blob: 4638303ba6a858793eded0e331b67aeea67db5d0 [file] [log] [blame]
// SPDX-License-Identifier: GPL-2.0
/*
* hosting IBM Z kernel virtual machines (s390x)
*
* Copyright IBM Corp. 2008, 2018
*
* Author(s): Carsten Otte <cotte@de.ibm.com>
* Christian Borntraeger <borntraeger@de.ibm.com>
* Heiko Carstens <heiko.carstens@de.ibm.com>
* Christian Ehrhardt <ehrhardt@de.ibm.com>
* Jason J. Herne <jjherne@us.ibm.com>
*/
#define KMSG_COMPONENT "kvm-s390"
#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
#include <linux/hrtimer.h>
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/mman.h>
#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/vmalloc.h>
#include <linux/bitmap.h>
#include <linux/sched/signal.h>
#include <linux/string.h>
#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
#include <asm/stp.h>
#include <asm/pgtable.h>
#include <asm/gmap.h>
#include <asm/nmi.h>
#include <asm/switch_to.h>
#include <asm/isc.h>
#include <asm/sclp.h>
#include <asm/cpacf.h>
#include <asm/timex.h>
#include <asm/ap.h>
#include "kvm-s390.h"
#include "gaccess.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
#include "trace-s390.h"
#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */
#define LOCAL_IRQS 32
#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
(KVM_MAX_VCPUS + LOCAL_IRQS))
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
#define VM_STAT(x) offsetof(struct kvm, stat.x), KVM_STAT_VM
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "userspace_handled", VCPU_STAT(exit_userspace) },
{ "exit_null", VCPU_STAT(exit_null) },
{ "exit_validity", VCPU_STAT(exit_validity) },
{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
{ "exit_external_request", VCPU_STAT(exit_external_request) },
{ "exit_io_request", VCPU_STAT(exit_io_request) },
{ "exit_external_interrupt", VCPU_STAT(exit_external_interrupt) },
{ "exit_instruction", VCPU_STAT(exit_instruction) },
{ "exit_pei", VCPU_STAT(exit_pei) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
{ "exit_operation_exception", VCPU_STAT(exit_operation_exception) },
{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
{ "halt_poll_invalid", VCPU_STAT(halt_poll_invalid) },
{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
{ "instruction_stctl", VCPU_STAT(instruction_stctl) },
{ "instruction_stctg", VCPU_STAT(instruction_stctg) },
{ "deliver_ckc", VCPU_STAT(deliver_ckc) },
{ "deliver_cputm", VCPU_STAT(deliver_cputm) },
{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
{ "deliver_external_call", VCPU_STAT(deliver_external_call) },
{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
{ "deliver_virtio", VCPU_STAT(deliver_virtio) },
{ "deliver_stop_signal", VCPU_STAT(deliver_stop_signal) },
{ "deliver_prefix_signal", VCPU_STAT(deliver_prefix_signal) },
{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
{ "deliver_program", VCPU_STAT(deliver_program) },
{ "deliver_io", VCPU_STAT(deliver_io) },
{ "deliver_machine_check", VCPU_STAT(deliver_machine_check) },
{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
{ "inject_ckc", VCPU_STAT(inject_ckc) },
{ "inject_cputm", VCPU_STAT(inject_cputm) },
{ "inject_external_call", VCPU_STAT(inject_external_call) },
{ "inject_float_mchk", VM_STAT(inject_float_mchk) },
{ "inject_emergency_signal", VCPU_STAT(inject_emergency_signal) },
{ "inject_io", VM_STAT(inject_io) },
{ "inject_mchk", VCPU_STAT(inject_mchk) },
{ "inject_pfault_done", VM_STAT(inject_pfault_done) },
{ "inject_program", VCPU_STAT(inject_program) },
{ "inject_restart", VCPU_STAT(inject_restart) },
{ "inject_service_signal", VM_STAT(inject_service_signal) },
{ "inject_set_prefix", VCPU_STAT(inject_set_prefix) },
{ "inject_stop_signal", VCPU_STAT(inject_stop_signal) },
{ "inject_pfault_init", VCPU_STAT(inject_pfault_init) },
{ "inject_virtio", VM_STAT(inject_virtio) },
{ "instruction_epsw", VCPU_STAT(instruction_epsw) },
{ "instruction_gs", VCPU_STAT(instruction_gs) },
{ "instruction_io_other", VCPU_STAT(instruction_io_other) },
{ "instruction_lpsw", VCPU_STAT(instruction_lpsw) },
{ "instruction_lpswe", VCPU_STAT(instruction_lpswe) },
{ "instruction_pfmf", VCPU_STAT(instruction_pfmf) },
{ "instruction_ptff", VCPU_STAT(instruction_ptff) },
{ "instruction_stidp", VCPU_STAT(instruction_stidp) },
{ "instruction_sck", VCPU_STAT(instruction_sck) },
{ "instruction_sckpf", VCPU_STAT(instruction_sckpf) },
{ "instruction_spx", VCPU_STAT(instruction_spx) },
{ "instruction_stpx", VCPU_STAT(instruction_stpx) },
{ "instruction_stap", VCPU_STAT(instruction_stap) },
{ "instruction_iske", VCPU_STAT(instruction_iske) },
{ "instruction_ri", VCPU_STAT(instruction_ri) },
{ "instruction_rrbe", VCPU_STAT(instruction_rrbe) },
{ "instruction_sske", VCPU_STAT(instruction_sske) },
{ "instruction_ipte_interlock", VCPU_STAT(instruction_ipte_interlock) },
{ "instruction_essa", VCPU_STAT(instruction_essa) },
{ "instruction_stsi", VCPU_STAT(instruction_stsi) },
{ "instruction_stfl", VCPU_STAT(instruction_stfl) },
{ "instruction_tb", VCPU_STAT(instruction_tb) },
{ "instruction_tpi", VCPU_STAT(instruction_tpi) },
{ "instruction_tprot", VCPU_STAT(instruction_tprot) },
{ "instruction_tsch", VCPU_STAT(instruction_tsch) },
{ "instruction_sthyi", VCPU_STAT(instruction_sthyi) },
{ "instruction_sie", VCPU_STAT(instruction_sie) },
{ "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
{ "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
{ "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
{ "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
{ "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
{ "instruction_sigp_store_adtl_status", VCPU_STAT(instruction_sigp_store_adtl_status) },
{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
{ "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
{ "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
{ "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
{ "instruction_diag_10", VCPU_STAT(diagnose_10) },
{ "instruction_diag_44", VCPU_STAT(diagnose_44) },
{ "instruction_diag_9c", VCPU_STAT(diagnose_9c) },
{ "instruction_diag_258", VCPU_STAT(diagnose_258) },
{ "instruction_diag_308", VCPU_STAT(diagnose_308) },
{ "instruction_diag_500", VCPU_STAT(diagnose_500) },
{ "instruction_diag_other", VCPU_STAT(diagnose_other) },
{ NULL }
};
struct kvm_s390_tod_clock_ext {
__u8 epoch_idx;
__u64 tod;
__u8 reserved[7];
} __packed;
/* allow nested virtualization in KVM (if enabled by user space) */
static int nested;
module_param(nested, int, S_IRUGO);
MODULE_PARM_DESC(nested, "Nested virtualization support");
/* allow 1m huge page guest backing, if !nested */
static int hpage;
module_param(hpage, int, 0444);
MODULE_PARM_DESC(hpage, "1m huge page backing support");
/*
* For now we handle at most 16 double words as this is what the s390 base
* kernel handles and stores in the prefix page. If we ever need to go beyond
* this, this requires changes to code, but the external uapi can stay.
*/
#define SIZE_INTERNAL 16
/*
* Base feature mask that defines default mask for facilities. Consists of the
* defines in FACILITIES_KVM and the non-hypervisor managed bits.
*/
static unsigned long kvm_s390_fac_base[SIZE_INTERNAL] = { FACILITIES_KVM };
/*
* Extended feature mask. Consists of the defines in FACILITIES_KVM_CPUMODEL
* and defines the facilities that can be enabled via a cpu model.
*/
static unsigned long kvm_s390_fac_ext[SIZE_INTERNAL] = { FACILITIES_KVM_CPUMODEL };
static unsigned long kvm_s390_fac_size(void)
{
BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_MASK_SIZE_U64);
BUILD_BUG_ON(SIZE_INTERNAL > S390_ARCH_FAC_LIST_SIZE_U64);
BUILD_BUG_ON(SIZE_INTERNAL * sizeof(unsigned long) >
sizeof(S390_lowcore.stfle_fac_list));
return SIZE_INTERNAL;
}
/* available cpu features supported by kvm */
static DECLARE_BITMAP(kvm_s390_available_cpu_feat, KVM_S390_VM_CPU_FEAT_NR_BITS);
/* available subfunctions indicated via query / "test bit" */
static struct kvm_s390_vm_cpu_subfunc kvm_s390_available_subfunc;
static struct gmap_notifier gmap_notifier;
static struct gmap_notifier vsie_gmap_notifier;
debug_info_t *kvm_s390_dbf;
/* Section: not file related */
int kvm_arch_hardware_enable(void)
{
/* every s390 is virtualization enabled ;-) */
return 0;
}
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
static void kvm_clock_sync_scb(struct kvm_s390_sie_block *scb, u64 delta)
{
u8 delta_idx = 0;
/*
* The TOD jumps by delta, we have to compensate this by adding
* -delta to the epoch.
