Merge git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM fixes from Marcelo Tosatti:
 - Fix for guest triggerable BUG_ON (CVE-2014-0155)
 - CR4.SMAP support
 - Spurious WARN_ON() fix

* git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: x86: remove WARN_ON from get_kernel_ns()
  KVM: Rename variable smep to cr4_smep
  KVM: expose SMAP feature to guest
  KVM: Disable SMAP for guests in EPT realmode and EPT unpaging mode
  KVM: Add SMAP support when setting CR4
  KVM: Remove SMAP bit from CR4_RESERVED_BITS
  KVM: ioapic: try to recover if pending_eoi goes out of range
  KVM: ioapic: fix assignment of ioapic->rtc_status.pending_eoi (CVE-2014-0155)

arch/x86/include/asm/kvm_host.h

@@ -60,7 +60,7 @@
 			  | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE     \
 			  | X86_CR4_PGE | X86_CR4_PCE | X86_CR4_OSFXSR | X86_CR4_PCIDE \
 			  | X86_CR4_OSXSAVE | X86_CR4_SMEP | X86_CR4_FSGSBASE \
-			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE))
+			  | X86_CR4_OSXMMEXCPT | X86_CR4_VMXE | X86_CR4_SMAP))
 
 #define CR8_RESERVED_BITS (~(unsigned long)X86_CR8_TPR)
 

arch/x86/kvm/cpuid.c

@@ -308,7 +308,7 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 	const u32 kvm_supported_word9_x86_features =
 		F(FSGSBASE) | F(BMI1) | F(HLE) | F(AVX2) | F(SMEP) |
 		F(BMI2) | F(ERMS) | f_invpcid | F(RTM) | f_mpx | F(RDSEED) |
-		F(ADX);
+		F(ADX) | F(SMAP);
 
 	/* all calls to cpuid_count() should be made on the same cpu */
 	get_cpu();

arch/x86/kvm/cpuid.h

@@ -48,6 +48,14 @@ static inline bool guest_cpuid_has_smep(struct kvm_vcpu *vcpu)
 	return best && (best->ebx & bit(X86_FEATURE_SMEP));
 }
 
+static inline bool guest_cpuid_has_smap(struct kvm_vcpu *vcpu)
+{
+	struct kvm_cpuid_entry2 *best;
+
+	best = kvm_find_cpuid_entry(vcpu, 7, 0);
+	return best && (best->ebx & bit(X86_FEATURE_SMAP));
+}
+
 static inline bool guest_cpuid_has_fsgsbase(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;

arch/x86/kvm/mmu.c

@@ -3601,20 +3601,27 @@ static void reset_rsvds_bits_mask_ept(struct kvm_vcpu *vcpu,
 	}
 }
 
-static void update_permission_bitmask(struct kvm_vcpu *vcpu,
+void update_permission_bitmask(struct kvm_vcpu *vcpu,
 		struct kvm_mmu *mmu, bool ept)
 {
 	unsigned bit, byte, pfec;
 	u8 map;
-	bool fault, x, w, u, wf, uf, ff, smep;
+	bool fault, x, w, u, wf, uf, ff, smapf, cr4_smap, cr4_smep, smap = 0;
 
-	smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	cr4_smep = kvm_read_cr4_bits(vcpu, X86_CR4_SMEP);
+	cr4_smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
 	for (byte = 0; byte < ARRAY_SIZE(mmu->permissions); ++byte) {
 		pfec = byte << 1;
 		map = 0;
 		wf = pfec & PFERR_WRITE_MASK;
 		uf = pfec & PFERR_USER_MASK;
 		ff = pfec & PFERR_FETCH_MASK;
+		/*
+		 * PFERR_RSVD_MASK bit is set in PFEC if the access is not
+		 * subject to SMAP restrictions, and cleared otherwise. The
+		 * bit is only meaningful if the SMAP bit is set in CR4.
+		 */
+		smapf = !(pfec & PFERR_RSVD_MASK);
 		for (bit = 0; bit < 8; ++bit) {
 			x = bit & ACC_EXEC_MASK;
 			w = bit & ACC_WRITE_MASK;
@@ -3626,12 +3633,33 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				/* Allow supervisor writes if !cr0.wp */
 				w |= !is_write_protection(vcpu) && !uf;
 				/* Disallow supervisor fetches of user code if cr4.smep */
-				x &= !(smep && u && !uf);
+				x &= !(cr4_smep && u && !uf);
+
+				/*
+				 * SMAP:kernel-mode data accesses from user-mode
+				 * mappings should fault. A fault is considered
+				 * as a SMAP violation if all of the following
+				 * conditions are ture:
+				 *   - X86_CR4_SMAP is set in CR4
+				 *   - An user page is accessed
+				 *   - Page fault in kernel mode
+				 *   - if CPL = 3 or X86_EFLAGS_AC is clear
+				 *
+				 *   Here, we cover the first three conditions.
+				 *   The fourth is computed dynamically in
+				 *   permission_fault() and is in smapf.
+				 *
+				 *   Also, SMAP does not affect instruction
+				 *   fetches, add the !ff check here to make it
+				 *   clearer.
+				 */
+				smap = cr4_smap && u && !uf && !ff;
 			} else
 				/* Not really needed: no U/S accesses on ept  */
 				u = 1;
 
