Merge tag 'kvm-s390-next-5.6-1' of...

Merge tag 'kvm-s390-next-5.6-1' of git://git.kernel.org/pub/scm/linux/kernel/git/kvms390/linux into HEAD

KVM: s390: Fixes and cleanups for 5.6
- fix register corruption
- ENOTSUPP/EOPNOTSUPP mixed
- reset cleanups/fixes
- selftests

Documentation/virt/kvm/api.txt

@@ -4177,6 +4177,42 @@ This ioctl issues an ultravisor call to terminate the secure guest,
 unpins the VPA pages and releases all the device pages that are used to
 track the secure pages by hypervisor.
 
+4.122 KVM_S390_NORMAL_RESET
+
+Capability: KVM_CAP_S390_VCPU_RESETS
+Architectures: s390
+Type: vcpu ioctl
+Parameters: none
+Returns: 0
+
+This ioctl resets VCPU registers and control structures according to
+the cpu reset definition in the POP (Principles Of Operation).
+
+4.123 KVM_S390_INITIAL_RESET
+
+Capability: none
+Architectures: s390
+Type: vcpu ioctl
+Parameters: none
+Returns: 0
+
+This ioctl resets VCPU registers and control structures according to
+the initial cpu reset definition in the POP. However, the cpu is not
+put into ESA mode. This reset is a superset of the normal reset.
+
+4.124 KVM_S390_CLEAR_RESET
+
+Capability: KVM_CAP_S390_VCPU_RESETS
+Architectures: s390
+Type: vcpu ioctl
+Parameters: none
+Returns: 0
+
+This ioctl resets VCPU registers and control structures according to
+the clear cpu reset definition in the POP. However, the cpu is not put
+into ESA mode. This reset is a superset of the initial reset.
+
+
 5. The kvm_run structure
 ------------------------
 
@@ -5405,3 +5441,10 @@ handling by KVM (as some KVM hypercall may be mistakenly treated as TLB
 flush hypercalls by Hyper-V) so userspace should disable KVM identification
 in CPUID and only exposes Hyper-V identification. In this case, guest
 thinks it's running on Hyper-V and only use Hyper-V hypercalls.
+
+8.22 KVM_CAP_S390_VCPU_RESETS
+
+Architectures: s390
+
+This capability indicates that the KVM_S390_NORMAL_RESET and
+KVM_S390_CLEAR_RESET ioctls are available.

arch/s390/include/asm/kvm_host.h

@@ -122,6 +122,11 @@ struct mcck_volatile_info {
 	__u32 reserved;
 };
 
+#define CR0_INITIAL_MASK (CR0_UNUSED_56 | CR0_INTERRUPT_KEY_SUBMASK | \
+			  CR0_MEASUREMENT_ALERT_SUBMASK)
+#define CR14_INITIAL_MASK (CR14_UNUSED_32 | CR14_UNUSED_33 | \
+			   CR14_EXTERNAL_DAMAGE_SUBMASK)
+
 #define CPUSTAT_STOPPED    0x80000000
 #define CPUSTAT_WAIT       0x10000000
 #define CPUSTAT_ECALL_PEND 0x08000000

arch/s390/kvm/interrupt.c

@@ -2190,7 +2190,7 @@ static int flic_ais_mode_get_all(struct kvm *kvm, struct kvm_device_attr *attr)
 		return -EINVAL;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	mutex_lock(&fi->ais_lock);
 	ais.simm = fi->simm;
@@ -2499,7 +2499,7 @@ static int modify_ais_mode(struct kvm *kvm, struct kvm_device_attr *attr)
 	int ret = 0;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (copy_from_user(&req, (void __user *)attr->addr, sizeof(req)))
 		return -EFAULT;
@@ -2579,7 +2579,7 @@ static int flic_ais_mode_set_all(struct kvm *kvm, struct kvm_device_attr *attr)
 	struct kvm_s390_ais_all ais;
 
 	if (!test_kvm_facility(kvm, 72))
-		return -ENOTSUPP;
+		return -EOPNOTSUPP;
 
 	if (copy_from_user(&ais, (void __user *)attr->addr, sizeof(ais)))
 		return -EFAULT;

arch/s390/kvm/kvm-s390.c

@@ -529,6 +529,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_S390_CMMA_MIGRATION:
 	case KVM_CAP_S390_AIS:
 	case KVM_CAP_S390_AIS_MIGRATION:
+	case KVM_CAP_S390_VCPU_RESETS:
 		r = 1;
 		break;
 	case KVM_CAP_S390_HPAGE_1M:
@@ -2808,35 +2809,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 
 }
 