*/
delta = -delta;
/* sign-extension - we're adding to signed values below */
if ((s64)delta < 0)
delta_idx = -1;
scb->epoch += delta;
if (scb->ecd & ECD_MEF) {
scb->epdx += delta_idx;
if (scb->epoch < delta)
scb->epdx += 1;
}
}
/*
* This callback is executed during stop_machine(). All CPUs are therefore
* temporarily stopped. In order not to change guest behavior, we have to
* disable preemption whenever we touch the epoch of kvm and the VCPUs,
* so a CPU won't be stopped while calculating with the epoch.
*/
static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
void *v)
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
int i;
unsigned long long *delta = v;
list_for_each_entry(kvm, &vm_list, vm_list) {
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_clock_sync_scb(vcpu->arch.sie_block, *delta);
if (i == 0) {
kvm->arch.epoch = vcpu->arch.sie_block->epoch;
kvm->arch.epdx = vcpu->arch.sie_block->epdx;
}
if (vcpu->arch.cputm_enabled)
vcpu->arch.cputm_start += *delta;
if (vcpu->arch.vsie_block)
kvm_clock_sync_scb(vcpu->arch.vsie_block,
*delta);
}
}
return NOTIFY_OK;
}
static struct notifier_block kvm_clock_notifier = {
.notifier_call = kvm_clock_sync,
};
int kvm_arch_hardware_setup(void)
{
gmap_notifier.notifier_call = kvm_gmap_notifier;
gmap_register_pte_notifier(&gmap_notifier);
vsie_gmap_notifier.notifier_call = kvm_s390_vsie_gmap_notifier;
gmap_register_pte_notifier(&vsie_gmap_notifier);
atomic_notifier_chain_register(&s390_epoch_delta_notifier,
&kvm_clock_notifier);
return 0;
}
void kvm_arch_hardware_unsetup(void)
{
gmap_unregister_pte_notifier(&gmap_notifier);
gmap_unregister_pte_notifier(&vsie_gmap_notifier);
atomic_notifier_chain_unregister(&s390_epoch_delta_notifier,
&kvm_clock_notifier);
}
static void allow_cpu_feat(unsigned long nr)
{
set_bit_inv(nr, kvm_s390_available_cpu_feat);
}
static inline int plo_test_bit(unsigned char nr)
{
register unsigned long r0 asm("0") = (unsigned long) nr | 0x100;
int cc;
asm volatile(
/* Parameter registers are ignored for "test bit" */
" plo 0,0,0,0(0)\n"
" ipm %0\n"
" srl %0,28\n"
: "=d" (cc)
: "d" (r0)
: "cc");
return cc == 0;
}
static void kvm_s390_cpu_feat_init(void)
{
int i;
for (i = 0; i < 256; ++i) {
if (plo_test_bit(i))
kvm_s390_available_subfunc.plo[i >> 3] |= 0x80 >> (i & 7);
}
if (test_facility(28)) /* TOD-clock steering */
ptff(kvm_s390_available_subfunc.ptff,
sizeof(kvm_s390_available_subfunc.ptff),
PTFF_QAF);
if (test_facility(17)) { /* MSA */
__cpacf_query(CPACF_KMAC, (cpacf_mask_t *)
kvm_s390_available_subfunc.kmac);
__cpacf_query(CPACF_KMC, (cpacf_mask_t *)
kvm_s390_available_subfunc.kmc);
__cpacf_query(CPACF_KM, (cpacf_mask_t *)
kvm_s390_available_subfunc.km);
__cpacf_query(CPACF_KIMD, (cpacf_mask_t *)
kvm_s390_available_subfunc.kimd);
__cpacf_query(CPACF_KLMD, (cpacf_mask_t *)
kvm_s390_available_subfunc.klmd);
}
if (test_facility(76)) /* MSA3 */
__cpacf_query(CPACF_PCKMO, (cpacf_mask_t *)
kvm_s390_available_subfunc.pckmo);
if (test_facility(77)) { /* MSA4 */
__cpacf_query(CPACF_KMCTR, (cpacf_mask_t *)
kvm_s390_available_subfunc.kmctr);
__cpacf_query(CPACF_KMF, (cpacf_mask_t *)
kvm_s390_available_subfunc.kmf);
__cpacf_query(CPACF_KMO, (cpacf_mask_t *)
kvm_s390_available_subfunc.kmo);
__cpacf_query(CPACF_PCC, (cpacf_mask_t *)
kvm_s390_available_subfunc.pcc);
}
if (test_facility(57)) /* MSA5 */
__cpacf_query(CPACF_PRNO, (cpacf_mask_t *)
kvm_s390_available_subfunc.ppno);
if (test_facility(146)) /* MSA8 */
__cpacf_query(CPACF_KMA, (cpacf_mask_t *)
kvm_s390_available_subfunc.kma);
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 ||
!test_facility(3) || !nested)
return;
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIEF2);
if (sclp.has_64bscao)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_64BSCAO);
if (sclp.has_siif)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_SIIF);
if (sclp.has_gpere)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GPERE);
if (sclp.has_gsls)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_GSLS);
if (sclp.has_ib)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IB);
if (sclp.has_cei)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_CEI);
if (sclp.has_ibs)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_IBS);
if (sclp.has_kss)
allow_cpu_feat(KVM_S390_VM_CPU_FEAT_KSS);
/*
* KVM_S390_VM_CPU_FEAT_SKEY: Wrong shadow of PTE.I bits will make
* all skey handling functions read/set the skey from the PGSTE
* instead of the real storage key.
*
* KVM_S390_VM_CPU_FEAT_CMMA: Wrong shadow of PTE.I bits will make
* pages being detected as preserved although they are resident.
*
* KVM_S390_VM_CPU_FEAT_PFMFI: Wrong shadow of PTE.I bits will
* have the same effect as for KVM_S390_VM_CPU_FEAT_SKEY.
*
* For KVM_S390_VM_CPU_FEAT_SKEY, KVM_S390_VM_CPU_FEAT_CMMA and
* KVM_S390_VM_CPU_FEAT_PFMFI, all PTE.I and PGSTE bits have to be
* correctly shadowed. We can do that for the PGSTE but not for PTE.I.
*
* KVM_S390_VM_CPU_FEAT_SIGPIF: Wrong SCB addresses in the SCA. We
* cannot easily shadow the SCA because of the ipte lock.
*/
}
int kvm_arch_init(void *opaque)
{
int rc;
kvm_s390_dbf = debug_register("kvm-trace", 32, 1, 7 * sizeof(long));
if (!kvm_s390_dbf)
return -ENOMEM;
if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view)) {
rc = -ENOMEM;
goto out_debug_unreg;
}
kvm_s390_cpu_feat_init();
/* Register floating interrupt controller interface. */
rc = kvm_register_device_ops(&kvm_flic_ops, KVM_DEV_TYPE_FLIC);
if (rc) {
pr_err("A FLIC registration call failed with rc=%d\n", rc);
goto out_debug_unreg;
}
rc = kvm_s390_gib_init(GAL_ISC);
if (rc)
goto out_gib_destroy;
return 0;
out_gib_destroy:
kvm_s390_gib_destroy();
out_debug_unreg:
debug_unregister(kvm_s390_dbf);
return rc;
}
void kvm_arch_exit(void)
{
kvm_s390_gib_destroy();
debug_unregister(kvm_s390_dbf);
}
/* Section: device related */
long kvm_arch_dev_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
if (ioctl == KVM_S390_ENABLE_SIE)
return s390_enable_sie();
return -EINVAL;
}
int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
{
int r;
switch (ext) {
case KVM_CAP_S390_PSW:
case KVM_CAP_S390_GMAP:
case KVM_CAP_SYNC_MMU:
#ifdef CONFIG_KVM_S390_UCONTROL
case KVM_CAP_S390_UCONTROL:
#endif
case KVM_CAP_ASYNC_PF:
case KVM_CAP_SYNC_REGS:
case KVM_CAP_ONE_REG:
case KVM_CAP_ENABLE_CAP:
case KVM_CAP_S390_CSS_SUPPORT:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_S390_IRQCHIP:
case KVM_CAP_VM_ATTRIBUTES:
case KVM_CAP_MP_STATE:
case KVM_CAP_IMMEDIATE_EXIT:
case KVM_CAP_S390_INJECT_IRQ:
case KVM_CAP_S390_USER_SIGP:
case KVM_CAP_S390_USER_STSI:
case KVM_CAP_S390_SKEYS:
case KVM_CAP_S390_IRQ_STATE:
case KVM_CAP_S390_USER_INSTR0:
case KVM_CAP_S390_CMMA_MIGRATION:
case KVM_CAP_S390_AIS:
case KVM_CAP_S390_AIS_MIGRATION:
r = 1;
break;
case KVM_CAP_S390_HPAGE_1M:
r = 0;
if (hpage && !kvm_is_ucontrol(kvm))
r = 1;
break;
case KVM_CAP_S390_MEM_OP:
r = MEM_OP_MAX_SIZE;
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
r = KVM_S390_BSCA_CPU_SLOTS;
if (!kvm_s390_use_sca_entries())
r = KVM_MAX_VCPUS;
else if (sclp.has_esca && sclp.has_64bscao)
r = KVM_S390_ESCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
break;
case KVM_CAP_S390_COW:
r = MACHINE_HAS_ESOP;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
r = MACHINE_HAS_VX;
break;
case KVM_CAP_S390_RI:
r = test_facility(64);
break;
case KVM_CAP_S390_GS:
r = test_facility(133);
break;
case KVM_CAP_S390_BPB:
r = test_facility(82);
break;
default:
r = 0;
}
return r;
}
static void kvm_s390_sync_dirty_log(struct kvm *kvm,
struct kvm_memory_slot *memslot)
{
int i;
gfn_t cur_gfn, last_gfn;
unsigned long gaddr, vmaddr;
struct gmap *gmap = kvm->arch.gmap;
DECLARE_BITMAP(bitmap, _PAGE_ENTRIES);
/* Loop over all guest segments */
cur_gfn = memslot->base_gfn;
last_gfn = memslot->base_gfn + memslot->npages;
for (; cur_gfn <= last_gfn; cur_gfn += _PAGE_ENTRIES) {
gaddr = gfn_to_gpa(cur_gfn);
vmaddr = gfn_to_hva_memslot(memslot, cur_gfn);
if (kvm_is_error_hva(vmaddr))
continue;
bitmap_zero(bitmap, _PAGE_ENTRIES);
gmap_sync_dirty_log_pmd(gmap, bitmap, gaddr, vmaddr);
for (i = 0; i < _PAGE_ENTRIES; i++) {
if (test_bit(i, bitmap))
mark_page_dirty(kvm, cur_gfn + i);
}
if (fatal_signal_pending(current))
return;
cond_resched();
}
}
/* Section: vm related */
static void sca_del_vcpu(struct kvm_vcpu *vcpu);
