Merge tag 'kvm-arm-for-3.18' of git://git.kernel.org/pub/scm/linux/kernel/git/kvmarm/kvmarm into kvm-next

Changes for KVM for arm/arm64 for 3.18

This includes a bunch of changes:
 - Support read-only memory slots on arm/arm64
 - Various changes to fix Sparse warnings
 - Correctly detect write vs. read Stage-2 faults
 - Various VGIC cleanups and fixes
 - Dynamic VGIC data strcuture sizing
 - Fix SGI set_clear_pend offset bug
 - Fix VTTBR_BADDR Mask
 - Correctly report the FSC on Stage-2 faults

Conflicts:
	virt/kvm/eventfd.c
	[duplicate, different patch where the kvm-arm version broke x86.
	 The kvm tree instead has the right one]

15 files changed, 64 insertions, 63 deletions

diff --git a/arch/arm/include/asm/kvm_emulate.h b/arch/arm/include/asm/kvm_emulate.h
index 69b746955fca..b9db269c6e61 100644
--- a/arch/arm/include/asm/kvm_emulate.h
+++ b/arch/arm/include/asm/kvm_emulate.h
@@ -149,6 +149,11 @@ static inline bool kvm_vcpu_trap_is_iabt(struct kvm_vcpu *vcpu)
 
 static inline u8 kvm_vcpu_trap_get_fault(struct kvm_vcpu *vcpu)
 {
+	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(struct kvm_vcpu *vcpu)
+{
 	return kvm_vcpu_get_hsr(vcpu) & HSR_FSC_TYPE;
 }
 
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 155497c2b4da..53036e21756b 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 #include <kvm/arm_vgic.h>
 
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 void kvm_reset_coprocs(struct kvm_vcpu *vcpu);
 
diff --git a/arch/arm/include/asm/kvm_mmu.h b/arch/arm/include/asm/kvm_mmu.h
index 5cc0b0f5f72f..3f688b458143 100644
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -78,17 +78,6 @@ static inline void kvm_set_pte(pte_t *pte, pte_t new_pte)
 	flush_pmd_entry(pte);
 }
 
-static inline bool kvm_is_write_fault(unsigned long hsr)
-{
-	unsigned long hsr_ec = hsr >> HSR_EC_SHIFT;
-	if (hsr_ec == HSR_EC_IABT)
-		return false;
-	else if ((hsr & HSR_ISV) && !(hsr & HSR_WNR))
-		return false;
-	else
-		return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd)
 {
 	clean_dcache_area(pgd, PTRS_PER_S2_PGD * sizeof(pgd_t));
diff --git a/arch/arm/include/uapi/asm/kvm.h b/arch/arm/include/uapi/asm/kvm.h
index e6ebdd3471e5..09ee408c1a67 100644
--- a/arch/arm/include/uapi/asm/kvm.h
+++ b/arch/arm/include/uapi/asm/kvm.h
@@ -25,6 +25,7 @@
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -173,6 +174,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 005a7b5fd0aa..779605122f32 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -82,7 +82,7 @@ struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 /**
  * kvm_arm_get_running_vcpus - get the per-CPU array of currently running vcpus.
  */
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void)
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void)
 {
 	return &kvm_arm_running_vcpu;
 }
@@ -161,6 +161,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 			kvm->vcpus[i] = NULL;
 		}
 	}
+
+	kvm_vgic_destroy(kvm);
 }
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
@@ -177,6 +179,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_ONE_REG:
 	case KVM_CAP_ARM_PSCI:
 	case KVM_CAP_ARM_PSCI_0_2:
+	case KVM_CAP_READONLY_MEM:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -242,6 +245,7 @@ void kvm_arch_vcpu_free(struct kvm_vcpu *vcpu)
 {
 	kvm_mmu_free_memory_caches(vcpu);
 	kvm_timer_vcpu_terminate(vcpu);
+	kvm_vgic_vcpu_destroy(vcpu);
 	kmem_cache_free(kvm_vcpu_cache, vcpu);
 }
 