-static void kvm_s390_vcpu_initial_reset(struct kvm_vcpu *vcpu)
-{
-	/* this equals initial cpu reset in pop, but we don't switch to ESA */
-	vcpu->arch.sie_block->gpsw.mask = 0UL;
-	vcpu->arch.sie_block->gpsw.addr = 0UL;
-	kvm_s390_set_prefix(vcpu, 0);
-	kvm_s390_set_cpu_timer(vcpu, 0);
-	vcpu->arch.sie_block->ckc       = 0UL;
-	vcpu->arch.sie_block->todpr     = 0;
-	memset(vcpu->arch.sie_block->gcr, 0, 16 * sizeof(__u64));
-	vcpu->arch.sie_block->gcr[0]  = CR0_UNUSED_56 |
-					CR0_INTERRUPT_KEY_SUBMASK |
-					CR0_MEASUREMENT_ALERT_SUBMASK;
-	vcpu->arch.sie_block->gcr[14] = CR14_UNUSED_32 |
-					CR14_UNUSED_33 |
-					CR14_EXTERNAL_DAMAGE_SUBMASK;
-	/* make sure the new fpc will be lazily loaded */
-	save_fpu_regs();
-	current->thread.fpu.fpc = 0;
-	vcpu->arch.sie_block->gbea = 1;
-	vcpu->arch.sie_block->pp = 0;
-	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
-	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
-	kvm_clear_async_pf_completion_queue(vcpu);
-	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
-		kvm_s390_vcpu_stop(vcpu);
-	kvm_s390_clear_local_irqs(vcpu);
-}
-
 void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
 {
 	mutex_lock(&vcpu->kvm->lock);
@@ -3279,10 +3251,53 @@ static int kvm_arch_vcpu_ioctl_set_one_reg(struct kvm_vcpu *vcpu,
 	return r;
 }
 
-static int kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
+static void kvm_arch_vcpu_ioctl_normal_reset(struct kvm_vcpu *vcpu)
 {
-	kvm_s390_vcpu_initial_reset(vcpu);
-	return 0;
+	vcpu->arch.sie_block->gpsw.mask &= ~PSW_MASK_RI;
+	vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
+	memset(vcpu->run->s.regs.riccb, 0, sizeof(vcpu->run->s.regs.riccb));
+
+	kvm_clear_async_pf_completion_queue(vcpu);
+	if (!kvm_s390_user_cpu_state_ctrl(vcpu->kvm))
+		kvm_s390_vcpu_stop(vcpu);
+	kvm_s390_clear_local_irqs(vcpu);
+}
+
+static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
+{
+	/* Initial reset is a superset of the normal reset */
+	kvm_arch_vcpu_ioctl_normal_reset(vcpu);
+
+	/* this equals initial cpu reset in pop, but we don't switch to ESA */
+	vcpu->arch.sie_block->gpsw.mask = 0;
+	vcpu->arch.sie_block->gpsw.addr = 0;
+	kvm_s390_set_prefix(vcpu, 0);
+	kvm_s390_set_cpu_timer(vcpu, 0);
+	vcpu->arch.sie_block->ckc = 0;
+	vcpu->arch.sie_block->todpr = 0;
+	memset(vcpu->arch.sie_block->gcr, 0, sizeof(vcpu->arch.sie_block->gcr));
+	vcpu->arch.sie_block->gcr[0] = CR0_INITIAL_MASK;
+	vcpu->arch.sie_block->gcr[14] = CR14_INITIAL_MASK;
+	vcpu->run->s.regs.fpc = 0;
+	vcpu->arch.sie_block->gbea = 1;
+	vcpu->arch.sie_block->pp = 0;
+	vcpu->arch.sie_block->fpf &= ~FPF_BPBC;
+}
+
+static void kvm_arch_vcpu_ioctl_clear_reset(struct kvm_vcpu *vcpu)
+{
+	struct kvm_sync_regs *regs = &vcpu->run->s.regs;
+
+	/* Clear reset is a superset of the initial reset */
+	kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+
+	memset(&regs->gprs, 0, sizeof(regs->gprs));
+	memset(&regs->vrs, 0, sizeof(regs->vrs));
+	memset(&regs->acrs, 0, sizeof(regs->acrs));
+	memset(&regs->gscb, 0, sizeof(regs->gscb));
+
+	regs->etoken = 0;
+	regs->etoken_extension = 0;
 }
 