-			fault = (ff && !x) || (uf && !u) || (wf && !w);
+			fault = (ff && !x) || (uf && !u) || (wf && !w) ||
+				(smapf && smap);
 			map |= fault << bit;
 		}
 		mmu->permissions[byte] = map;

arch/x86/kvm/mmu.h

@@ -44,11 +44,17 @@
 #define PT_DIRECTORY_LEVEL 2
 #define PT_PAGE_TABLE_LEVEL 1
 
-#define PFERR_PRESENT_MASK (1U << 0)
-#define PFERR_WRITE_MASK (1U << 1)
-#define PFERR_USER_MASK (1U << 2)
-#define PFERR_RSVD_MASK (1U << 3)
-#define PFERR_FETCH_MASK (1U << 4)
+#define PFERR_PRESENT_BIT 0
+#define PFERR_WRITE_BIT 1
+#define PFERR_USER_BIT 2
+#define PFERR_RSVD_BIT 3
+#define PFERR_FETCH_BIT 4
+
+#define PFERR_PRESENT_MASK (1U << PFERR_PRESENT_BIT)
+#define PFERR_WRITE_MASK (1U << PFERR_WRITE_BIT)
+#define PFERR_USER_MASK (1U << PFERR_USER_BIT)
+#define PFERR_RSVD_MASK (1U << PFERR_RSVD_BIT)
+#define PFERR_FETCH_MASK (1U << PFERR_FETCH_BIT)
 
 int kvm_mmu_get_spte_hierarchy(struct kvm_vcpu *vcpu, u64 addr, u64 sptes[4]);
 void kvm_mmu_set_mmio_spte_mask(u64 mmio_mask);
@@ -73,6 +79,8 @@ int handle_mmio_page_fault_common(struct kvm_vcpu *vcpu, u64 addr, bool direct);
 void kvm_init_shadow_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context);
 void kvm_init_shadow_ept_mmu(struct kvm_vcpu *vcpu, struct kvm_mmu *context,
 		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)
 {
@@ -110,10 +118,30 @@ static inline bool is_write_protection(struct kvm_vcpu *vcpu)
  * Will a fault with a given page-fault error code (pfec) cause a permission
  * fault with the given access (in ACC_* format)?
  */
-static inline bool permission_fault(struct kvm_mmu *mmu, unsigned pte_access,
-				    unsigned pfec)
+static inline bool permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
+				    unsigned pte_access, unsigned pfec)
 {
-	return (mmu->permissions[pfec >> 1] >> pte_access) & 1;
+	int cpl = kvm_x86_ops->get_cpl(vcpu);
+	unsigned long rflags = kvm_x86_ops->get_rflags(vcpu);
+
+	/*
+	 * If CPL < 3, SMAP prevention are disabled if EFLAGS.AC = 1.
+	 *
+	 * If CPL = 3, SMAP applies to all supervisor-mode data accesses
+	 * (these are implicit supervisor accesses) regardless of the value
+	 * of EFLAGS.AC.
+	 *
+	 * This computes (cpl < 3) && (rflags & X86_EFLAGS_AC), leaving
+	 * the result in X86_EFLAGS_AC. We then insert it in place of
+	 * the PFERR_RSVD_MASK bit; this bit will always be zero in pfec,
+	 * but it will be one in index if SMAP checks are being overridden.
+	 * It is important to keep this branchless.
+	 */
+	unsigned long smap = (cpl - 3) & (rflags & X86_EFLAGS_AC);
+	int index = (pfec >> 1) +
+		    (smap >> (X86_EFLAGS_AC_BIT - PFERR_RSVD_BIT + 1));
+
+	return (mmu->permissions[index] >> pte_access) & 1;
 }
 
 void kvm_mmu_invalidate_zap_all_pages(struct kvm *kvm);

arch/x86/kvm/paging_tmpl.h

@@ -353,7 +353,7 @@ static int FNAME(walk_addr_generic)(struct guest_walker *walker,
 		walker->ptes[walker->level - 1] = pte;
 	} while (!is_last_gpte(mmu, walker->level, pte));
 
