1 files changed, 228 insertions, 64 deletions
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index d8080c27d45b..3f3175193fd7 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -23,6 +23,7 @@
 #include <linux/mman.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
+#include <linux/cpufeature.h>
 #include <linux/random.h>
 #include <linux/slab.h>
 #include <linux/timer.h>
@@ -36,6 +37,7 @@
 #include <asm/access-regs.h>
 #include <asm/asm-offsets.h>
 #include <asm/lowcore.h>
+#include <asm/machine.h>
 #include <asm/stp.h>
 #include <asm/gmap.h>
 #include <asm/nmi.h>
@@ -50,6 +52,7 @@
 #include "kvm-s390.h"
 #include "gaccess.h"
 #include "pci.h"
+#include "gmap.h"
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -442,13 +445,13 @@ static void __init kvm_s390_cpu_feat_init(void)
 	if (test_facility(201))	/* PFCR */
 		pfcr_query(&kvm_s390_available_subfunc.pfcr);
 
-	if (MACHINE_HAS_ESOP)
+	if (machine_has_esop())
 		allow_cpu_feat(KVM_S390_VM_CPU_FEAT_ESOP);
 	/*
 	 * We need SIE support, ESOP (PROT_READ protection for gmap_shadow),
 	 * 64bit SCAO (SCA passthrough) and IDTE (for gmap_shadow unshadowing).
 	 */
-	if (!sclp.has_sief2 || !MACHINE_HAS_ESOP || !sclp.has_64bscao ||
+	if (!sclp.has_sief2 || !machine_has_esop() || !sclp.has_64bscao ||
 	    !test_facility(3) || !nested)
 		return;
 	allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
@@ -637,7 +640,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 			r = min_t(unsigned int, num_online_cpus(), r);
 		break;
 	case KVM_CAP_S390_COW:
-		r = MACHINE_HAS_ESOP;
+		r = machine_has_esop();
 		break;
 	case KVM_CAP_S390_VECTOR_REGISTERS:
 		r = test_facility(129);
@@ -1019,7 +1022,7 @@ 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 address: %lu", new_limit);
-		VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+		VM_EVENT(kvm, 3, "New guest asce: 0x%p",
 			 (void *) kvm->arch.gmap->asce);
 		break;
 	}
@@ -3395,7 +3398,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	/* we emulate STHYI in kvm */
 	set_kvm_facility(kvm->arch.model.fac_mask, 74);
 	set_kvm_facility(kvm->arch.model.fac_list, 74);
-	if (MACHINE_HAS_TLB_GUEST) {
+	if (machine_has_tlb_guest()) {
 		set_kvm_facility(kvm->arch.model.fac_mask, 147);
 		set_kvm_facility(kvm->arch.model.fac_list, 147);
 	}
@@ -3428,8 +3431,20 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	VM_EVENT(kvm, 3, "vm created with type %lu", type);
 
 	if (type & KVM_VM_S390_UCONTROL) {
+		struct kvm_userspace_memory_region2 fake_memslot = {
+			.slot = KVM_S390_UCONTROL_MEMSLOT,
+			.guest_phys_addr = 0,
+			.userspace_addr = 0,
+			.memory_size = ALIGN_DOWN(TASK_SIZE, _SEGMENT_SIZE),
+			.flags = 0,
+		};
+
 		kvm->arch.gmap = NULL;
 		kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
+		/* one flat fake memslot covering the whole address-space */
+		mutex_lock(&kvm->slots_lock);
+		KVM_BUG_ON(kvm_set_internal_memslot(kvm, &fake_memslot), kvm);
+		mutex_unlock(&kvm->slots_lock);
 	} else {
 		if (sclp.hamax == U64_MAX)
 			kvm->arch.mem_limit = TASK_SIZE_MAX;
@@ -3451,7 +3466,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 		kvm_s390_gisa_init(kvm);
 	INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup);
 	kvm->arch.pv.set_aside = NULL;
-	KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
+	KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
 
 	return 0;
 out_err:
@@ -3514,7 +3529,7 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	kvm_s390_destroy_adapters(kvm);
 	kvm_s390_clear_float_irqs(kvm);
 	kvm_s390_vsie_destroy(kvm);
-	KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
+	KVM_EVENT(3, "vm 0x%p destroyed", kvm);
 }
 