 int kvm_arch_vcpu_ioctl_set_regs(struct kvm_vcpu *vcpu, struct kvm_regs *regs)
@@ -4343,7 +4358,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 	switch (ioctl) {
 	case KVM_S390_STORE_STATUS:
 		idx = srcu_read_lock(&vcpu->kvm->srcu);
-		r = kvm_s390_vcpu_store_status(vcpu, arg);
+		r = kvm_s390_store_status_unloaded(vcpu, arg);
 		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	case KVM_S390_SET_INITIAL_PSW: {
@@ -4355,8 +4370,17 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
 		r = kvm_arch_vcpu_ioctl_set_initial_psw(vcpu, psw);
 		break;
 	}
+	case KVM_S390_CLEAR_RESET:
+		r = 0;
+		kvm_arch_vcpu_ioctl_clear_reset(vcpu);
+		break;
 	case KVM_S390_INITIAL_RESET:
-		r = kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		r = 0;
+		kvm_arch_vcpu_ioctl_initial_reset(vcpu);
+		break;
+	case KVM_S390_NORMAL_RESET:
+		r = 0;
+		kvm_arch_vcpu_ioctl_normal_reset(vcpu);
 		break;
 	case KVM_SET_ONE_REG:
 	case KVM_GET_ONE_REG: {

include/uapi/linux/kvm.h

@@ -1009,6 +1009,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_PPC_GUEST_DEBUG_SSTEP 176
 #define KVM_CAP_ARM_NISV_TO_USER 177
 #define KVM_CAP_ARM_INJECT_EXT_DABT 178
+#define KVM_CAP_S390_VCPU_RESETS 179
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1473,6 +1474,10 @@ struct kvm_enc_region {
 /* Available with KVM_CAP_ARM_SVE */
 #define KVM_ARM_VCPU_FINALIZE	  _IOW(KVMIO,  0xc2, int)
 
+/* Available with  KVM_CAP_S390_VCPU_RESETS */
+#define KVM_S390_NORMAL_RESET	_IO(KVMIO,   0xc3)
+#define KVM_S390_CLEAR_RESET	_IO(KVMIO,   0xc4)
+
 /* Secure Encrypted Virtualization command */
 enum sev_cmd_id {
 	/* Guest initialization commands */

tools/testing/selftests/kvm/Makefile

@@ -36,6 +36,7 @@ TEST_GEN_PROGS_aarch64 += kvm_create_max_vcpus
 
 TEST_GEN_PROGS_s390x = s390x/memop
 TEST_GEN_PROGS_s390x += s390x/sync_regs_test
+TEST_GEN_PROGS_s390x += s390x/resets
 TEST_GEN_PROGS_s390x += dirty_log_test
 TEST_GEN_PROGS_s390x += kvm_create_max_vcpus
 

tools/testing/selftests/kvm/include/kvm_util.h

@@ -125,6 +125,12 @@ void vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
 		    struct kvm_sregs *sregs);
 int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid,
 		    struct kvm_sregs *sregs);
+void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid,
+		  struct kvm_fpu *fpu);
+void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid,
+		  struct kvm_fpu *fpu);
+void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
+void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg);
 #ifdef __KVM_HAVE_VCPU_EVENTS
 void vcpu_events_get(struct kvm_vm *vm, uint32_t vcpuid,
 		     struct kvm_vcpu_events *events);

tools/testing/selftests/kvm/lib/kvm_util.c

@@ -1373,6 +1373,42 @@ int _vcpu_sregs_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_sregs *sregs)
 	return ioctl(vcpu->fd, KVM_SET_SREGS, sregs);
 }
 
