
 		unsigned quadrant:2;
-		unsigned pad_for_nice_hex_output:6;
 		unsigned direct:1;
 		unsigned access:3;
 		unsigned invalid:1;
@@ -208,6 +197,15 @@ union kvm_mmu_page_role {
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
 		unsigned smap_andnot_wp:1;
+		unsigned :8;
+
+		/*
+		 * This is left at the top of the word so that
+		 * kvm_memslots_for_spte_role can extract it with a
+		 * simple shift.  While there is room, give it a whole
+		 * byte so it is also faster to load it from memory.
+		 */
+		unsigned smm:8;
 	};
 };
 
@@ -1120,6 +1118,12 @@ enum {
 #define HF_SMM_MASK		(1 << 6)
 #define HF_SMM_INSIDE_NMI_MASK	(1 << 7)
 
+#define __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#define KVM_ADDRESS_SPACE_NUM 2
+
+#define kvm_arch_vcpu_memslots_id(vcpu) ((vcpu)->arch.hflags & HF_SMM_MASK ? 1 : 0)
+#define kvm_memslots_for_spte_role(kvm, role) __kvm_memslots(kvm, (role).smm)
+
 /*
  * Hardware virtualization extension instructions may fault if a
  * reboot turns off virtualization while processes are running.

arch/x86/kvm/mmu.c

@@ -806,13 +806,15 @@ static struct kvm_lpage_info *lpage_info_slot(gfn_t gfn,
 
 static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
 	gfn_t gfn;
 	int i;
 
 	gfn = sp->gfn;
-	slot = gfn_to_memslot(kvm, gfn);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
 	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->write_count += 1;
@@ -822,13 +824,15 @@ static void account_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 
 static void unaccount_shadowed(struct kvm *kvm, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 	struct kvm_lpage_info *linfo;
 	gfn_t gfn;
 	int i;
 
 	gfn = sp->gfn;
-	slot = gfn_to_memslot(kvm, gfn);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
 	for (i = PT_DIRECTORY_LEVEL; i <= PT_MAX_HUGEPAGE_LEVEL; ++i) {
 		linfo = lpage_info_slot(gfn, slot, i);
 		linfo->write_count -= 1;
@@ -1045,9 +1049,11 @@ static unsigned long *__gfn_to_rmap(gfn_t gfn, int level,
  */
 static unsigned long *gfn_to_rmap(struct kvm *kvm, gfn_t gfn, struct kvm_mmu_page *sp)
 {
+	struct kvm_memslots *slots;
 	struct kvm_memory_slot *slot;
 
-	slot = gfn_to_memslot(kvm, gfn);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
 	return __gfn_to_rmap(gfn, sp->role.level, slot);
 }
 
@@ -3924,6 +3930,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	context->base_role.word = 0;
+	context->base_role.smm = is_smm(vcpu);
 	context->page_fault = tdp_page_fault;
 	context->sync_page = nonpaging_sync_page;
 	context->invlpg = nonpaging_invlpg;
@@ -3985,6 +3992,7 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 		= smep && !is_write_protection(vcpu);
 	context->base_role.smap_andnot_wp
 		= smap && !is_write_protection(vcpu);
+	context->base_role.smm = is_smm(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -4268,6 +4276,7 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	mask.nxe = 1;
 	mask.smep_andnot_wp = 1;
 	mask.smap_andnot_wp = 1;
+	mask.smm = 1;
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is

arch/x86/kvm/mmu_audit.c

@@ -131,12 +131,16 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 	static DEFINE_RATELIMIT_STATE(ratelimit_state, 5 * HZ, 10);
 	unsigned long *rmapp;
 	struct kvm_mmu_page *rev_sp;
+	struct kvm_memslots *slots;
+	struct kvm_memory_slot *slot;
 	gfn_t gfn;
 
 	rev_sp = page_header(__pa(sptep));
 	gfn = kvm_mmu_page_get_gfn(rev_sp, sptep - rev_sp->spt);
 
-	if (!gfn_to_memslot(kvm, gfn)) {
+	slots = kvm_memslots_for_spte_role(kvm, rev_sp->role);
+	slot = __gfn_to_memslot(slots, gfn);
+	if (!slot) {
 		if (!__ratelimit(&ratelimit_state))
 			return;
 		audit_printk(kvm, "no memslot for gfn %llx\n", gfn);
@@ -146,7 +150,7 @@ static void inspect_spte_has_rmap(struct kvm *kvm, u64 *sptep)
 		return;
 	}
 
-	rmapp = gfn_to_rmap(kvm, gfn, rev_sp);
+	rmapp = __gfn_to_rmap(gfn, rev_sp->role.level, slot);
 	if (!*rmapp) {
 		if (!__ratelimit(&ratelimit_state))
 			return;
@@ -197,7 +201,7 @@ static void audit_write_protection(struct kvm *kvm, struct kvm_mmu_page *sp)
 	if (sp->role.direct || sp->unsync || sp->role.invalid)
 		return;
 
-	slots = kvm_memslots(kvm);
+	slots = kvm_memslots_for_spte_role(kvm, sp->role);
 	slot = __gfn_to_memslot(slots, sp->gfn);
 	rmapp = __gfn_to_rmap(sp->gfn, PT_PAGE_TABLE_LEVEL, slot);
 

arch/x86/kvm/x86.c

@@ -5490,6 +5490,8 @@ static void kvm_smm_changed(struct kvm_vcpu *vcpu)
 			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		}
 	}
+
+	kvm_mmu_reset_context(vcpu);
 }
 
 static void kvm_set_hflags(struct kvm_vcpu *vcpu, unsigned emul_flags)