 /* Section: vcpu related */
@@ -3635,7 +3650,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
 
 	free_page((unsigned long)old_sca);
 
-	VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+	VM_EVENT(kvm, 2, "Switched to ESCA (0x%p -> 0x%p)",
 		 old_sca, kvm->arch.sca);
 	return 0;
 }
@@ -3879,8 +3894,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 
 	kvm_s390_vcpu_setup_model(vcpu);
 
-	/* pgste_set_pte has special handling for !MACHINE_HAS_ESOP */
-	if (MACHINE_HAS_ESOP)
+	/* pgste_set_pte has special handling for !machine_has_esop() */
+	if (machine_has_esop())
 		vcpu->arch.sie_block->ecb |= ECB_HOSTPROTINT;
 	if (test_kvm_facility(vcpu->kvm, 9))
 		vcpu->arch.sie_block->ecb |= ECB_SRSI;
@@ -3930,8 +3945,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
 		if (rc)
 			return rc;
 	}
-	hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
-	vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+	hrtimer_setup(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup, CLOCK_MONOTONIC,
+		      HRTIMER_MODE_REL);
 
 	vcpu->arch.sie_block->hpid = HPID_KVM;
 
@@ -4012,7 +4027,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 			goto out_free_sie_block;
 	}
 
-	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK",
+	VM_EVENT(vcpu->kvm, 3, "create cpu %d at 0x%p, sie block at 0x%p",
 		 vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
 	trace_kvm_s390_create_vcpu(vcpu->vcpu_id, vcpu, vcpu->arch.sie_block);
 
@@ -4498,6 +4513,75 @@ static bool ibs_enabled(struct kvm_vcpu *vcpu)
 	return kvm_s390_test_cpuflags(vcpu, CPUSTAT_IBS);
 }
 
+static int __kvm_s390_fixup_fault_sync(struct gmap *gmap, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm *kvm = gmap->private;
+	gfn_t gfn = gpa_to_gfn(gaddr);
+	bool unlocked;
+	hva_t vmaddr;
+	gpa_t tmp;
+	int rc;
+
+	if (kvm_is_ucontrol(kvm)) {
+		tmp = __gmap_translate(gmap, gaddr);
+		gfn = gpa_to_gfn(tmp);
+	}
+
+	vmaddr = gfn_to_hva(kvm, gfn);
+	rc = fixup_user_fault(gmap->mm, vmaddr, FAULT_FLAG_WRITE, &unlocked);
+	if (!rc)
+		rc = __gmap_link(gmap, gaddr, vmaddr);
+	return rc;
+}
+
+/**
+ * __kvm_s390_mprotect_many() - Apply specified protection to guest pages
+ * @gmap: the gmap of the guest
+ * @gpa: the starting guest address
+ * @npages: how many pages to protect
+ * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE
+ * @bits: pgste notification bits to set
+ *
+ * Returns: 0 in case of success, < 0 in case of error - see gmap_protect_one()
+ *
+ * Context: kvm->srcu and gmap->mm need to be held in read mode
+ */
+int __kvm_s390_mprotect_many(struct gmap *gmap, gpa_t gpa, u8 npages, unsigned int prot,
+			     unsigned long bits)
+{
+	unsigned int fault_flag = (prot & PROT_WRITE) ? FAULT_FLAG_WRITE : 0;
+	gpa_t end = gpa + npages * PAGE_SIZE;
+	int rc;
+
+	for (; gpa < end; gpa = ALIGN(gpa + 1, rc)) {
+		rc = gmap_protect_one(gmap, gpa, prot, bits);
+		if (rc == -EAGAIN) {
+			__kvm_s390_fixup_fault_sync(gmap, gpa, fault_flag);
+			rc = gmap_protect_one(gmap, gpa, prot, bits);
+		}
+		if (rc < 0)
+			return rc;
+	}
+
+	return 0;
+}
+
+static int kvm_s390_mprotect_notify_prefix(struct kvm_vcpu *vcpu)
+{
+	gpa_t gaddr = kvm_s390_get_prefix(vcpu);
+	int idx, rc;
+
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	mmap_read_lock(vcpu->arch.gmap->mm);
+
+	rc = __kvm_s390_mprotect_many(vcpu->arch.gmap, gaddr, 2, PROT_WRITE, GMAP_NOTIFY_MPROT);
+
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
+	return rc;
+}
+
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
 retry:
@@ -4513,9 +4597,8 @@ retry:
 	 */
 	if (kvm_check_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu)) {
 		int rc;
-		rc = gmap_mprotect_notify(vcpu->arch.gmap,
-					  kvm_s390_get_prefix(vcpu),
-					  PAGE_SIZE * 2, PROT_WRITE);
+
+		rc = kvm_s390_mprotect_notify_prefix(vcpu);
 		if (rc) {
 			kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
 			return rc;
@@ -4766,11 +4849,112 @@ static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu)
 	return kvm_s390_inject_prog_irq(vcpu, &pgm_info);
 }
 
