Merge tag 'kvm-s390-next-4.5-2' of...

Merge tag 'kvm-s390-next-4.5-2' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390 features and fixes for 4.5 (kvm/next)

Some small cleanups
- use assignment instead of memcpy
- use %pK for kernel pointers

Changes regarding guest memory size
- Fix an off-by-one error in our guest memory interface (we might
use unnecessarily big page tables, e.g. 3 levels for a 2GB guest
instead of 2 levels)
- We now ask the machine about the max. supported guest address
  and limit accordingly.

Documentation/virtual/kvm/devices/vm.txt

@@ -37,7 +37,8 @@ Returns: -EFAULT if the given address is not accessible
 Allows userspace to query the actual limit and set a new limit for
 the maximum guest memory size. The limit will be rounded up to
 2048 MB, 4096 GB, 8192 TB respectively, as this limit is governed by
-the number of page table levels.
+the number of page table levels. In the case that there is no limit we will set
+the limit to KVM_S390_NO_MEM_LIMIT (U64_MAX).
 
 2. GROUP: KVM_S390_VM_CPU_MODEL
 Architectures: s390

arch/s390/include/asm/kvm_host.h

@@ -627,6 +627,7 @@ struct kvm_arch{
 	struct kvm_s390_float_interrupt float_int;
 	struct kvm_device *flic;
 	struct gmap *gmap;
+	unsigned long mem_limit;
 	int css_support;
 	int use_irqchip;
 	int use_cmma;

arch/s390/include/uapi/asm/kvm.h

@@ -66,6 +66,8 @@ struct kvm_s390_io_adapter_req {
 #define KVM_S390_VM_MEM_CLR_CMMA	1
 #define KVM_S390_VM_MEM_LIMIT_SIZE	2
 
+#define KVM_S390_NO_MEM_LIMIT		U64_MAX
+
 /* kvm attributes for KVM_S390_VM_TOD */
 #define KVM_S390_VM_TOD_LOW		0
 #define KVM_S390_VM_TOD_HIGH		1

arch/s390/kvm/kvm-s390.c

@@ -378,8 +378,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 	case KVM_S390_VM_MEM_LIMIT_SIZE:
 		ret = 0;
 		VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
-			 kvm->arch.gmap->asce_end);
-		if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+			 kvm->arch.mem_limit);
+		if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
 			ret = -EFAULT;
 		break;
 	default:
@@ -431,9 +431,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 		if (get_user(new_limit, (u64 __user *)attr->addr))
 			return -EFAULT;
 
-		if (new_limit > kvm->arch.gmap->asce_end)
+		if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+		    new_limit > kvm->arch.mem_limit)
 			return -E2BIG;
 
+		if (!new_limit)
+			return -EINVAL;
+
+		/* gmap_alloc takes last usable address */
+		if (new_limit != KVM_S390_NO_MEM_LIMIT)
+			new_limit -= 1;
+
 		ret = -EBUSY;
 		mutex_lock(&kvm->lock);
 		if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -450,7 +458,9 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
 			}
 		}
 		mutex_unlock(&kvm->lock);
-		VM_EVENT(kvm, 3, "SET: max guest memory: %lu bytes", new_limit);
+		VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+			 (void *) kvm->arch.gmap->asce);
 		break;
 	}
 	default:
@@ -1172,8 +1182,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 	if (type & KVM_VM_S390_UCONTROL) {
 		kvm->arch.gmap = NULL;
+		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
 	} else {
-		kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+		if (sclp.hamax == U64_MAX)
+			kvm->arch.mem_limit = TASK_MAX_SIZE;
+		else
+			kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+						    sclp.hamax + 1);
+		kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
 		if (!kvm->arch.gmap)
 			goto out_err;
 		kvm->arch.gmap->private = kvm;
@@ -1185,7 +1201,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	kvm->arch.epoch = 0;
 
 	spin_lock_init(&kvm->arch.start_stop_lock);
-	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -1245,7 +1261,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		gmap_free(kvm->arch.gmap);
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
-	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -1349,7 +1365,8 @@ static int sca_switch_to_extended(struct kvm *kvm)
 
 	free_page((unsigned long)old_sca);
 