@@ -257,16 +261,9 @@ int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu)
 
 int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 {
-	int ret;
-
 	/* Force users to call KVM_ARM_VCPU_INIT */
 	vcpu->arch.target = -1;
 
-	/* Set up VGIC */
-	ret = kvm_vgic_vcpu_init(vcpu);
-	if (ret)
-		return ret;
-
 	/* Set up the timer */
 	kvm_timer_vcpu_init(vcpu);
 
@@ -413,9 +410,9 @@ static void update_vttbr(struct kvm *kvm)
 
 	/* update vttbr to be used with the new vmid */
 	pgd_phys = virt_to_phys(kvm->arch.pgd);
+	BUG_ON(pgd_phys & ~VTTBR_BADDR_MASK);
 	vmid = ((u64)(kvm->arch.vmid) << VTTBR_VMID_SHIFT) & VTTBR_VMID_MASK;
-	kvm->arch.vttbr = pgd_phys & VTTBR_BADDR_MASK;
-	kvm->arch.vttbr |= vmid;
+	kvm->arch.vttbr = pgd_phys | vmid;
 
 	spin_unlock(&kvm_vmid_lock);
 }
diff --git a/arch/arm/kvm/coproc.c b/arch/arm/kvm/coproc.c
index 37a0fe1bb9bb..7928dbdf2102 100644
--- a/arch/arm/kvm/coproc.c
+++ b/arch/arm/kvm/coproc.c
@@ -791,7 +791,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
         level = (val >> 1);
diff --git a/arch/arm/kvm/guest.c b/arch/arm/kvm/guest.c
index 813e49258690..cc0b78769bd8 100644
--- a/arch/arm/kvm/guest.c
+++ b/arch/arm/kvm/guest.c
@@ -163,7 +163,7 @@ static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
 	if (ret != 0)
-		return ret;
+		return -EFAULT;
 
 	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
 }
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 16e7994bf347..eea03069161b 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -746,22 +746,29 @@ static bool transparent_hugepage_adjust(pfn_t *pfnp, phys_addr_t *ipap)
 	return false;
 }
 
+static bool kvm_is_write_fault(struct kvm_vcpu *vcpu)
+{
+	if (kvm_vcpu_trap_is_iabt(vcpu))
+		return false;
+
+	return kvm_vcpu_dabt_iswrite(vcpu);
+}
+
 static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
-			  struct kvm_memory_slot *memslot,
+			  struct kvm_memory_slot *memslot, unsigned long hva,
 			  unsigned long fault_status)
 {
 	int ret;
 	bool write_fault, writable, hugetlb = false, force_pte = false;
 	unsigned long mmu_seq;
 	gfn_t gfn = fault_ipa >> PAGE_SHIFT;
-	unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
 	struct kvm *kvm = vcpu->kvm;
 	struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
 	struct vm_area_struct *vma;
 	pfn_t pfn;
 	pgprot_t mem_type = PAGE_S2;
 
-	write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
+	write_fault = kvm_is_write_fault(vcpu);
 	if (fault_status == FSC_PERM && !write_fault) {
 		kvm_err("Unexpected L2 read permission error\n");
 		return -EFAULT;
@@ -863,7 +870,8 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	unsigned long fault_status;
 	phys_addr_t fault_ipa;
 	struct kvm_memory_slot *memslot;
-	bool is_iabt;
+	unsigned long hva;
+	bool is_iabt, write_fault, writable;
 	gfn_t gfn;
 	int ret, idx;
 
@@ -874,17 +882,22 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			      kvm_vcpu_get_hfar(vcpu), fault_ipa);
 
