KVM: s390: arm64: Implement basic page fault handler

Add host functionality to page in guest memory. If the guest does
something unexpected or illegal exit to userspace abort guest execution.
This behaviour will be changed to guest error injects once all sysregs
are accessible for the host. Add pre-fault handler.

Co-developed-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Signed-off-by: Nina Schoetterl-Glausch <nsg@linux.ibm.com>
Signed-off-by: Steffen Eiden <seiden@linux.ibm.com>
[borntraeger@linux.ibm.com: fixup for recent arm changes]
Signed-off-by: Christian Borntraeger <borntraeger@linux.ibm.com>

arch/s390/kvm/arm64/handle_exit.c

@@ -62,6 +62,8 @@ static int kvm_handle_unknown_ec(struct kvm_vcpu *vcpu)
 static exit_handle_fn arm_exit_handlers[] = {
 	[0 ... ESR_ELx_EC_MAX]	= kvm_handle_unknown_ec,
 	[ESR_ELx_EC_HVC64]	= handle_hvc,
+	[ESR_ELx_EC_IABT_LOW]	= kvm_handle_guest_abort,
+	[ESR_ELx_EC_DABT_LOW]	= kvm_handle_guest_abort,
 };
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)

arch/s390/kvm/arm64/mmio.c

@@ -0,0 +1,15 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/kvm_host.h>
+#include <linux/bitfield.h>
+
+#include <trace/events/kvm.h>
+
+#include <arm64/kvm_emulate.h>
+#include <arm64/sysreg.h>
+
+#include "trace.h"
+
+#define __INCL_GEN_ARM_FILE
+#include "generated/mmio.inc"
+#undef __INCL_GEN_ARM_FILE

arch/s390/kvm/arm64/mmu.c

@@ -0,0 +1,210 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/kvm_host.h>
+
+#include <arm64/kvm_emulate.h>
+
+#include <faultin.h>
+
+#include "trace.h"
+
+static inline bool kvm_s390_cur_gmap_fault_is_write(struct kvm_vcpu *vcpu)
+{
+	return (vcpu->arch.sae_block.hai.pic & PGM_INT_CODE_MASK) == PGM_PROTECTION ||
+	       vcpu->arch.sae_block.hai.teid.fsi == TEID_FSI_STORE;
+}
+
+/*
+ * user_mem_abort() - handle a dat fault for the gmap of a vcpu
+ *
+ * Return: 0 on success, < 0 in case of error.
+ * Context: The mm lock must not be held before calling. May sleep.
+ */
+static int user_mem_abort(struct kvm_vcpu *vcpu, gpa_t fault_ipa,
+			  struct kvm_memory_slot *slot, hva_t hva)
+{
+	struct guest_fault f = { };
+	int ret;
+
+	if (kvm_s390_cur_gmap_fault_is_write(vcpu))
+		f.write_attempt = FOLL_WRITE;
+	f.gfn = gpa_to_gfn(fault_ipa);
+
+	ret = kvm_s390_faultin_gfn(vcpu, NULL, &f);
+	if (ret <= 0)
+		return ret;
+	if (ret == PGM_ADDRESSING)
+		/*
+		 * Without the relevant sysregs we cannot do anything for now.
+		 * Go back to userspace with an error. TODO sysreg handling
+		 */
+		return -ENOEXEC;
+	KVM_BUG_ON(ret, vcpu->kvm);
+	return -EINVAL;
+}
+
+static int kvm_handle_pic(struct kvm_vcpu *vcpu, bool *translation)
+{
+	switch (kvm_vcpu_fault_pic(vcpu)) {
+	/* expected cases: */
+	case PGM_ASCE_TYPE:
+	case PGM_REGION_FIRST_TRANS:
+	case PGM_REGION_SECOND_TRANS:
+	case PGM_REGION_THIRD_TRANS:
+	case PGM_SEGMENT_TRANSLATION:
+	case PGM_PAGE_TRANSLATION:
+		*translation = true;
+		break;
+	case PGM_PROTECTION:
+		break;
+	/* unexpected cases: */
+	case 0:
+		KVM_BUG(1, vcpu->kvm, "On MMU fault path but no fault occurred");
+		return -EFAULT;
+	default:
+		KVM_BUG(1, vcpu->kvm, "Unexpected program interrupt 0x%x, TEID 0x%016lx",
+			vcpu->arch.sae_block.hai.pic, vcpu->arch.sae_block.hai.teid.val);
+		send_sig(SIGSEGV, current, 0);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int kvm_handle_guest_abort(struct kvm_vcpu *vcpu)
+{
+	struct kvm_memory_slot *memslot;
+	bool translation = false;
+	phys_addr_t fault_ipa;
+	unsigned long hva;
+	unsigned long esr;
+	bool write_fault;
+	bool guest_size_err;
+	bool writable;
+	bool is_iabt;
+	int ret;
+	gfn_t gfn;
+
+	esr = kvm_vcpu_get_esr(vcpu);
+	fault_ipa = kvm_vcpu_get_fault_ipa(vcpu);
+	is_iabt = kvm_vcpu_trap_is_iabt(vcpu);
+	guest_size_err = vcpu->arch.sae_block.icptr == SAE_ICPTR_GUEST_ADDRESS_SIZE;
+
+	if (guest_size_err) {
+		translation = true;
+	} else {
+		ret = kvm_handle_pic(vcpu, &translation);
+		if (ret)
+			return ret;
+	}
+
+	if (translation) {
+		/*
+		 * For both cases:
+		 * Without the relevant sysregs we cannot do anything for now.
+		 * Go back to userspace with an error. TODO sysreg handling
+		 */
+		if (fault_ipa >= BIT_ULL(get_kvm_ipa_limit()))
+			return -ENOEXEC;
+
+		if (fault_ipa >= vcpu->kvm->arch.guest_phys_size)
+			return -ENOEXEC;
+	}
+
+	trace_kvm_guest_fault(*vcpu_pc(vcpu), kvm_vcpu_get_esr(vcpu),
+		      kvm_vcpu_get_hfar(vcpu), fault_ipa);
+
+	kvm_vcpu_srcu_read_lock(vcpu);
+
+	gfn = fault_ipa >> PAGE_SHIFT;
+
+	memslot = gfn_to_memslot(vcpu->kvm, gfn);
+	hva = gfn_to_hva_memslot_prot(memslot, gfn, &writable);
+	write_fault = kvm_s390_cur_gmap_fault_is_write(vcpu);
+	if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
+		ret = -ENOEXEC;
+		/*
+		 * The guest has put either its instructions or its page-tables
+		 * somewhere it shouldn't have. Userspace won't be able to do
+		 * anything about this (there's no syndrome for a start).
+		 *
+		 * Without the relevant sysregs we cannot do anything for now.
+		 * Go back to userspace with an error. TODO sysreg handling
+		 */
+		if (is_iabt)
+			goto out_unlock;
+
+		if (kvm_vcpu_abt_iss1tw(vcpu)) {
+			/*
+			 * Without the relevant sysregs we cannot do anything for now.
+			 * Go back to userspace with an error. TODO sysreg handling
+			 */
+			goto out_unlock;
+		}
+
+		/*
+		 * Check for a cache maintenance operation. Assume the guest is
+		 * cautious and skip instruction
+		 */
+		if (kvm_is_error_hva(hva) && esr_dabt_is_cm(esr)) {
+			kvm_incr_pc(vcpu);
+			ret = 1;
+			goto out_unlock;
+		}
+
+		/*
+		 * The IPA is reported as [MAX:12], so we need to
+		 * complement it with the bottom 12 bits from the
+		 * faulting VA. This is always 12 bits, irrespective
+		 * of the page size.
+		 */
+		fault_ipa |= kvm_vcpu_get_hfar(vcpu) & ((1 << 12) - 1);
+		ret = io_mem_abort(vcpu, fault_ipa);
+		goto out_unlock;
+	}
+
+	/* Userspace should not be able to register out-of-bounds IPAs */
+	VM_BUG_ON(fault_ipa >= vcpu->kvm->arch.guest_phys_size);
+	/*
+	 * Proper guest size faults have been injected.
+	 * In theory it's fine to have device memory higher than MSL,
+	 * even if not currently possible, but that would have been handled above.
+	 * So if we get here with a guest size intercept, we have a bug somewhere.
+	 */
+	VM_BUG_ON(guest_size_err);
+
+	ret = user_mem_abort(vcpu, fault_ipa, memslot, hva);
+	if (!ret)
+		ret = 1;
+out_unlock:
+	kvm_vcpu_srcu_read_unlock(vcpu);
+	return ret;
+}
+
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu, struct kvm_pre_fault_memory *range)
+{
+	struct guest_fault f = { .gfn = gpa_to_gfn(range->gpa), };
+	gpa_t end;
+	int rc;
+
+	rc = kvm_s390_faultin_gfn(vcpu, NULL, &f);
+	if (rc == PGM_ADDRESSING)
+		return -ENOENT;
+	if (rc > 0)
+		return -EIO;
+	if (rc < 0)
+		return rc;
+
+	if (f.ptep)
+		return PAGE_SIZE;
+
+	end = ALIGN(range->gpa + PAGE_SIZE, f.crste_region3 ? _REGION3_SIZE : HPAGE_SIZE);
+	return min(range->size, end - range->gpa);
+}
+
+int kvm_arch_pre_fault_allowed(struct kvm_vcpu *vcpu)
+{
+	if (!kvm_vcpu_initialized(vcpu))
+		return -ENOEXEC;
+
+	return 0;
+}