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm,
struct kvm_dirty_log *log)
{
int r;
unsigned long n;
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int is_dirty = 0;
if (kvm_is_ucontrol(kvm))
return -EINVAL;
mutex_lock(&kvm->slots_lock);
r = -EINVAL;
if (log->slot >= KVM_USER_MEM_SLOTS)
goto out;
slots = kvm_memslots(kvm);
memslot = id_to_memslot(slots, log->slot);
r = -ENOENT;
if (!memslot->dirty_bitmap)
goto out;
kvm_s390_sync_dirty_log(kvm, memslot);
r = kvm_get_dirty_log(kvm, log, &is_dirty);
if (r)
goto out;
/* Clear the dirty log */
if (is_dirty) {
n = kvm_dirty_bitmap_bytes(memslot);
memset(memslot->dirty_bitmap, 0, n);
}
r = 0;
out:
mutex_unlock(&kvm->slots_lock);
return r;
}
static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
{
unsigned int i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_s390_sync_request(KVM_REQ_ICPT_OPEREXC, vcpu);
}
}
int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
{
int r;
if (cap->flags)
return -EINVAL;
switch (cap->cap) {
case KVM_CAP_S390_IRQCHIP:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_IRQCHIP");
kvm->arch.use_irqchip = 1;
r = 0;
break;
case KVM_CAP_S390_USER_SIGP:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_SIGP");
kvm->arch.user_sigp = 1;
r = 0;
break;
case KVM_CAP_S390_VECTOR_REGISTERS:
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
r = -EBUSY;
} else if (MACHINE_HAS_VX) {
set_kvm_facility(kvm->arch.model.fac_mask, 129);
set_kvm_facility(kvm->arch.model.fac_list, 129);
if (test_facility(134)) {
set_kvm_facility(kvm->arch.model.fac_mask, 134);
set_kvm_facility(kvm->arch.model.fac_list, 134);
}
if (test_facility(135)) {
set_kvm_facility(kvm->arch.model.fac_mask, 135);
set_kvm_facility(kvm->arch.model.fac_list, 135);
}
r = 0;
} else
r = -EINVAL;
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
r ? "(not available)" : "(success)");
break;
case KVM_CAP_S390_RI:
r = -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
r = -EBUSY;
} else if (test_facility(64)) {
set_kvm_facility(kvm->arch.model.fac_mask, 64);
set_kvm_facility(kvm->arch.model.fac_list, 64);
r = 0;
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
r ? "(not available)" : "(success)");
break;
case KVM_CAP_S390_AIS:
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
r = -EBUSY;
} else {
set_kvm_facility(kvm->arch.model.fac_mask, 72);
set_kvm_facility(kvm->arch.model.fac_list, 72);
r = 0;
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: AIS %s",
r ? "(not available)" : "(success)");
break;
case KVM_CAP_S390_GS:
r = -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
r = -EBUSY;
} else if (test_facility(133)) {
set_kvm_facility(kvm->arch.model.fac_mask, 133);
set_kvm_facility(kvm->arch.model.fac_list, 133);
r = 0;
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_GS %s",
r ? "(not available)" : "(success)");
break;
case KVM_CAP_S390_HPAGE_1M:
mutex_lock(&kvm->lock);
if (kvm->created_vcpus)
r = -EBUSY;
else if (!hpage || kvm->arch.use_cmma || kvm_is_ucontrol(kvm))
r = -EINVAL;
else {
r = 0;
down_write(&kvm->mm->mmap_sem);
kvm->mm->context.allow_gmap_hpage_1m = 1;
up_write(&kvm->mm->mmap_sem);
/*
* We might have to create fake 4k page
* tables. To avoid that the hardware works on
* stale PGSTEs, we emulate these instructions.
*/
kvm->arch.use_skf = 0;
kvm->arch.use_pfmfi = 0;
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_HPAGE %s",
r ? "(not available)" : "(success)");
break;
case KVM_CAP_S390_USER_STSI:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
kvm->arch.user_stsi = 1;
r = 0;
break;
case KVM_CAP_S390_USER_INSTR0:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_INSTR0");
kvm->arch.user_instr0 = 1;
icpt_operexc_on_all_vcpus(kvm);
r = 0;
break;
default:
r = -EINVAL;
break;
}
return r;
}
static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
switch (attr->attr) {
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
kvm->arch.mem_limit);
if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
ret = -EFAULT;
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
unsigned int idx;
switch (attr->attr) {
case KVM_S390_VM_MEM_ENABLE_CMMA:
ret = -ENXIO;
if (!sclp.has_cmma)
break;
VM_EVENT(kvm, 3, "%s", "ENABLE: CMMA support");
mutex_lock(&kvm->lock);
if (kvm->created_vcpus)
ret = -EBUSY;
else if (kvm->mm->context.allow_gmap_hpage_1m)
ret = -EINVAL;
else {
kvm->arch.use_cmma = 1;
/* Not compatible with cmma. */
kvm->arch.use_pfmfi = 0;
ret = 0;
}
mutex_unlock(&kvm->lock);
break;
case KVM_S390_VM_MEM_CLR_CMMA:
ret = -ENXIO;
if (!sclp.has_cmma)
break;
ret = -EINVAL;
if (!kvm->arch.use_cmma)
break;
VM_EVENT(kvm, 3, "%s", "RESET: CMMA states");
mutex_lock(&kvm->lock);
idx = srcu_read_lock(&kvm->srcu);
s390_reset_cmma(kvm->arch.gmap->mm);
srcu_read_unlock(&kvm->srcu, idx);
mutex_unlock(&kvm->lock);
ret = 0;
break;
case KVM_S390_VM_MEM_LIMIT_SIZE: {
unsigned long new_limit;
if (kvm_is_ucontrol(kvm))
return -EINVAL;
if (get_user(new_limit, (u64 __user *)attr->addr))
return -EFAULT;
if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
new_limit > kvm->arch.mem_limit)
return -E2BIG;
if (!new_limit)
return -EINVAL;
/* gmap_create takes last usable address */
if (new_limit != KVM_S390_NO_MEM_LIMIT)
new_limit -= 1;
ret = -EBUSY;
mutex_lock(&kvm->lock);
if (!kvm->created_vcpus) {
/* gmap_create will round the limit up */
struct gmap *new = gmap_create(current->mm, new_limit);
if (!new) {
ret = -ENOMEM;
} else {
gmap_remove(kvm->arch.gmap);
new->private = kvm;
kvm->arch.gmap = new;
ret = 0;
}
}
mutex_unlock(&kvm->lock);
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:
ret = -ENXIO;
break;
}
return ret;
}
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu);
void kvm_s390_vcpu_crypto_reset_all(struct kvm *kvm)
{
struct kvm_vcpu *vcpu;
int i;
kvm_s390_vcpu_block_all(kvm);
kvm_for_each_vcpu(i, vcpu, kvm) {
kvm_s390_vcpu_crypto_setup(vcpu);
/* recreate the shadow crycb by leaving the VSIE handler */
kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
}
kvm_s390_vcpu_unblock_all(kvm);
}
static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
{
mutex_lock(&kvm->lock);
switch (attr->attr) {
case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
if (!test_kvm_facility(kvm, 76)) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
get_random_bytes(
kvm->arch.crypto.crycb->aes_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
kvm->arch.crypto.aes_kw = 1;
VM_EVENT(kvm, 3, "%s", "ENABLE: AES keywrapping support");
break;
case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
if (!test_kvm_facility(kvm, 76)) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
get_random_bytes(
kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
kvm->arch.crypto.dea_kw = 1;
VM_EVENT(kvm, 3, "%s", "ENABLE: DEA keywrapping support");
break;
case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
if (!test_kvm_facility(kvm, 76)) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
kvm->arch.crypto.aes_kw = 0;
memset(kvm->arch.crypto.crycb->aes_wrapping_key_mask, 0,
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
VM_EVENT(kvm, 3, "%s", "DISABLE: AES keywrapping support");
break;
case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
if (!test_kvm_facility(kvm, 76)) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
kvm->arch.crypto.dea_kw = 0;
memset(kvm->arch.crypto.crycb->dea_wrapping_key_mask, 0,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
VM_EVENT(kvm, 3, "%s", "DISABLE: DEA keywrapping support");
break;
case KVM_S390_VM_CRYPTO_ENABLE_APIE:
if (!ap_instructions_available()) {
mutex_unlock(&kvm->lock);
return -EOPNOTSUPP;
}
kvm->arch.crypto.apie = 1;
break;
case KVM_S390_VM_CRYPTO_DISABLE_APIE:
if (!ap_instructions_available()) {
mutex_unlock(&kvm->lock);
return -EOPNOTSUPP;
}
kvm->arch.crypto.apie = 0;
break;
default:
mutex_unlock(&kvm->lock);
return -ENXIO;
}
kvm_s390_vcpu_crypto_reset_all(kvm);
mutex_unlock(&kvm->lock);
return 0;
}
static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
{
int cx;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(cx, vcpu, kvm)
kvm_s390_sync_request(req, vcpu);
}
/*
* Must be called with kvm->srcu held to avoid races on memslots, and with
* kvm->slots_lock to avoid races with ourselves and kvm_s390_vm_stop_migration.