-	VM_EVENT(kvm, 2, "Switched to ESCA (%p -> %p)", old_sca, kvm->arch.sca);
+	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+		 old_sca, kvm->arch.sca);
 	return 0;
 }
 
@@ -1624,7 +1641,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 	rc = kvm_vcpu_init(vcpu, kvm, id);
 	if (rc)
 		goto out_free_sie_block;
-	VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+	VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
 		 vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
 
@@ -2120,7 +2137,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
 	 */
 	kvm_check_async_pf_completion(vcpu);
 
-	memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+	vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+	vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
 
 	if (need_resched())
 		schedule();
@@ -2185,7 +2203,8 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
 	if (guestdbg_enabled(vcpu))
 		kvm_s390_restore_guest_per_regs(vcpu);
 
-	memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
+	vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+	vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
 
 	if (vcpu->arch.sie_block->icptcode > 0) {
 		int rc = kvm_handle_sie_intercept(vcpu);
@@ -2826,6 +2845,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 	if (mem->memory_size & 0xffffful)
 		return -EINVAL;
 
+	if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+		return -EINVAL;
+
 	return 0;
 }
 

arch/s390/kvm/trace-s390.h

@@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu,
 		    __entry->sie_block = sie_block;
 		    ),
 
-	    TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
-		      __entry->vcpu, __entry->sie_block)
+	    TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+		      __entry->id, __entry->vcpu, __entry->sie_block)
 	);
 
 TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css,
 		    __entry->kvm = kvm;
 		    ),
 
-	    TP_printk("enabling channel I/O support (kvm @ %p)\n",
+	    TP_printk("enabling channel I/O support (kvm @ %pK)\n",
 		      __entry->kvm)
 	);
 

arch/s390/mm/pgtable.c

@@ -133,7 +133,7 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 /**
  * gmap_alloc - allocate a guest address space
  * @mm: pointer to the parent mm_struct
- * @limit: maximum size of the gmap address space
+ * @limit: maximum address of the gmap address space
  *
  * Returns a guest address space structure.
  */
@@ -402,7 +402,7 @@ int gmap_map_segment(struct gmap *gmap, unsigned long from,
 	if ((from | to | len) & (PMD_SIZE - 1))
 		return -EINVAL;
 	if (len == 0 || from + len < from || to + len < to ||
-	    from + len > TASK_MAX_SIZE || to + len > gmap->asce_end)
+	    from + len - 1 > TASK_MAX_SIZE || to + len - 1 > gmap->asce_end)
 		return -EINVAL;
 
 	flush = 0;

drivers/s390/char/sclp_early.c

@@ -40,7 +40,8 @@ struct read_info_sccb {
 	u8	fac85;			/* 85 */
 	u8	_pad_86[91 - 86];	/* 86-90 */
 	u8	flags;			/* 91 */
-	u8	_pad_92[100 - 92];	/* 92-99 */
+	u8	_pad_92[99 - 92];	/* 92-98 */
+	u8	hamaxpow;		/* 99 */
 	u32	rnsize2;		/* 100-103 */
 	u64	rnmax2;			/* 104-111 */
 	u8	_pad_112[116 - 112];	/* 112-115 */
@@ -120,6 +121,11 @@ static void __init sclp_facilities_detect(struct read_info_sccb *sccb)
 	sclp.rzm <<= 20;
 	sclp.ibc = sccb->ibc;
 
+	if (sccb->hamaxpow && sccb->hamaxpow < 64)
+		sclp.hamax = (1UL << sccb->hamaxpow) - 1;
+	else
+		sclp.hamax = U64_MAX;
+
 	if (!sccb->hcpua) {
 		if (MACHINE_IS_VM)
 			sclp.max_cores = 64;