+static void kvm_s390_assert_primary_as(struct kvm_vcpu *vcpu)
+{
+	KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
+		"Unexpected program interrupt 0x%x, TEID 0x%016lx",
+		current->thread.gmap_int_code, current->thread.gmap_teid.val);
+}
+
+/*
+ * __kvm_s390_handle_dat_fault() - handle a dat fault for the gmap of a vcpu
+ * @vcpu: the vCPU whose gmap is to be fixed up
+ * @gfn: the guest frame number used for memslots (including fake memslots)
+ * @gaddr: the gmap address, does not have to match @gfn for ucontrol gmaps
+ * @flags: FOLL_* flags
+ *
+ * Return: 0 on success, < 0 in case of error.
+ * Context: The mm lock must not be held before calling. May sleep.
+ */
+int __kvm_s390_handle_dat_fault(struct kvm_vcpu *vcpu, gfn_t gfn, gpa_t gaddr, unsigned int flags)
+{
+	struct kvm_memory_slot *slot;
+	unsigned int fault_flags;
+	bool writable, unlocked;
+	unsigned long vmaddr;
+	struct page *page;
+	kvm_pfn_t pfn;
+	int rc;
+
+	slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn);
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
+		return vcpu_post_run_addressing_exception(vcpu);
+
+	fault_flags = flags & FOLL_WRITE ? FAULT_FLAG_WRITE : 0;
+	if (vcpu->arch.gmap->pfault_enabled)
+		flags |= FOLL_NOWAIT;
+	vmaddr = __gfn_to_hva_memslot(slot, gfn);
+
+try_again:
+	pfn = __kvm_faultin_pfn(slot, gfn, flags, &writable, &page);
+
+	/* Access outside memory, inject addressing exception */
+	if (is_noslot_pfn(pfn))
+		return vcpu_post_run_addressing_exception(vcpu);
+	/* Signal pending: try again */
+	if (pfn == KVM_PFN_ERR_SIGPENDING)
+		return -EAGAIN;
+
+	/* Needs I/O, try to setup async pfault (only possible with FOLL_NOWAIT) */
+	if (pfn == KVM_PFN_ERR_NEEDS_IO) {
+		trace_kvm_s390_major_guest_pfault(vcpu);
+		if (kvm_arch_setup_async_pf(vcpu))
+			return 0;
+		vcpu->stat.pfault_sync++;
+		/* Could not setup async pfault, try again synchronously */
+		flags &= ~FOLL_NOWAIT;
+		goto try_again;
+	}
+	/* Any other error */
+	if (is_error_pfn(pfn))
+		return -EFAULT;
+
+	/* Success */
+	mmap_read_lock(vcpu->arch.gmap->mm);
+	/* Mark the userspace PTEs as young and/or dirty, to avoid page fault loops */
+	rc = fixup_user_fault(vcpu->arch.gmap->mm, vmaddr, fault_flags, &unlocked);
+	if (!rc)
+		rc = __gmap_link(vcpu->arch.gmap, gaddr, vmaddr);
+	scoped_guard(spinlock, &vcpu->kvm->mmu_lock) {
+		kvm_release_faultin_page(vcpu->kvm, page, false, writable);
+	}
+	mmap_read_unlock(vcpu->arch.gmap->mm);
+	return rc;
+}
+
+static int vcpu_dat_fault_handler(struct kvm_vcpu *vcpu, unsigned long gaddr, unsigned int flags)
+{
+	unsigned long gaddr_tmp;
+	gfn_t gfn;
+
+	gfn = gpa_to_gfn(gaddr);
+	if (kvm_is_ucontrol(vcpu->kvm)) {
+		/*
+		 * This translates the per-vCPU guest address into a
+		 * fake guest address, which can then be used with the
+		 * fake memslots that are identity mapping userspace.
+		 * This allows ucontrol VMs to use the normal fault
+		 * resolution path, like normal VMs.
+		 */
+		mmap_read_lock(vcpu->arch.gmap->mm);
+		gaddr_tmp = __gmap_translate(vcpu->arch.gmap, gaddr);
+		mmap_read_unlock(vcpu->arch.gmap->mm);
+		if (gaddr_tmp == -EFAULT) {
+			vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
+			vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
+			vcpu->run->s390_ucontrol.pgm_code = PGM_SEGMENT_TRANSLATION;
+			return -EREMOTE;
+		}
+		gfn = gpa_to_gfn(gaddr_tmp);
+	}
+	return __kvm_s390_handle_dat_fault(vcpu, gfn, gaddr, flags);
+}
+
 static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 {
 	unsigned int flags = 0;
 	unsigned long gaddr;
-	int rc = 0;
+	int rc;
 