+void vcpu_fpu_get(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu)
+{
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_FPU, fpu);
+	TEST_ASSERT(ret == 0, "KVM_GET_FPU failed, rc: %i errno: %i (%s)",
+		    ret, errno, strerror(errno));
+}
+
+void vcpu_fpu_set(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_fpu *fpu)
+{
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_FPU, fpu);
+	TEST_ASSERT(ret == 0, "KVM_SET_FPU failed, rc: %i errno: %i (%s)",
+		    ret, errno, strerror(errno));
+}
+
+void vcpu_get_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg)
+{
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_GET_ONE_REG, reg);
+	TEST_ASSERT(ret == 0, "KVM_GET_ONE_REG failed, rc: %i errno: %i (%s)",
+		    ret, errno, strerror(errno));
+}
+
+void vcpu_set_reg(struct kvm_vm *vm, uint32_t vcpuid, struct kvm_one_reg *reg)
+{
+	int ret;
+
+	ret = _vcpu_ioctl(vm, vcpuid, KVM_SET_ONE_REG, reg);
+	TEST_ASSERT(ret == 0, "KVM_SET_ONE_REG failed, rc: %i errno: %i (%s)",
+		    ret, errno, strerror(errno));
+}
+
 /*
  * VCPU Ioctl
  *

tools/testing/selftests/kvm/s390x/resets.c

+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Test for s390x CPU resets
+ *
+ * Copyright (C) 2020, IBM
+ */
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+
+#include "test_util.h"
+#include "kvm_util.h"
+
+#define VCPU_ID 3
+#define LOCAL_IRQS 32
+
+struct kvm_s390_irq buf[VCPU_ID + LOCAL_IRQS];
+
+struct kvm_vm *vm;
+struct kvm_run *run;
+struct kvm_sync_regs *regs;
+static uint64_t regs_null[16];
+
+static uint64_t crs[16] = { 0x40000ULL,
+			    0x42000ULL,
+			    0, 0, 0, 0, 0,
+			    0x43000ULL,
+			    0, 0, 0, 0, 0,
+			    0x44000ULL,
+			    0, 0
+};
+
+static void guest_code_initial(void)
+{
+	/* Round toward 0 */
+	uint32_t fpc = 0x11;
+
+	/* Dirty registers */
+	asm volatile (
+		"	lctlg	0,15,%0\n"
+		"	sfpc	%1\n"
+		: : "Q" (crs), "d" (fpc));
+	GUEST_SYNC(0);
+}
+
+static void test_one_reg(uint64_t id, uint64_t value)
+{
+	struct kvm_one_reg reg;
+	uint64_t eval_reg;
+
+	reg.addr = (uintptr_t)&eval_reg;
+	reg.id = id;
+	vcpu_get_reg(vm, VCPU_ID, &reg);
+	TEST_ASSERT(eval_reg == value, "value == %s", value);
+}
+
+static void assert_noirq(void)
+{
+	struct kvm_s390_irq_state irq_state;
+	int irqs;
+
+	irq_state.len = sizeof(buf);
+	irq_state.buf = (unsigned long)buf;
+	irqs = _vcpu_ioctl(vm, VCPU_ID, KVM_S390_GET_IRQ_STATE, &irq_state);
+	/*
+	 * irqs contains the number of retrieved interrupts. Any interrupt
+	 * (notably, the emergency call interrupt we have injected) should
+	 * be cleared by the resets, so this should be 0.
+	 */
+	TEST_ASSERT(irqs >= 0, "Could not fetch IRQs: errno %d\n", errno);
+	TEST_ASSERT(!irqs, "IRQ pending");
+}
+
+static void assert_clear(void)
+{
+	struct kvm_sregs sregs;
+	struct kvm_regs regs;
+	struct kvm_fpu fpu;
+
+	vcpu_regs_get(vm, VCPU_ID, &regs);