arch/s390/kvm/arm64/trace.h

@@ -41,6 +41,55 @@ TRACE_EVENT(kvm_exit,
 		  __entry->vcpu_pc)
 );
 
+TRACE_EVENT(kvm_mmio_nisv,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long esr,
+		 unsigned long far, unsigned long ipa),
+	TP_ARGS(vcpu_pc, esr, far, ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	esr		)
+		__field(	unsigned long,	far		)
+		__field(	unsigned long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->esr			= esr;
+		__entry->far			= far;
+		__entry->ipa			= ipa;
+	),
+
+	TP_printk("ipa %#016lx, esr %#016lx, far %#016lx, pc %#016lx",
+		  __entry->ipa, __entry->esr,
+		  __entry->far, __entry->vcpu_pc)
+);
+
+TRACE_EVENT(kvm_guest_fault,
+	TP_PROTO(unsigned long vcpu_pc, unsigned long hsr,
+		 unsigned long hxfar,
+		 unsigned long long ipa),
+	TP_ARGS(vcpu_pc, hsr, hxfar, ipa),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	vcpu_pc		)
+		__field(	unsigned long,	hsr		)
+		__field(	unsigned long,	hxfar		)
+		__field(   unsigned long long,	ipa		)
+	),
+
+	TP_fast_assign(
+		__entry->vcpu_pc		= vcpu_pc;
+		__entry->hsr			= hsr;
+		__entry->hxfar			= hxfar;
+		__entry->ipa			= ipa;
+	),
+
+	TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx",
+		  __entry->ipa, __entry->hsr,
+		  __entry->hxfar, __entry->vcpu_pc)
+);
+
 #endif /* KVM_ARM64_TRACE_KVM_H */
 
 #undef TRACE_INCLUDE_PATH