 	gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
 	if (kvm_s390_cur_gmap_fault_is_write())
@@ -4780,23 +4964,9 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	case 0:
 		vcpu->stat.exit_null++;
 		break;
-	case PGM_NON_SECURE_STORAGE_ACCESS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
-		/*
-		 * This is normal operation; a page belonging to a protected
-		 * guest has not been imported yet. Try to import the page into
-		 * the protected guest.
-		 */
-		if (gmap_convert_to_secure(vcpu->arch.gmap, gaddr) == -EINVAL)
-			send_sig(SIGSEGV, current, 0);
-		break;
 	case PGM_SECURE_STORAGE_ACCESS:
 	case PGM_SECURE_STORAGE_VIOLATION:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
+		kvm_s390_assert_primary_as(vcpu);
 		/*
 		 * This can happen after a reboot with asynchronous teardown;
 		 * the new guest (normal or protected) will run on top of the
@@ -4818,6 +4988,20 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 			send_sig(SIGSEGV, current, 0);
 		}
 		break;
+	case PGM_NON_SECURE_STORAGE_ACCESS:
+		kvm_s390_assert_primary_as(vcpu);
+		/*
+		 * This is normal operation; a page belonging to a protected
+		 * guest has not been imported yet. Try to import the page into
+		 * the protected guest.
+		 */
+		rc = gmap_convert_to_secure(vcpu->arch.gmap, gaddr);
+		if (rc == -EINVAL)
+			send_sig(SIGSEGV, current, 0);
+		if (rc != -ENXIO)
+			break;
+		flags = FAULT_FLAG_WRITE;
+		fallthrough;
 	case PGM_PROTECTION:
 	case PGM_SEGMENT_TRANSLATION:
 	case PGM_PAGE_TRANSLATION:
@@ -4825,40 +5009,15 @@ static int vcpu_post_run_handle_fault(struct kvm_vcpu *vcpu)
 	case PGM_REGION_FIRST_TRANS:
 	case PGM_REGION_SECOND_TRANS:
 	case PGM_REGION_THIRD_TRANS:
-		KVM_BUG(current->thread.gmap_teid.as != PSW_BITS_AS_PRIMARY, vcpu->kvm,
-			"Unexpected program interrupt 0x%x, TEID 0x%016lx",
-			current->thread.gmap_int_code, current->thread.gmap_teid.val);
-		if (vcpu->arch.gmap->pfault_enabled) {
-			rc = gmap_fault(vcpu->arch.gmap, gaddr, flags | FAULT_FLAG_RETRY_NOWAIT);
-			if (rc == -EFAULT)
-				return vcpu_post_run_addressing_exception(vcpu);
-			if (rc == -EAGAIN) {
-				trace_kvm_s390_major_guest_pfault(vcpu);
-				if (kvm_arch_setup_async_pf(vcpu))
-					return 0;
-				vcpu->stat.pfault_sync++;
-			} else {
-				return rc;
-			}
-		}
-		rc = gmap_fault(vcpu->arch.gmap, gaddr, flags);
-		if (rc == -EFAULT) {
-			if (kvm_is_ucontrol(vcpu->kvm)) {
-				vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
-				vcpu->run->s390_ucontrol.trans_exc_code = gaddr;
-				vcpu->run->s390_ucontrol.pgm_code = 0x10;
-				return -EREMOTE;
-			}
-			return vcpu_post_run_addressing_exception(vcpu);
-		}
-		break;
+		kvm_s390_assert_primary_as(vcpu);
+		return vcpu_dat_fault_handler(vcpu, gaddr, flags);
 	default:
 		KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
 			current->thread.gmap_int_code, current->thread.gmap_teid.val);
 		send_sig(SIGSEGV, current, 0);
 		break;
 	}
-	return rc;
+	return 0;
 }
 