*/
static int kvm_s390_vm_start_migration(struct kvm *kvm)
{
struct kvm_memory_slot *ms;
struct kvm_memslots *slots;
unsigned long ram_pages = 0;
int slotnr;
/* migration mode already enabled */
if (kvm->arch.migration_mode)
return 0;
slots = kvm_memslots(kvm);
if (!slots || !slots->used_slots)
return -EINVAL;
if (!kvm->arch.use_cmma) {
kvm->arch.migration_mode = 1;
return 0;
}
/* mark all the pages in active slots as dirty */
for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
ms = slots->memslots + slotnr;
/*
* The second half of the bitmap is only used on x86,
* and would be wasted otherwise, so we put it to good
* use here to keep track of the state of the storage
* attributes.
*/
memset(kvm_second_dirty_bitmap(ms), 0xff, kvm_dirty_bitmap_bytes(ms));
ram_pages += ms->npages;
}
atomic64_set(&kvm->arch.cmma_dirty_pages, ram_pages);
kvm->arch.migration_mode = 1;
kvm_s390_sync_request_broadcast(kvm, KVM_REQ_START_MIGRATION);
return 0;
}
/*
* Must be called with kvm->slots_lock to avoid races with ourselves and
* kvm_s390_vm_start_migration.
*/
static int kvm_s390_vm_stop_migration(struct kvm *kvm)
{
/* migration mode already disabled */
if (!kvm->arch.migration_mode)
return 0;
kvm->arch.migration_mode = 0;
if (kvm->arch.use_cmma)
kvm_s390_sync_request_broadcast(kvm, KVM_REQ_STOP_MIGRATION);
return 0;
}
static int kvm_s390_vm_set_migration(struct kvm *kvm,
struct kvm_device_attr *attr)
{
int res = -ENXIO;
mutex_lock(&kvm->slots_lock);
switch (attr->attr) {
case KVM_S390_VM_MIGRATION_START:
res = kvm_s390_vm_start_migration(kvm);
break;
case KVM_S390_VM_MIGRATION_STOP:
res = kvm_s390_vm_stop_migration(kvm);
break;
default:
break;
}
mutex_unlock(&kvm->slots_lock);
return res;
}
static int kvm_s390_vm_get_migration(struct kvm *kvm,
struct kvm_device_attr *attr)
{
u64 mig = kvm->arch.migration_mode;
if (attr->attr != KVM_S390_VM_MIGRATION_STATUS)
return -ENXIO;
if (copy_to_user((void __user *)attr->addr, &mig, sizeof(mig)))
return -EFAULT;
return 0;
}
static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_tod_clock gtod;
if (copy_from_user(&gtod, (void __user *)attr->addr, sizeof(gtod)))
return -EFAULT;
if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
return -EINVAL;
kvm_s390_set_tod_clock(kvm, &gtod);
VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x, TOD base: 0x%llx",
gtod.epoch_idx, gtod.tod);
return 0;
}
static int kvm_s390_set_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
u8 gtod_high;
if (copy_from_user(&gtod_high, (void __user *)attr->addr,
sizeof(gtod_high)))
return -EFAULT;
if (gtod_high != 0)
return -EINVAL;
VM_EVENT(kvm, 3, "SET: TOD extension: 0x%x", gtod_high);
return 0;
}
static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_tod_clock gtod = { 0 };
if (copy_from_user(&gtod.tod, (void __user *)attr->addr,
sizeof(gtod.tod)))
return -EFAULT;
kvm_s390_set_tod_clock(kvm, &gtod);
VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
return 0;
}
static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
if (attr->flags)
return -EINVAL;
switch (attr->attr) {
case KVM_S390_VM_TOD_EXT:
ret = kvm_s390_set_tod_ext(kvm, attr);
break;
case KVM_S390_VM_TOD_HIGH:
ret = kvm_s390_set_tod_high(kvm, attr);
break;
case KVM_S390_VM_TOD_LOW:
ret = kvm_s390_set_tod_low(kvm, attr);
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static void kvm_s390_get_tod_clock(struct kvm *kvm,
struct kvm_s390_vm_tod_clock *gtod)
{
struct kvm_s390_tod_clock_ext htod;
preempt_disable();
get_tod_clock_ext((char *)&htod);
gtod->tod = htod.tod + kvm->arch.epoch;
gtod->epoch_idx = 0;
if (test_kvm_facility(kvm, 139)) {
gtod->epoch_idx = htod.epoch_idx + kvm->arch.epdx;
if (gtod->tod < htod.tod)
gtod->epoch_idx += 1;
}
preempt_enable();
}
static int kvm_s390_get_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_tod_clock gtod;
memset(&gtod, 0, sizeof(gtod));
kvm_s390_get_tod_clock(kvm, &gtod);
if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
return -EFAULT;
VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x, TOD base: 0x%llx",
gtod.epoch_idx, gtod.tod);
return 0;
}
static int kvm_s390_get_tod_high(struct kvm *kvm, struct kvm_device_attr *attr)
{
u8 gtod_high = 0;
if (copy_to_user((void __user *)attr->addr, &gtod_high,
sizeof(gtod_high)))
return -EFAULT;
VM_EVENT(kvm, 3, "QUERY: TOD extension: 0x%x", gtod_high);
return 0;
}
static int kvm_s390_get_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
{
u64 gtod;
gtod = kvm_s390_get_tod_clock_fast(kvm);
if (copy_to_user((void __user *)attr->addr, &gtod, sizeof(gtod)))
return -EFAULT;
VM_EVENT(kvm, 3, "QUERY: TOD base: 0x%llx", gtod);
return 0;
}
static int kvm_s390_get_tod(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
if (attr->flags)
return -EINVAL;
switch (attr->attr) {
case KVM_S390_VM_TOD_EXT:
ret = kvm_s390_get_tod_ext(kvm, attr);
break;
case KVM_S390_VM_TOD_HIGH:
ret = kvm_s390_get_tod_high(kvm, attr);
break;
case KVM_S390_VM_TOD_LOW:
ret = kvm_s390_get_tod_low(kvm, attr);
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static int kvm_s390_set_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_processor *proc;
u16 lowest_ibc, unblocked_ibc;
int ret = 0;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
ret = -EBUSY;
goto out;
}
proc = kzalloc(sizeof(*proc), GFP_KERNEL);
if (!proc) {
ret = -ENOMEM;
goto out;
}
if (!copy_from_user(proc, (void __user *)attr->addr,
sizeof(*proc))) {
kvm->arch.model.cpuid = proc->cpuid;
lowest_ibc = sclp.ibc >> 16 & 0xfff;
unblocked_ibc = sclp.ibc & 0xfff;
if (lowest_ibc && proc->ibc) {
if (proc->ibc > unblocked_ibc)
kvm->arch.model.ibc = unblocked_ibc;
else if (proc->ibc < lowest_ibc)
kvm->arch.model.ibc = lowest_ibc;
else
kvm->arch.model.ibc = proc->ibc;
}
memcpy(kvm->arch.model.fac_list, proc->fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
VM_EVENT(kvm, 3, "SET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
kvm->arch.model.ibc,
kvm->arch.model.cpuid);
VM_EVENT(kvm, 3, "SET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
kvm->arch.model.fac_list[0],
kvm->arch.model.fac_list[1],
kvm->arch.model.fac_list[2]);
} else
ret = -EFAULT;
kfree(proc);
out:
mutex_unlock(&kvm->lock);
return ret;
}
static int kvm_s390_set_processor_feat(struct kvm *kvm,
struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_feat data;
if (copy_from_user(&data, (void __user *)attr->addr, sizeof(data)))
return -EFAULT;
if (!bitmap_subset((unsigned long *) data.feat,
kvm_s390_available_cpu_feat,
KVM_S390_VM_CPU_FEAT_NR_BITS))
return -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
mutex_unlock(&kvm->lock);
return -EBUSY;
}
bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
KVM_S390_VM_CPU_FEAT_NR_BITS);
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "SET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
data.feat[0],
data.feat[1],
data.feat[2]);
return 0;
}
static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
struct kvm_device_attr *attr)
{
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
mutex_unlock(&kvm->lock);
return -EBUSY;
}
if (copy_from_user(&kvm->arch.model.subfuncs, (void __user *)attr->addr,
sizeof(struct kvm_s390_vm_cpu_subfunc))) {
mutex_unlock(&kvm->lock);
return -EFAULT;
}
mutex_unlock(&kvm->lock);
VM_EVENT(kvm, 3, "SET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.plo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[1],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[2],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]);
VM_EVENT(kvm, 3, "SET: guest PTFF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0],
((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]);
VM_EVENT(kvm, 3, "SET: guest KMAC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]);