 	/* Check the stage-2 fault is trans. fault or write fault */
-	fault_status = kvm_vcpu_trap_get_fault(vcpu);
+	fault_status = kvm_vcpu_trap_get_fault_type(vcpu);
 	if (fault_status != FSC_FAULT && fault_status != FSC_PERM) {
-		kvm_err("Unsupported fault status: EC=%#x DFCS=%#lx\n",
-			kvm_vcpu_trap_get_class(vcpu), fault_status);
+		kvm_err("Unsupported FSC: EC=%#x xFSC=%#lx ESR_EL2=%#lx\n",
+			kvm_vcpu_trap_get_class(vcpu),
+			(unsigned long)kvm_vcpu_trap_get_fault(vcpu),
+			(unsigned long)kvm_vcpu_get_hsr(vcpu));
 		return -EFAULT;
 	}
 
 	idx = srcu_read_lock(&vcpu->kvm->srcu);
 
 	gfn = fault_ipa >> PAGE_SHIFT;
-	if (!kvm_is_visible_gfn(vcpu->kvm, gfn)) {
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+	write_fault = kvm_is_write_fault(vcpu);
+	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
 		if (is_iabt) {
 			/* Prefetch Abort on I/O address */
 			kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
@@ -892,13 +905,6 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 			goto out_unlock;
 		}
 
-		if (fault_status != FSC_FAULT) {
-			kvm_err("Unsupported fault status on io memory: %#lx\n",
-				fault_status);
-			ret = -EFAULT;
-			goto out_unlock;
-		}
-
 		/*
 		 * The IPA is reported as [MAX:12], so we need to
 		 * complement it with the bottom 12 bits from the
@@ -910,9 +916,7 @@ int kvm_handle_guest_abort(struct kvm_vcpu *vcpu, struct kvm_run *run)
 		goto out_unlock;
 	}
 
-	memslot = gfn_to_memslot(vcpu->kvm, gfn);
-
-	ret = user_mem_abort(vcpu, fault_ipa, memslot, fault_status);
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
 	if (ret == 0)
 		ret = 1;
 out_unlock:
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index cc83520459ed..7fd3e27e3ccc 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -122,6 +122,17 @@
 #define VTCR_EL2_T0SZ_MASK	0x3f
 #define VTCR_EL2_T0SZ_40B	24
 
+/*
+ * We configure the Stage-2 page tables to always restrict the IPA space to be
+ * 40 bits wide (T0SZ = 24).  Systems with a PARange smaller than 40 bits are
+ * not known to exist and will break with this configuration.
+ *
+ * Note that when using 4K pages, we concatenate two first level page tables
+ * together.
+ *
+ * The magic numbers used for VTTBR_X in this patch can be found in Tables
+ * D4-23 and D4-25 in ARM DDI 0487A.b.
+ */
 #ifdef CONFIG_ARM64_64K_PAGES
 /*
  * Stage2 translation configuration:
@@ -149,7 +160,7 @@
 #endif
 
 #define VTTBR_BADDR_SHIFT (VTTBR_X - 1)
-#define VTTBR_BADDR_MASK  (((1LLU << (40 - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
+#define VTTBR_BADDR_MASK  (((1LLU << (PHYS_MASK_SHIFT - VTTBR_X)) - 1) << VTTBR_BADDR_SHIFT)
 #define VTTBR_VMID_SHIFT  (48LLU)
 #define VTTBR_VMID_MASK	  (0xffLLU << VTTBR_VMID_SHIFT)
 
diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h
index fdc3e21abd8d..5674a55b5518 100644
--- a/arch/arm64/include/asm/kvm_emulate.h
+++ b/arch/arm64/include/asm/kvm_emulate.h
@@ -174,6 +174,11 @@ static inline bool kvm_vcpu_trap_is_iabt(const struct kvm_vcpu *vcpu)
 
 static inline u8 kvm_vcpu_trap_get_fault(const struct kvm_vcpu *vcpu)
 {
+	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC;
+}
+
+static inline u8 kvm_vcpu_trap_get_fault_type(const struct kvm_vcpu *vcpu)
+{
 	return kvm_vcpu_get_hsr(vcpu) & ESR_EL2_FSC_TYPE;
 }
 