-	if (unlikely(permission_fault(mmu, pte_access, access))) {
+	if (unlikely(permission_fault(vcpu, mmu, pte_access, access))) {
 		errcode |= PFERR_PRESENT_MASK;
 		goto error;
 	}

arch/x86/kvm/vmx.c

@@ -3484,13 +3484,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 			hw_cr4 &= ~X86_CR4_PAE;
 			hw_cr4 |= X86_CR4_PSE;
 			/*
-			 * SMEP is disabled if CPU is in non-paging mode in
-			 * hardware. However KVM always uses paging mode to
+			 * SMEP/SMAP is disabled if CPU is in non-paging mode
+			 * in hardware. However KVM always uses paging mode to
 			 * emulate guest non-paging mode with TDP.
-			 * To emulate this behavior, SMEP needs to be manually
-			 * disabled when guest switches to non-paging mode.
+			 * To emulate this behavior, SMEP/SMAP needs to be
+			 * manually disabled when guest switches to non-paging
+			 * mode.
 			 */
-			hw_cr4 &= ~X86_CR4_SMEP;
+			hw_cr4 &= ~(X86_CR4_SMEP | X86_CR4_SMAP);
 		} else if (!(cr4 & X86_CR4_PAE)) {
 			hw_cr4 &= ~X86_CR4_PAE;
 		}

arch/x86/kvm/x86.c

@@ -652,6 +652,9 @@ int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	if (!guest_cpuid_has_smep(vcpu) && (cr4 & X86_CR4_SMEP))
 		return 1;
 
+	if (!guest_cpuid_has_smap(vcpu) && (cr4 & X86_CR4_SMAP))
+		return 1;
+
 	if (!guest_cpuid_has_fsgsbase(vcpu) && (cr4 & X86_CR4_FSGSBASE))
 		return 1;
 
@@ -680,6 +683,9 @@ 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);
 
@@ -1117,7 +1123,6 @@ static inline u64 get_kernel_ns(void)
 {
 	struct timespec ts;
 
-	WARN_ON(preemptible());
 	ktime_get_ts(&ts);
 	monotonic_to_bootbased(&ts);
 	return timespec_to_ns(&ts);
@@ -4164,7 +4169,8 @@ static int vcpu_mmio_gva_to_gpa(struct kvm_vcpu *vcpu, unsigned long gva,
 		| (write ? PFERR_WRITE_MASK : 0);
 
 	if (vcpu_match_mmio_gva(vcpu, gva)
-	    && !permission_fault(vcpu->arch.walk_mmu, vcpu->arch.access, access)) {
+	    && !permission_fault(vcpu, vcpu->arch.walk_mmu,
+				 vcpu->arch.access, access)) {
 		*gpa = vcpu->arch.mmio_gfn << PAGE_SHIFT |
 					(gva & (PAGE_SIZE - 1));
 		trace_vcpu_match_mmio(gva, *gpa, write, false);

virt/kvm/ioapic.c

@@ -97,6 +97,14 @@ static void rtc_irq_eoi_tracking_reset(struct kvm_ioapic *ioapic)
 	bitmap_zero(ioapic->rtc_status.dest_map, KVM_MAX_VCPUS);
 }
 
+static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic);
+
+static void rtc_status_pending_eoi_check_valid(struct kvm_ioapic *ioapic)
+{
+	if (WARN_ON(ioapic->rtc_status.pending_eoi < 0))
+		kvm_rtc_eoi_tracking_restore_all(ioapic);
+}
+
 static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 {
 	bool new_val, old_val;
@@ -120,9 +128,8 @@ static void __rtc_irq_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
 	} else {
 		__clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map);
 		ioapic->rtc_status.pending_eoi--;
+		rtc_status_pending_eoi_check_valid(ioapic);
 	}
-
-	WARN_ON(ioapic->rtc_status.pending_eoi < 0);
 }
 
 void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu)
@@ -149,10 +156,10 @@ static void kvm_rtc_eoi_tracking_restore_all(struct kvm_ioapic *ioapic)
 
 static void rtc_irq_eoi(struct kvm_ioapic *ioapic, struct kvm_vcpu *vcpu)
 {
-	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map))
+	if (test_and_clear_bit(vcpu->vcpu_id, ioapic->rtc_status.dest_map)) {
 		--ioapic->rtc_status.pending_eoi;
-
-	WARN_ON(ioapic->rtc_status.pending_eoi < 0);
+		rtc_status_pending_eoi_check_valid(ioapic);
+	}
 }
 
 static bool rtc_irq_check_coalesced(struct kvm_ioapic *ioapic)
@@ -353,10 +360,16 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
 		ioapic->irr &= ~(1 << irq);
 
 	if (irq == RTC_GSI && line_status) {
+		/*
+		 * pending_eoi cannot ever become negative (see
+		 * rtc_status_pending_eoi_check_valid) and the caller
+		 * ensures that it is only called if it is >= zero, namely
+		 * if rtc_irq_check_coalesced returns false).
+		 */
 		BUG_ON(ioapic->rtc_status.pending_eoi != 0);
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe,
 				ioapic->rtc_status.dest_map);
-		ioapic->rtc_status.pending_eoi = ret;
+		ioapic->rtc_status.pending_eoi = (ret < 0 ? 0 : ret);
 	} else
 		ret = kvm_irq_delivery_to_apic(ioapic->kvm, NULL, &irqe, NULL);