VM_EVENT(kvm, 3, "SET: guest KMC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]);
VM_EVENT(kvm, 3, "SET: guest KM subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.km)[0],
((unsigned long *) &kvm->arch.model.subfuncs.km)[1]);
VM_EVENT(kvm, 3, "SET: guest KIMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]);
VM_EVENT(kvm, 3, "SET: guest KLMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0],
((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]);
VM_EVENT(kvm, 3, "SET: guest PCKMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]);
VM_EVENT(kvm, 3, "SET: guest KMCTR subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]);
VM_EVENT(kvm, 3, "SET: guest KMF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]);
VM_EVENT(kvm, 3, "SET: guest KMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]);
VM_EVENT(kvm, 3, "SET: guest PCC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0],
((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]);
VM_EVENT(kvm, 3, "SET: guest PPNO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0],
((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]);
VM_EVENT(kvm, 3, "SET: guest KMA subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
return 0;
}
static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret = -ENXIO;
switch (attr->attr) {
case KVM_S390_VM_CPU_PROCESSOR:
ret = kvm_s390_set_processor(kvm, attr);
break;
case KVM_S390_VM_CPU_PROCESSOR_FEAT:
ret = kvm_s390_set_processor_feat(kvm, attr);
break;
case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
ret = kvm_s390_set_processor_subfunc(kvm, attr);
break;
}
return ret;
}
static int kvm_s390_get_processor(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_processor *proc;
int ret = 0;
proc = kzalloc(sizeof(*proc), GFP_KERNEL);
if (!proc) {
ret = -ENOMEM;
goto out;
}
proc->cpuid = kvm->arch.model.cpuid;
proc->ibc = kvm->arch.model.ibc;
memcpy(&proc->fac_list, kvm->arch.model.fac_list,
S390_ARCH_FAC_LIST_SIZE_BYTE);
VM_EVENT(kvm, 3, "GET: guest ibc: 0x%4.4x, guest cpuid: 0x%16.16llx",
kvm->arch.model.ibc,
kvm->arch.model.cpuid);
VM_EVENT(kvm, 3, "GET: guest faclist: 0x%16.16llx.%16.16llx.%16.16llx",
kvm->arch.model.fac_list[0],
kvm->arch.model.fac_list[1],
kvm->arch.model.fac_list[2]);
if (copy_to_user((void __user *)attr->addr, proc, sizeof(*proc)))
ret = -EFAULT;
kfree(proc);
out:
return ret;
}
static int kvm_s390_get_machine(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_machine *mach;
int ret = 0;
mach = kzalloc(sizeof(*mach), GFP_KERNEL);
if (!mach) {
ret = -ENOMEM;
goto out;
}
get_cpu_id((struct cpuid *) &mach->cpuid);
mach->ibc = sclp.ibc;
memcpy(&mach->fac_mask, kvm->arch.model.fac_mask,
S390_ARCH_FAC_LIST_SIZE_BYTE);
memcpy((unsigned long *)&mach->fac_list, S390_lowcore.stfle_fac_list,
sizeof(S390_lowcore.stfle_fac_list));
VM_EVENT(kvm, 3, "GET: host ibc: 0x%4.4x, host cpuid: 0x%16.16llx",
kvm->arch.model.ibc,
kvm->arch.model.cpuid);
VM_EVENT(kvm, 3, "GET: host facmask: 0x%16.16llx.%16.16llx.%16.16llx",
mach->fac_mask[0],
mach->fac_mask[1],
mach->fac_mask[2]);
VM_EVENT(kvm, 3, "GET: host faclist: 0x%16.16llx.%16.16llx.%16.16llx",
mach->fac_list[0],
mach->fac_list[1],
mach->fac_list[2]);
if (copy_to_user((void __user *)attr->addr, mach, sizeof(*mach)))
ret = -EFAULT;
kfree(mach);
out:
return ret;
}
static int kvm_s390_get_processor_feat(struct kvm *kvm,
struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_feat data;
bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
VM_EVENT(kvm, 3, "GET: guest feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
data.feat[0],
data.feat[1],
data.feat[2]);
return 0;
}
static int kvm_s390_get_machine_feat(struct kvm *kvm,
struct kvm_device_attr *attr)
{
struct kvm_s390_vm_cpu_feat data;
bitmap_copy((unsigned long *) data.feat,
kvm_s390_available_cpu_feat,
KVM_S390_VM_CPU_FEAT_NR_BITS);
if (copy_to_user((void __user *)attr->addr, &data, sizeof(data)))
return -EFAULT;
VM_EVENT(kvm, 3, "GET: host feat: 0x%16.16llx.0x%16.16llx.0x%16.16llx",
data.feat[0],
data.feat[1],
data.feat[2]);
return 0;
}
static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
struct kvm_device_attr *attr)
{
if (copy_to_user((void __user *)attr->addr, &kvm->arch.model.subfuncs,
sizeof(struct kvm_s390_vm_cpu_subfunc)))
return -EFAULT;
VM_EVENT(kvm, 3, "GET: guest PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.plo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[1],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[2],
((unsigned long *) &kvm->arch.model.subfuncs.plo)[3]);
VM_EVENT(kvm, 3, "GET: guest PTFF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.ptff)[0],
((unsigned long *) &kvm->arch.model.subfuncs.ptff)[1]);
VM_EVENT(kvm, 3, "GET: guest KMAC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmac)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmac)[1]);
VM_EVENT(kvm, 3, "GET: guest KMC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmc)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmc)[1]);
VM_EVENT(kvm, 3, "GET: guest KM subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.km)[0],
((unsigned long *) &kvm->arch.model.subfuncs.km)[1]);
VM_EVENT(kvm, 3, "GET: guest KIMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kimd)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kimd)[1]);
VM_EVENT(kvm, 3, "GET: guest KLMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.klmd)[0],
((unsigned long *) &kvm->arch.model.subfuncs.klmd)[1]);
VM_EVENT(kvm, 3, "GET: guest PCKMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.pckmo)[1]);
VM_EVENT(kvm, 3, "GET: guest KMCTR subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmctr)[1]);
VM_EVENT(kvm, 3, "GET: guest KMF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmf)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmf)[1]);
VM_EVENT(kvm, 3, "GET: guest KMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kmo)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kmo)[1]);
VM_EVENT(kvm, 3, "GET: guest PCC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.pcc)[0],
((unsigned long *) &kvm->arch.model.subfuncs.pcc)[1]);
VM_EVENT(kvm, 3, "GET: guest PPNO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.ppno)[0],
((unsigned long *) &kvm->arch.model.subfuncs.ppno)[1]);
VM_EVENT(kvm, 3, "GET: guest KMA subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm->arch.model.subfuncs.kma)[0],
((unsigned long *) &kvm->arch.model.subfuncs.kma)[1]);
return 0;
}
static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
struct kvm_device_attr *attr)
{
if (copy_to_user((void __user *)attr->addr, &kvm_s390_available_subfunc,
sizeof(struct kvm_s390_vm_cpu_subfunc)))
return -EFAULT;
VM_EVENT(kvm, 3, "GET: host PLO subfunc 0x%16.16lx.%16.16lx.%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.plo)[0],
((unsigned long *) &kvm_s390_available_subfunc.plo)[1],
((unsigned long *) &kvm_s390_available_subfunc.plo)[2],
((unsigned long *) &kvm_s390_available_subfunc.plo)[3]);
VM_EVENT(kvm, 3, "GET: host PTFF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.ptff)[0],
((unsigned long *) &kvm_s390_available_subfunc.ptff)[1]);
VM_EVENT(kvm, 3, "GET: host KMAC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kmac)[0],
((unsigned long *) &kvm_s390_available_subfunc.kmac)[1]);
VM_EVENT(kvm, 3, "GET: host KMC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kmc)[0],
((unsigned long *) &kvm_s390_available_subfunc.kmc)[1]);
VM_EVENT(kvm, 3, "GET: host KM subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.km)[0],
((unsigned long *) &kvm_s390_available_subfunc.km)[1]);