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 992d9da88119..2012c4ba8d67 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -43,7 +43,7 @@
 
 #define KVM_VCPU_MAX_FEATURES 3
 
-int kvm_target_cpu(void);
+int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
 int kvm_arch_dev_ioctl_check_extension(long ext);
 
@@ -197,7 +197,7 @@ static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
 }
 
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
-struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
+struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 u64 kvm_call_hyp(void *hypfn, ...);
 
diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h
index 8e138c7c53ac..a030d163840b 100644
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -59,10 +59,9 @@
 #define KERN_TO_HYP(kva)	((unsigned long)kva - PAGE_OFFSET + HYP_PAGE_OFFSET)
 
 /*
- * Align KVM with the kernel's view of physical memory. Should be
- * 40bit IPA, with PGD being 8kB aligned in the 4KB page configuration.
+ * We currently only support a 40bit IPA.
  */
-#define KVM_PHYS_SHIFT	PHYS_MASK_SHIFT
+#define KVM_PHYS_SHIFT	(40)
 #define KVM_PHYS_SIZE	(1UL << KVM_PHYS_SHIFT)
 #define KVM_PHYS_MASK	(KVM_PHYS_SIZE - 1UL)
 
@@ -93,19 +92,6 @@ void kvm_clear_hyp_idmap(void);
 #define	kvm_set_pte(ptep, pte)		set_pte(ptep, pte)
 #define	kvm_set_pmd(pmdp, pmd)		set_pmd(pmdp, pmd)
 
-static inline bool kvm_is_write_fault(unsigned long esr)
-{
-	unsigned long esr_ec = esr >> ESR_EL2_EC_SHIFT;
-
-	if (esr_ec == ESR_EL2_EC_IABT)
-		return false;
-
-	if ((esr & ESR_EL2_ISV) && !(esr & ESR_EL2_WNR))
-		return false;
-
-	return true;
-}
-
 static inline void kvm_clean_pgd(pgd_t *pgd) {}
 static inline void kvm_clean_pmd_entry(pmd_t *pmd) {}
 static inline void kvm_clean_pte(pte_t *pte) {}
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index e633ff8cdec8..8e38878c87c6 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -37,6 +37,7 @@
 
 #define __KVM_HAVE_GUEST_DEBUG
 #define __KVM_HAVE_IRQ_LINE
+#define __KVM_HAVE_READONLY_MEM
 
 #define KVM_REG_SIZE(id)						\
 	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
@@ -159,6 +160,7 @@ struct kvm_arch_memory_slot {
 #define   KVM_DEV_ARM_VGIC_CPUID_MASK	(0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT)
 #define   KVM_DEV_ARM_VGIC_OFFSET_SHIFT	0
 #define   KVM_DEV_ARM_VGIC_OFFSET_MASK	(0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT)
+#define KVM_DEV_ARM_VGIC_GRP_NR_IRQS	3
 
 /* KVM_IRQ_LINE irq field index values */
 #define KVM_ARM_IRQ_TYPE_SHIFT		24
diff --git a/arch/arm64/kvm/guest.c b/arch/arm64/kvm/guest.c
index 8d1ec2887a26..76794692c20b 100644
--- a/arch/arm64/kvm/guest.c
+++ b/arch/arm64/kvm/guest.c
@@ -174,7 +174,7 @@ static int set_timer_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg)
 
 	ret = copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id));
 	if (ret != 0)
-		return ret;
+		return -EFAULT;
 
 	return kvm_arm_timer_set_reg(vcpu, reg->id, val);
 }
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index 5805e7c4a4dd..4cc3b719208e 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -1218,7 +1218,7 @@ static bool is_valid_cache(u32 val)
 	u32 level, ctype;
 
 	if (val >= CSSELR_MAX)
-		return -ENOENT;
+		return false;
 
 	/* Bottom bit is Instruction or Data bit.  Next 3 bits are level. */
 	level = (val >> 1);