KVM: MMU: fix SMAP virtualization

KVM may turn a user page to a kernel page when kernel writes a readonly
user page if CR0.WP = 1. This shadow page entry will be reused after
SMAP is enabled so that kernel is allowed to access this user page

Fix it by setting SMAP && !CR0.WP into shadow page's role and reset mmu
once CR4.SMAP is updated
Signed-off-by: Xiao Guangrong <guangrong.xiao@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

Documentation/virtual/kvm/mmu.txt

@@ -169,6 +169,10 @@ Shadow pages contain the following information:
     Contains the value of cr4.smep && !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.smap_andnot_wp:
+    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).
   gfn:
     Either the guest page table containing the translations shadowed by this
     page, or the base page frame for linear translations.  See role.direct.
@@ -344,10 +348,16 @@ on fault type:
 
 (user write faults generate a #PF)
 
-In the first case there is an additional complication if CR4.SMEP is
-enabled: since we've turned the page into a kernel page, the kernel may now
-execute it.  We handle this by also setting spte.nx.  If we get a user
-fetch or read fault, we'll change spte.u=1 and spte.nx=gpte.nx back.
+In the first case there are two additional complications:
+- if CR4.SMEP is enabled: since we've turned the page into a kernel page,
+  the kernel may now execute it.  We handle this by also setting spte.nx.
+  If we get a user fetch or read fault, we'll change spte.u=1 and
+  spte.nx=gpte.nx back.
+- if CR4.SMAP is disabled: since the page has been changed to a kernel
+  page, it can not be reused when CR4.SMAP is enabled. We set
+  CR4.SMAP && !CR0.WP into shadow page's role to avoid this case. Note,
+  here we do not care the case that CR4.SMAP is enabled since KVM will
+  directly inject #PF to guest due to failed permission check.
 
 To prevent an spte that was converted into a kernel page with cr0.wp=0
 from being written by the kernel after cr0.wp has changed to 1, we make

arch/x86/include/asm/kvm_host.h

@@ -207,6 +207,7 @@ union kvm_mmu_page_role {
 		unsigned nxe:1;
 		unsigned cr0_wp:1;
 		unsigned smep_andnot_wp:1;
+		unsigned smap_andnot_wp:1;
 	};
 };
 

arch/x86/kvm/mmu.c

@@ -3736,8 +3736,8 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-void update_permission_bitmask(struct kvm_vcpu *vcpu,
-		struct kvm_mmu *mmu, bool ept)
+static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+				      struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
@@ -3918,6 +3918,7 @@ static void init_kvm_tdp_mmu(struct kvm_vcpu *vcpu)
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 {
 	bool smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	bool smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	struct kvm_mmu *context = &vcpu->arch.mmu;
 
 	MMU_WARN_ON(VALID_PAGE(context->root_hpa));
@@ -3936,6 +3937,8 @@ void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu)
 	context->base_role.cr0_wp  = is_write_protection(vcpu);
 	context->base_role.smep_andnot_wp
 		= smep && !is_write_protection(vcpu);
+	context->base_role.smap_andnot_wp
+		= smap && !is_write_protection(vcpu);
 }
 EXPORT_SYMBOL_GPL(kvm_init_shadow_mmu);
 
@@ -4207,12 +4210,18 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 		       const u8 *new, int bytes)
 {
 	gfn_t gfn = gpa >> PAGE_SHIFT;
-	union kvm_mmu_page_role mask = { .word = 0 };
 	struct kvm_mmu_page *sp;
 	LIST_HEAD(invalid_list);
 	u64 entry, gentry, *spte;
 	int npte;
 	bool remote_flush, local_flush, zap_page;
+	union kvm_mmu_page_role mask = (union kvm_mmu_page_role) {
+		.cr0_wp = 1,
+		.cr4_pae = 1,
+		.nxe = 1,
+		.smep_andnot_wp = 1,
+		.smap_andnot_wp = 1,
+	};
 
 	/*
 	 * If we don't have indirect shadow pages, it means no page is
@@ -4238,7 +4247,6 @@ void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa,
 	++vcpu->kvm->stat.mmu_pte_write;
 	kvm_mmu_audit(vcpu, AUDIT_PRE_PTE_WRITE);
 
-	mask.cr0_wp = mask.cr4_pae = mask.nxe = mask.smep_andnot_wp = 1;
 	for_each_gfn_indirect_valid_sp(vcpu->kvm, sp, gfn) {
 		if (detect_write_misaligned(sp, gpa, bytes) ||
 		      detect_write_flooding(sp)) {

arch/x86/kvm/mmu.h

@@ -71,8 +71,6 @@ enum {
 int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, bool execonly);
-void update_permission_bitmask(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
-		bool ept);
 
 static inline unsigned int kvm_mmu_available_pages(struct kvm *kvm)
 {

arch/x86/kvm/x86.c

@@ -702,8 +702,9 @@ EXPORT_SYMBOL_GPL(kvm_set_xcr);
 int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
 	unsigned long old_cr4 = kvm_read_cr4(vcpu);
-	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE |
-				   X86_CR4_PAE | X86_CR4_SMEP;
+	unsigned long pdptr_bits = X86_CR4_PGE | X86_CR4_PSE | X86_CR4_PAE |
+				   X86_CR4_SMEP | X86_CR4_SMAP;
+
 	if (cr4 & CR4_RESERVED_BITS)
 		return 1;
 
@@ -744,9 +745,6 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	    (!(cr4 & X86_CR4_PCIDE) && (old_cr4 & X86_CR4_PCIDE)))
 		kvm_mmu_reset_context(vcpu);
 
-	if ((cr4 ^ old_cr4) & X86_CR4_SMAP)
-		update_permission_bitmask(vcpu, vcpu->arch.walk_mmu, false);
-
 	if ((cr4 ^ old_cr4) & X86_CR4_OSXSAVE)
 		kvm_update_cpuid(vcpu);