VM_EVENT(kvm, 3, "GET: host KIMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kimd)[0],
((unsigned long *) &kvm_s390_available_subfunc.kimd)[1]);
VM_EVENT(kvm, 3, "GET: host KLMD subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.klmd)[0],
((unsigned long *) &kvm_s390_available_subfunc.klmd)[1]);
VM_EVENT(kvm, 3, "GET: host PCKMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.pckmo)[0],
((unsigned long *) &kvm_s390_available_subfunc.pckmo)[1]);
VM_EVENT(kvm, 3, "GET: host KMCTR subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kmctr)[0],
((unsigned long *) &kvm_s390_available_subfunc.kmctr)[1]);
VM_EVENT(kvm, 3, "GET: host KMF subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kmf)[0],
((unsigned long *) &kvm_s390_available_subfunc.kmf)[1]);
VM_EVENT(kvm, 3, "GET: host KMO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kmo)[0],
((unsigned long *) &kvm_s390_available_subfunc.kmo)[1]);
VM_EVENT(kvm, 3, "GET: host PCC subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.pcc)[0],
((unsigned long *) &kvm_s390_available_subfunc.pcc)[1]);
VM_EVENT(kvm, 3, "GET: host PPNO subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.ppno)[0],
((unsigned long *) &kvm_s390_available_subfunc.ppno)[1]);
VM_EVENT(kvm, 3, "GET: host KMA subfunc 0x%16.16lx.%16.16lx",
((unsigned long *) &kvm_s390_available_subfunc.kma)[0],
((unsigned long *) &kvm_s390_available_subfunc.kma)[1]);
return 0;
}
static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret = -ENXIO;
switch (attr->attr) {
case KVM_S390_VM_CPU_PROCESSOR:
ret = kvm_s390_get_processor(kvm, attr);
break;
case KVM_S390_VM_CPU_MACHINE:
ret = kvm_s390_get_machine(kvm, attr);
break;
case KVM_S390_VM_CPU_PROCESSOR_FEAT:
ret = kvm_s390_get_processor_feat(kvm, attr);
break;
case KVM_S390_VM_CPU_MACHINE_FEAT:
ret = kvm_s390_get_machine_feat(kvm, attr);
break;
case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
ret = kvm_s390_get_processor_subfunc(kvm, attr);
break;
case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
ret = kvm_s390_get_machine_subfunc(kvm, attr);
break;
}
return ret;
}
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
switch (attr->group) {
case KVM_S390_VM_MEM_CTRL:
ret = kvm_s390_set_mem_control(kvm, attr);
break;
case KVM_S390_VM_TOD:
ret = kvm_s390_set_tod(kvm, attr);
break;
case KVM_S390_VM_CPU_MODEL:
ret = kvm_s390_set_cpu_model(kvm, attr);
break;
case KVM_S390_VM_CRYPTO:
ret = kvm_s390_vm_set_crypto(kvm, attr);
break;
case KVM_S390_VM_MIGRATION:
ret = kvm_s390_vm_set_migration(kvm, attr);
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
switch (attr->group) {
case KVM_S390_VM_MEM_CTRL:
ret = kvm_s390_get_mem_control(kvm, attr);
break;
case KVM_S390_VM_TOD:
ret = kvm_s390_get_tod(kvm, attr);
break;
case KVM_S390_VM_CPU_MODEL:
ret = kvm_s390_get_cpu_model(kvm, attr);
break;
case KVM_S390_VM_MIGRATION:
ret = kvm_s390_vm_get_migration(kvm, attr);
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
switch (attr->group) {
case KVM_S390_VM_MEM_CTRL:
switch (attr->attr) {
case KVM_S390_VM_MEM_ENABLE_CMMA:
case KVM_S390_VM_MEM_CLR_CMMA:
ret = sclp.has_cmma ? 0 : -ENXIO;
break;
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
break;
default:
ret = -ENXIO;
break;
}
break;
case KVM_S390_VM_TOD:
switch (attr->attr) {
case KVM_S390_VM_TOD_LOW:
case KVM_S390_VM_TOD_HIGH:
ret = 0;
break;
default:
ret = -ENXIO;
break;
}
break;
case KVM_S390_VM_CPU_MODEL:
switch (attr->attr) {
case KVM_S390_VM_CPU_PROCESSOR:
case KVM_S390_VM_CPU_MACHINE:
case KVM_S390_VM_CPU_PROCESSOR_FEAT:
case KVM_S390_VM_CPU_MACHINE_FEAT:
case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
ret = 0;
break;
default:
ret = -ENXIO;
break;
}
break;
case KVM_S390_VM_CRYPTO:
switch (attr->attr) {
case KVM_S390_VM_CRYPTO_ENABLE_AES_KW:
case KVM_S390_VM_CRYPTO_ENABLE_DEA_KW:
case KVM_S390_VM_CRYPTO_DISABLE_AES_KW:
case KVM_S390_VM_CRYPTO_DISABLE_DEA_KW:
ret = 0;
break;
case KVM_S390_VM_CRYPTO_ENABLE_APIE:
case KVM_S390_VM_CRYPTO_DISABLE_APIE:
ret = ap_instructions_available() ? 0 : -ENXIO;
break;
default:
ret = -ENXIO;
break;
}
break;
case KVM_S390_VM_MIGRATION:
ret = 0;
break;
default:
ret = -ENXIO;
break;
}
return ret;
}
static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
uint8_t *keys;
uint64_t hva;
int srcu_idx, i, r = 0;
if (args->flags != 0)
return -EINVAL;
/* Is this guest using storage keys? */
if (!mm_uses_skeys(current->mm))
return KVM_S390_GET_SKEYS_NONE;
/* Enforce sane limit on memory allocation */
if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
return -EINVAL;
keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
if (!keys)
return -ENOMEM;
down_read(&current->mm->mmap_sem);
srcu_idx = srcu_read_lock(&kvm->srcu);
for (i = 0; i < args->count; i++) {
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
break;
}
r = get_guest_storage_key(current->mm, hva, &keys[i]);
if (r)
break;
}
srcu_read_unlock(&kvm->srcu, srcu_idx);
up_read(&current->mm->mmap_sem);
if (!r) {
r = copy_to_user((uint8_t __user *)args->skeydata_addr, keys,
sizeof(uint8_t) * args->count);
if (r)
r = -EFAULT;
}
kvfree(keys);
return r;
}
static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
uint8_t *keys;
uint64_t hva;
int srcu_idx, i, r = 0;
bool unlocked;
if (args->flags != 0)
return -EINVAL;
/* Enforce sane limit on memory allocation */
if (args->count < 1 || args->count > KVM_S390_SKEYS_MAX)
return -EINVAL;
keys = kvmalloc_array(args->count, sizeof(uint8_t), GFP_KERNEL);
if (!keys)
return -ENOMEM;
r = copy_from_user(keys, (uint8_t __user *)args->skeydata_addr,
sizeof(uint8_t) * args->count);
if (r) {
r = -EFAULT;
goto out;
}
/* Enable storage key handling for the guest */
r = s390_enable_skey();
if (r)
goto out;
i = 0;
down_read(&current->mm->mmap_sem);
srcu_idx = srcu_read_lock(&kvm->srcu);
while (i < args->count) {
unlocked = false;
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
break;
}
/* Lowest order bit is reserved */
if (keys[i] & 0x01) {
r = -EINVAL;
break;
}
r = set_guest_storage_key(current->mm, hva, keys[i], 0);
if (r) {
r = fixup_user_fault(current, current->mm, hva,
FAULT_FLAG_WRITE, &unlocked);
if (r)
break;
}
if (!r)
i++;
}
srcu_read_unlock(&kvm->srcu, srcu_idx);
up_read(&current->mm->mmap_sem);
out:
kvfree(keys);
return r;
}
/*
* Base address and length must be sent at the start of each block, therefore
* it's cheaper to send some clean data, as long as it's less than the size of
* two longs.
*/
#define KVM_S390_MAX_BIT_DISTANCE (2 * sizeof(void *))
/* for consistency */
#define KVM_S390_CMMA_SIZE_MAX ((u32)KVM_S390_SKEYS_MAX)
/*
* Similar to gfn_to_memslot, but returns the index of a memslot also when the
* address falls in a hole. In that case the index of one of the memslots
* bordering the hole is returned.
*/
static int gfn_to_memslot_approx(struct kvm_memslots *slots, gfn_t gfn)
{
int start = 0, end = slots->used_slots;
int slot = atomic_read(&slots->lru_slot);
struct kvm_memory_slot *memslots = slots->memslots;
if (gfn >= memslots[slot].base_gfn &&
gfn < memslots[slot].base_gfn + memslots[slot].npages)
return slot;
while (start < end) {
slot = start + (end - start) / 2;
if (gfn >= memslots[slot].base_gfn)
end = slot;
else
start = slot + 1;
}
if (gfn >= memslots[start].base_gfn &&
gfn < memslots[start].base_gfn + memslots[start].npages) {
atomic_set(&slots->lru_slot, start);
}
return start;
}
static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
u8 *res, unsigned long bufsize)
{
unsigned long pgstev, hva, cur_gfn = args->start_gfn;
args->count = 0;
while (args->count < bufsize) {
hva = gfn_to_hva(kvm, cur_gfn);
/*
* We return an error if the first value was invalid, but we
* return successfully if at least one value was copied.