 static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
@@ -5019,7 +5178,7 @@ static void sync_regs_fmt2(struct kvm_vcpu *vcpu)
 		vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
 		vcpu->arch.sie_block->fpf |= kvm_run->s.regs.bpbc ? FPF_BPBC : 0;
 	}
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		preempt_disable();
 		local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
 		if (current->thread.gs_cb) {
@@ -5085,7 +5244,7 @@ static void store_regs_fmt2(struct kvm_vcpu *vcpu)
 	kvm_run->s.regs.gbea = vcpu->arch.sie_block->gbea;
 	kvm_run->s.regs.bpbc = (vcpu->arch.sie_block->fpf & FPF_BPBC) == FPF_BPBC;
 	kvm_run->s.regs.diag318 = vcpu->arch.diag318_info.val;
-	if (MACHINE_HAS_GS) {
+	if (cpu_has_gs()) {
 		preempt_disable();
 		local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
 		if (vcpu->arch.gs_enabled)
@@ -5737,7 +5896,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	}
 #endif
 	case KVM_S390_VCPU_FAULT: {
-		r = gmap_fault(vcpu->arch.gmap, arg, 0);
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		r = vcpu_dat_fault_handler(vcpu, arg, 0);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 	case KVM_ENABLE_CAP:
@@ -5853,7 +6014,7 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 {
 	gpa_t size;
 
-	if (kvm_is_ucontrol(kvm))
+	if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS)
 		return -EINVAL;
 
 	/* When we are protected, we should not change the memory slots */
@@ -5905,6 +6066,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 {
 	int rc = 0;
 
+	if (kvm_is_ucontrol(kvm))
+		return;
+
 	switch (change) {
 	case KVM_MR_DELETE:
 		rc = gmap_unmap_segment(kvm->arch.gmap, old->base_gfn * PAGE_SIZE,