+	TEST_ASSERT(!memcmp(&regs.gprs, regs_null, sizeof(regs.gprs)), "grs == 0");
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(!memcmp(&sregs.acrs, regs_null, sizeof(sregs.acrs)), "acrs == 0");
+
+	vcpu_fpu_get(vm, VCPU_ID, &fpu);
+	TEST_ASSERT(!memcmp(&fpu.fprs, regs_null, sizeof(fpu.fprs)), "fprs == 0");
+}
+
+static void assert_initial(void)
+{
+	struct kvm_sregs sregs;
+	struct kvm_fpu fpu;
+
+	vcpu_sregs_get(vm, VCPU_ID, &sregs);
+	TEST_ASSERT(sregs.crs[0] == 0xE0UL, "cr0 == 0xE0");
+	TEST_ASSERT(sregs.crs[14] == 0xC2000000UL, "cr14 == 0xC2000000");
+	TEST_ASSERT(!memcmp(&sregs.crs[1], regs_null, sizeof(sregs.crs[1]) * 12),
+		    "cr1-13 == 0");
+	TEST_ASSERT(sregs.crs[15] == 0, "cr15 == 0");
+
+	vcpu_fpu_get(vm, VCPU_ID, &fpu);
+	TEST_ASSERT(!fpu.fpc, "fpc == 0");
+
+	test_one_reg(KVM_REG_S390_GBEA, 1);
+	test_one_reg(KVM_REG_S390_PP, 0);
+	test_one_reg(KVM_REG_S390_TODPR, 0);
+	test_one_reg(KVM_REG_S390_CPU_TIMER, 0);
+	test_one_reg(KVM_REG_S390_CLOCK_COMP, 0);
+}
+
+static void assert_normal(void)
+{
+	test_one_reg(KVM_REG_S390_PFTOKEN, KVM_S390_PFAULT_TOKEN_INVALID);
+	assert_noirq();
+}
+
+static void inject_irq(int cpu_id)
+{
+	struct kvm_s390_irq_state irq_state;
+	struct kvm_s390_irq *irq = &buf[0];
+	int irqs;
+
+	/* Inject IRQ */
+	irq_state.len = sizeof(struct kvm_s390_irq);
+	irq_state.buf = (unsigned long)buf;
+	irq->type = KVM_S390_INT_EMERGENCY;
+	irq->u.emerg.code = cpu_id;
+	irqs = _vcpu_ioctl(vm, cpu_id, KVM_S390_SET_IRQ_STATE, &irq_state);
+	TEST_ASSERT(irqs >= 0, "Error injecting EMERGENCY IRQ errno %d\n", errno);
+}
+
+static void test_normal(void)
+{
+	printf("Testing normal reset\n");
+	/* Create VM */
+	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
+	run = vcpu_state(vm, VCPU_ID);
+	regs = &run->s.regs;
+
+	vcpu_run(vm, VCPU_ID);
+
+	inject_irq(VCPU_ID);
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_S390_NORMAL_RESET, 0);
+	assert_normal();
+	kvm_vm_free(vm);
+}
+
+static void test_initial(void)
+{
+	printf("Testing initial reset\n");
+	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
+	run = vcpu_state(vm, VCPU_ID);
+	regs = &run->s.regs;
+
+	vcpu_run(vm, VCPU_ID);
+
+	inject_irq(VCPU_ID);
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_S390_INITIAL_RESET, 0);
+	assert_normal();
+	assert_initial();
+	kvm_vm_free(vm);
+}
+
+static void test_clear(void)
+{
+	printf("Testing clear reset\n");
+	vm = vm_create_default(VCPU_ID, 0, guest_code_initial);
+	run = vcpu_state(vm, VCPU_ID);
+	regs = &run->s.regs;
+
+	vcpu_run(vm, VCPU_ID);
+
+	inject_irq(VCPU_ID);
+
+	vcpu_ioctl(vm, VCPU_ID, KVM_S390_CLEAR_RESET, 0);
+	assert_normal();
+	assert_initial();
+	assert_clear();
+	kvm_vm_free(vm);
+}
+
+int main(int argc, char *argv[])
+{
+	setbuf(stdout, NULL);	/* Tell stdout not to buffer its content */
+
+	test_initial();
+	if (kvm_check_cap(KVM_CAP_S390_VCPU_RESETS)) {
+		test_normal();
+		test_clear();
+	}
+	return 0;
+}