*/
if (kvm_is_error_hva(hva))
return args->count ? 0 : -EFAULT;
if (get_pgste(kvm->mm, hva, &pgstev) < 0)
pgstev = 0;
res[args->count++] = (pgstev >> 24) & 0x43;
cur_gfn++;
}
return 0;
}
static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
unsigned long cur_gfn)
{
int slotidx = gfn_to_memslot_approx(slots, cur_gfn);
struct kvm_memory_slot *ms = slots->memslots + slotidx;
unsigned long ofs = cur_gfn - ms->base_gfn;
if (ms->base_gfn + ms->npages <= cur_gfn) {
slotidx--;
/* If we are above the highest slot, wrap around */
if (slotidx < 0)
slotidx = slots->used_slots - 1;
ms = slots->memslots + slotidx;
ofs = 0;
}
ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs);
while ((slotidx > 0) && (ofs >= ms->npages)) {
slotidx--;
ms = slots->memslots + slotidx;
ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, 0);
}
return ms->base_gfn + ofs;
}
static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
u8 *res, unsigned long bufsize)
{
unsigned long mem_end, cur_gfn, next_gfn, hva, pgstev;
struct kvm_memslots *slots = kvm_memslots(kvm);
struct kvm_memory_slot *ms;
cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
ms = gfn_to_memslot(kvm, cur_gfn);
args->count = 0;
args->start_gfn = cur_gfn;
if (!ms)
return 0;
next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1);
mem_end = slots->memslots[0].base_gfn + slots->memslots[0].npages;
while (args->count < bufsize) {
hva = gfn_to_hva(kvm, cur_gfn);
if (kvm_is_error_hva(hva))
return 0;
/* Decrement only if we actually flipped the bit to 0 */
if (test_and_clear_bit(cur_gfn - ms->base_gfn, kvm_second_dirty_bitmap(ms)))
atomic64_dec(&kvm->arch.cmma_dirty_pages);
if (get_pgste(kvm->mm, hva, &pgstev) < 0)
pgstev = 0;
/* Save the value */
res[args->count++] = (pgstev >> 24) & 0x43;
/* If the next bit is too far away, stop. */
if (next_gfn > cur_gfn + KVM_S390_MAX_BIT_DISTANCE)
return 0;
/* If we reached the previous "next", find the next one */
if (cur_gfn == next_gfn)
next_gfn = kvm_s390_next_dirty_cmma(slots, cur_gfn + 1);
/* Reached the end of memory or of the buffer, stop */
if ((next_gfn >= mem_end) ||
(next_gfn - args->start_gfn >= bufsize))
return 0;
cur_gfn++;
/* Reached the end of the current memslot, take the next one. */
if (cur_gfn - ms->base_gfn >= ms->npages) {
ms = gfn_to_memslot(kvm, cur_gfn);
if (!ms)
return 0;
}
}
return 0;
}
/*
* This function searches for the next page with dirty CMMA attributes, and
* saves the attributes in the buffer up to either the end of the buffer or
* until a block of at least KVM_S390_MAX_BIT_DISTANCE clean bits is found;
* no trailing clean bytes are saved.
* In case no dirty bits were found, or if CMMA was not enabled or used, the
* output buffer will indicate 0 as length.
*/
static int kvm_s390_get_cmma_bits(struct kvm *kvm,
struct kvm_s390_cmma_log *args)
{
unsigned long bufsize;
int srcu_idx, peek, ret;
u8 *values;
if (!kvm->arch.use_cmma)
return -ENXIO;
/* Invalid/unsupported flags were specified */
if (args->flags & ~KVM_S390_CMMA_PEEK)
return -EINVAL;
/* Migration mode query, and we are not doing a migration */
peek = !!(args->flags & KVM_S390_CMMA_PEEK);
if (!peek && !kvm->arch.migration_mode)
return -EINVAL;
/* CMMA is disabled or was not used, or the buffer has length zero */
bufsize = min(args->count, KVM_S390_CMMA_SIZE_MAX);
if (!bufsize || !kvm->mm->context.uses_cmm) {
memset(args, 0, sizeof(*args));
return 0;
}
/* We are not peeking, and there are no dirty pages */
if (!peek && !atomic64_read(&kvm->arch.cmma_dirty_pages)) {
memset(args, 0, sizeof(*args));
return 0;
}
values = vmalloc(bufsize);
if (!values)
return -ENOMEM;
down_read(&kvm->mm->mmap_sem);
srcu_idx = srcu_read_lock(&kvm->srcu);
if (peek)
ret = kvm_s390_peek_cmma(kvm, args, values, bufsize);
else
ret = kvm_s390_get_cmma(kvm, args, values, bufsize);
srcu_read_unlock(&kvm->srcu, srcu_idx);
up_read(&kvm->mm->mmap_sem);
if (kvm->arch.migration_mode)
args->remaining = atomic64_read(&kvm->arch.cmma_dirty_pages);
else
args->remaining = 0;
if (copy_to_user((void __user *)args->values, values, args->count))
ret = -EFAULT;
vfree(values);
return ret;
}
/*
* This function sets the CMMA attributes for the given pages. If the input
* buffer has zero length, no action is taken, otherwise the attributes are
* set and the mm->context.uses_cmm flag is set.
*/
static int kvm_s390_set_cmma_bits(struct kvm *kvm,
const struct kvm_s390_cmma_log *args)
{
unsigned long hva, mask, pgstev, i;
uint8_t *bits;
int srcu_idx, r = 0;
mask = args->mask;
if (!kvm->arch.use_cmma)
return -ENXIO;
/* invalid/unsupported flags */
if (args->flags != 0)
return -EINVAL;
/* Enforce sane limit on memory allocation */
if (args->count > KVM_S390_CMMA_SIZE_MAX)
return -EINVAL;
/* Nothing to do */
if (args->count == 0)
return 0;
bits = vmalloc(array_size(sizeof(*bits), args->count));
if (!bits)
return -ENOMEM;
r = copy_from_user(bits, (void __user *)args->values, args->count);
if (r) {
r = -EFAULT;
goto out;
}
down_read(&kvm->mm->mmap_sem);
srcu_idx = srcu_read_lock(&kvm->srcu);
for (i = 0; i < args->count; i++) {
hva = gfn_to_hva(kvm, args->start_gfn + i);
if (kvm_is_error_hva(hva)) {
r = -EFAULT;
break;
}
pgstev = bits[i];
pgstev = pgstev << 24;
mask &= _PGSTE_GPS_USAGE_MASK | _PGSTE_GPS_NODAT;
set_pgste_bits(kvm->mm, hva, mask, pgstev);
}
srcu_read_unlock(&kvm->srcu, srcu_idx);
up_read(&kvm->mm->mmap_sem);
if (!kvm->mm->context.uses_cmm) {
down_write(&kvm->mm->mmap_sem);
kvm->mm->context.uses_cmm = 1;
up_write(&kvm->mm->mmap_sem);
}
out:
vfree(bits);
return r;
}
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm *kvm = filp->private_data;
void __user *argp = (void __user *)arg;
struct kvm_device_attr attr;
int r;
switch (ioctl) {
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
r = -EFAULT;
if (copy_from_user(&s390int, argp, sizeof(s390int)))
break;
r = kvm_s390_inject_vm(kvm, &s390int);
break;
}
case KVM_CREATE_IRQCHIP: {
struct kvm_irq_routing_entry routing;
r = -EINVAL;
if (kvm->arch.use_irqchip) {
/* Set up dummy routing. */
memset(&routing, 0, sizeof(routing));
r = kvm_set_irq_routing(kvm, &routing, 0, 0);
}
break;
}
case KVM_SET_DEVICE_ATTR: {
r = -EFAULT;
if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
break;
r = kvm_s390_vm_set_attr(kvm, &attr);
break;
}
case KVM_GET_DEVICE_ATTR: {
r = -EFAULT;
if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
break;
r = kvm_s390_vm_get_attr(kvm, &attr);
break;
}
case KVM_HAS_DEVICE_ATTR: {
r = -EFAULT;
if (copy_from_user(&attr, (void __user *)arg, sizeof(attr)))
break;
r = kvm_s390_vm_has_attr(kvm, &attr);
break;
}
case KVM_S390_GET_SKEYS: {
struct kvm_s390_skeys args;
r = -EFAULT;
if (copy_from_user(&args, argp,
sizeof(struct kvm_s390_skeys)))
break;
r = kvm_s390_get_skeys(kvm, &args);
break;
}
case KVM_S390_SET_SKEYS: {
struct kvm_s390_skeys args;
r = -EFAULT;
if (copy_from_user(&args, argp,
sizeof(struct kvm_s390_skeys)))
break;
r = kvm_s390_set_skeys(kvm, &args);
break;
}
case KVM_S390_GET_CMMA_BITS: {
struct kvm_s390_cmma_log args;
r = -EFAULT;
if (copy_from_user(&args, argp, sizeof(args)))
break;
mutex_lock(&kvm->slots_lock);
r = kvm_s390_get_cmma_bits(kvm, &args);
mutex_unlock(&kvm->slots_lock);
if (!r) {
r = copy_to_user(argp, &args, sizeof(args));
if (r)
r = -EFAULT;
}
break;
}
case KVM_S390_SET_CMMA_BITS: {
struct kvm_s390_cmma_log args;
r = -EFAULT;
if (copy_from_user(&args, argp, sizeof(args)))
break;
mutex_lock(&kvm->slots_lock);
r = kvm_s390_set_cmma_bits(kvm, &args);
mutex_unlock(&kvm->slots_lock);
break;
}
default:
r = -ENOTTY;
}
return r;
}
static int kvm_s390_apxa_installed(void)
{
struct ap_config_info info;
if (ap_instructions_available()) {
if (ap_qci(&info) == 0)
return info.apxa;
}
return 0;
}
/*
* The format of the crypto control block (CRYCB) is specified in the 3 low
* order bits of the CRYCB designation (CRYCBD) field as follows:
* Format 0: Neither the message security assist extension 3 (MSAX3) nor the
* AP extended addressing (APXA) facility are installed.
* Format 1: The APXA facility is not installed but the MSAX3 facility is.
* Format 2: Both the APXA and MSAX3 facilities are installed
*/
static void kvm_s390_set_crycb_format(struct kvm *kvm)
{
kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;
/* Clear the CRYCB format bits - i.e., set format 0 by default */
kvm->arch.crypto.crycbd &= ~(CRYCB_FORMAT_MASK);
/* Check whether MSAX3 is installed */
if (!test_kvm_facility(kvm, 76))
return;
if (kvm_s390_apxa_installed())
kvm->arch.crypto.crycbd |= CRYCB_FORMAT2;
else
kvm->arch.crypto.crycbd |= CRYCB_FORMAT1;
}
void kvm_arch_crypto_set_masks(struct kvm *kvm, unsigned long *apm,
unsigned long *aqm, unsigned long *adm)
{
struct kvm_s390_crypto_cb *crycb = kvm->arch.crypto.crycb;
mutex_lock(&kvm->lock);
kvm_s390_vcpu_block_all(kvm);
switch (kvm->arch.crypto.crycbd & CRYCB_FORMAT_MASK) {
case CRYCB_FORMAT2: /* APCB1 use 256 bits */
memcpy(crycb->apcb1.apm, apm, 32);
VM_EVENT(kvm, 3, "SET CRYCB: apm %016lx %016lx %016lx %016lx",
apm[0], apm[1], apm[2], apm[3]);
memcpy(crycb->apcb1.aqm, aqm, 32);
VM_EVENT(kvm, 3, "SET CRYCB: aqm %016lx %016lx %016lx %016lx",
aqm[0], aqm[1], aqm[2], aqm[3]);
memcpy(crycb->apcb1.adm, adm, 32);
VM_EVENT(kvm, 3, "SET CRYCB: adm %016lx %016lx %016lx %016lx",
adm[0], adm[1], adm[2], adm[3]);
break;
case CRYCB_FORMAT1:
case CRYCB_FORMAT0: /* Fall through both use APCB0 */
memcpy(crycb->apcb0.apm, apm, 8);
memcpy(crycb->apcb0.aqm, aqm, 2);
memcpy(crycb->apcb0.adm, adm, 2);
VM_EVENT(kvm, 3, "SET CRYCB: apm %016lx aqm %04x adm %04x",
apm[0], *((unsigned short *)aqm),
*((unsigned short *)adm));
break;
default: /* Can not happen */
break;
}
/* recreate the shadow crycb for each vcpu */
kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART);
kvm_s390_vcpu_unblock_all(kvm);
mutex_unlock(&kvm->lock);
}
EXPORT_SYMBOL_GPL(kvm_arch_crypto_set_masks);
void kvm_arch_crypto_clear_masks(struct kvm *kvm)
{
mutex_lock(&kvm->lock);
kvm_s390_vcpu_block_all(kvm);
memset(&kvm->arch.crypto.crycb->apcb0, 0,
sizeof(kvm->arch.crypto.crycb->apcb0));
memset(&kvm->arch.crypto.crycb->apcb1, 0,
sizeof(kvm->arch.crypto.crycb->apcb1));
VM_EVENT(kvm, 3, "%s", "CLR CRYCB:");
/* recreate the shadow crycb for each vcpu */
kvm_s390_sync_request_broadcast(kvm, KVM_REQ_VSIE_RESTART);
kvm_s390_vcpu_unblock_all(kvm);
mutex_unlock(&kvm->lock);
}
EXPORT_SYMBOL_GPL(kvm_arch_crypto_clear_masks);
static u64 kvm_s390_get_initial_cpuid(void)
{
struct cpuid cpuid;
get_cpu_id(&cpuid);
cpuid.version = 0xff;
return *((u64 *) &cpuid);
}
static void kvm_s390_crypto_init(struct kvm *kvm)
{
kvm->arch.crypto.crycb = &kvm->arch.sie_page2->crycb;
kvm_s390_set_crycb_format(kvm);
if (!test_kvm_facility(kvm, 76))
return;
/* Enable AES/DEA protected key functions by default */
kvm->arch.crypto.aes_kw = 1;
kvm->arch.crypto.dea_kw = 1;
get_random_bytes(kvm->arch.crypto.crycb->aes_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->aes_wrapping_key_mask));
get_random_bytes(kvm->arch.crypto.crycb->dea_wrapping_key_mask,
sizeof(kvm->arch.crypto.crycb->dea_wrapping_key_mask));
}
static void sca_dispose(struct kvm *kvm)
{
if (kvm->arch.use_esca)
free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
else
free_page((unsigned long)(kvm->arch.sca));
kvm->arch.sca = NULL;
}
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
gfp_t alloc_flags = GFP_KERNEL;
int i, rc;
char debug_name[16];
static unsigned long sca_offset;
rc = -EINVAL;
#ifdef CONFIG_KVM_S390_UCONTROL
if (type & ~KVM_VM_S390_UCONTROL)
goto out_err;
if ((type & KVM_VM_S390_UCONTROL) && (!capable(CAP_SYS_ADMIN)))
goto out_err;
#else
if (type)
goto out_err;
#endif
rc = s390_enable_sie();
if (rc)
goto out_err;
rc = -ENOMEM;
if (!sclp.has_64bscao)
alloc_flags |= GFP_DMA;
rwlock_init(&kvm->arch.sca_lock);
/* start with basic SCA */
kvm->arch.sca = (struct bsca_block *) get_zeroed_page(alloc_flags);
if (!kvm->arch.sca)
goto out_err;
spin_lock(&kvm_lock);
sca_offset += 16;
if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
kvm->arch.sca = (struct bsca_block *)
((char *) kvm->arch.sca + sca_offset);
spin_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
kvm->arch.dbf = debug_register(debug_name, 32, 1, 7 * sizeof(long));
if (!kvm->arch.dbf)
goto out_err;
BUILD_BUG_ON(sizeof(struct sie_page2) != 4096);
kvm->arch.sie_page2 =
(struct sie_page2 *) get_zeroed_page(GFP_KERNEL | GFP_DMA);
if (!kvm->arch.sie_page2)
goto out_err;
kvm->arch.sie_page2->kvm = kvm;
kvm->arch.model.fac_list = kvm->arch.sie_page2->fac_list;
for (i = 0; i < kvm_s390_fac_size(); i++) {
kvm->arch.model.fac_mask[i] = S390_lowcore.stfle_fac_list[i] &
(kvm_s390_fac_base[i] |
kvm_s390_fac_ext[i]);
kvm->arch.model.fac_list[i] = S390_lowcore.stfle_fac_list[i] &
kvm_s390_fac_base[i];
}
kvm->arch.model.subfuncs = kvm_s390_available_subfunc;
/* we are always in czam mode - even on pre z14 machines */
set_kvm_facility(kvm->arch.model.fac_mask, 138);
set_kvm_facility(kvm->arch.model.fac_list, 138);
/* 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) {
set_kvm_facility(kvm->arch.model.fac_mask, 147);
set_kvm_facility(kvm->arch.model.fac_list, 147);
}
kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
kvm_s390_crypto_init(kvm);
mutex_init(&kvm->arch.float_int.ais_lock);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
INIT_LIST_HEAD(&kvm->arch.float_int.lists[i]);
init_waitqueue_head(&kvm->arch.ipte_wq);
mutex_init(&kvm->arch.ipte_mutex);
debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
VM_EVENT(kvm, 3, "vm created with type %lu", type);
if (type & KVM_VM_S390_UCONTROL) {
kvm->arch.gmap = NULL;
kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
} else {
if (sclp.hamax == U64_MAX)
kvm->arch.mem_limit = TASK_SIZE_MAX;
else
kvm->arch.mem_limit = min_t(unsigned long, TASK_SIZE_MAX,
sclp.hamax + 1);
kvm->arch.gmap = gmap_create(current->mm, kvm->arch.mem_limit - 1);
if (!kvm->arch.gmap)
goto out_err;
kvm->arch.gmap->private = kvm;
kvm->arch.gmap->pfault_enabled = 0;
}
kvm->arch.use_pfmfi = sclp.has_pfmfi;
kvm->arch.use_skf = sclp.has_skey;
spin_lock_init(&kvm->arch.start_stop_lock);
kvm_s390_vsie_init(kvm);
kvm_s390_gisa_init(kvm);
KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
out_err:
free_page((unsigned long)kvm->arch.sie_page2);
debug_unregister(kvm->arch.dbf);
sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
return rc;
}
bool kvm_arch_has_vcpu_debugfs(void)
{
return false;
}
int kvm_arch_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
return 0;
}
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
VCPU_EVENT(vcpu, 3, "%s", "free cpu");
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
kvm_s390_clear_local_irqs(vcpu);
kvm_clear_async_pf_completion_queue(vcpu);
if (!kvm_is_ucontrol(vcpu->kvm))
sca_del_vcpu(vcpu);
if (kvm_is_ucontrol(vcpu->kvm))
gmap_remove(vcpu->arch.gmap);
if (vcpu->kvm->arch.use_cmma)
kvm_s390_vcpu_unsetup_cmma(vcpu);
free_page((unsigned long)(vcpu->arch.sie_block));
kvm_vcpu_uninit(vcpu);
kmem_cache_free(kvm_vcpu_cache, vcpu);
}
static void kvm_free_vcpus(struct kvm *kvm)
{
unsigned int i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_arch_vcpu_destroy(vcpu);
mutex_lock(&kvm->lock);
for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
kvm->vcpus[i] = NULL;
atomic_set(&kvm->online_vcpus, 0);
mutex_unlock(&kvm->lock);
}
void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
kvm_s390_gisa_destroy(kvm);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
gmap_remove(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
kvm_s390_vsie_destroy(kvm);
KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
/* Section: vcpu related */
static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
{
vcpu->arch.gmap = gmap_create(current->mm, -1UL);
if (!vcpu->arch.gmap)
return -ENOMEM;
vcpu->arch.gmap->private = vcpu->kvm;
return 0;
}
static void sca_del_vcpu(struct kvm_vcpu *vcpu)
{
if (!kvm_s390_use_sca_entries())
return;
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
sca->cpu[vcpu->vcpu_id].sda = 0;
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
sca->cpu[vcpu->vcpu_id].sda = 0;
}
read_unlock(&vcpu->kvm->arch.sca_lock);
}
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
{
if (!kvm_s390_use_sca_entries()) {
struct bsca_block *sca = vcpu