aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/arch/s390/kvm/kvm-s390.c
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm/kvm-s390.c')
-rw-r--r--arch/s390/kvm/kvm-s390.c1619
1 files changed, 1282 insertions, 337 deletions
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 8fcb56141689..d5ad10791c25 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>
@@ -31,22 +32,27 @@
#include <linux/sched/signal.h>
#include <linux/string.h>
#include <linux/pgtable.h>
+#include <linux/mmu_notifier.h>
+#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/gmap_helpers.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/asm.h>
+#include <asm/fpu.h>
#include <asm/ap.h>
#include <asm/uv.h>
-#include <asm/fpu/api.h>
#include "kvm-s390.h"
#include "gaccess.h"
+#include "pci.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -63,7 +69,15 @@ const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
STATS_DESC_COUNTER(VM, inject_float_mchk),
STATS_DESC_COUNTER(VM, inject_pfault_done),
STATS_DESC_COUNTER(VM, inject_service_signal),
- STATS_DESC_COUNTER(VM, inject_virtio)
+ STATS_DESC_COUNTER(VM, inject_virtio),
+ STATS_DESC_COUNTER(VM, aen_forward),
+ STATS_DESC_COUNTER(VM, gmap_shadow_reuse),
+ STATS_DESC_COUNTER(VM, gmap_shadow_create),
+ STATS_DESC_COUNTER(VM, gmap_shadow_r1_entry),
+ STATS_DESC_COUNTER(VM, gmap_shadow_r2_entry),
+ STATS_DESC_COUNTER(VM, gmap_shadow_r3_entry),
+ STATS_DESC_COUNTER(VM, gmap_shadow_sg_entry),
+ STATS_DESC_COUNTER(VM, gmap_shadow_pg_entry),
};
const struct kvm_stats_header kvm_vm_stats_header = {
@@ -122,6 +136,7 @@ const struct _kvm_stats_desc kvm_vcpu_stats_desc[] = {
STATS_DESC_COUNTER(VCPU, instruction_io_other),
STATS_DESC_COUNTER(VCPU, instruction_lpsw),
STATS_DESC_COUNTER(VCPU, instruction_lpswe),
+ STATS_DESC_COUNTER(VCPU, instruction_lpswey),
STATS_DESC_COUNTER(VCPU, instruction_pfmf),
STATS_DESC_COUNTER(VCPU, instruction_ptff),
STATS_DESC_COUNTER(VCPU, instruction_sck),
@@ -207,6 +222,14 @@ module_param(diag9c_forwarding_hz, uint, 0644);
MODULE_PARM_DESC(diag9c_forwarding_hz, "Maximum diag9c forwarding per second, 0 to turn off");
/*
+ * allow asynchronous deinit for protected guests; enable by default since
+ * the feature is opt-in anyway
+ */
+static int async_destroy = 1;
+module_param(async_destroy, int, 0444);
+MODULE_PARM_DESC(async_destroy, "Asynchronous destroy for protected guests");
+
+/*
* 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.
@@ -245,17 +268,6 @@ debug_info_t *kvm_s390_dbf;
debug_info_t *kvm_s390_dbf_uv;
/* Section: not file related */
-int kvm_arch_hardware_enable(void)
-{
- /* every s390 is virtualization enabled ;-) */
- return 0;
-}
-
-int kvm_arch_check_processor_compat(void *opaque)
-{
- return 0;
-}
-
/* forward declarations */
static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long end);
@@ -318,25 +330,6 @@ static struct notifier_block kvm_clock_notifier = {
.notifier_call = kvm_clock_sync,
};
-int kvm_arch_hardware_setup(void *opaque)
-{
- 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);
@@ -351,30 +344,48 @@ static inline int plo_test_bit(unsigned char nr)
" lgr 0,%[function]\n"
/* Parameter registers are ignored for "test bit" */
" plo 0,0,0,0(0)\n"
- " ipm %0\n"
- " srl %0,28\n"
- : "=d" (cc)
+ CC_IPM(cc)
+ : CC_OUT(cc, cc)
: [function] "d" (function)
+ : CC_CLOBBER_LIST("0"));
+ return CC_TRANSFORM(cc) == 0;
+}
+
+static __always_inline void pfcr_query(u8 (*query)[16])
+{
+ asm volatile(
+ " lghi 0,0\n"
+ " .insn rsy,0xeb0000000016,0,0,%[query]\n"
+ : [query] "=QS" (*query)
+ :
: "cc", "0");
- return cc == 0;
}
-static __always_inline void __insn32_query(unsigned int opcode, u8 *query)
+static __always_inline void __sortl_query(u8 (*query)[32])
{
asm volatile(
" lghi 0,0\n"
- " lgr 1,%[query]\n"
+ " la 1,%[query]\n"
/* Parameter registers are ignored */
- " .insn rrf,%[opc] << 16,2,4,6,0\n"
+ " .insn rre,0xb9380000,2,4\n"
+ : [query] "=R" (*query)
:
- : [query] "d" ((unsigned long)query), [opc] "i" (opcode)
- : "cc", "memory", "0", "1");
+ : "cc", "0", "1");
}
-#define INSN_SORTL 0xb938
-#define INSN_DFLTCC 0xb939
+static __always_inline void __dfltcc_query(u8 (*query)[32])
+{
+ asm volatile(
+ " lghi 0,0\n"
+ " la 1,%[query]\n"
+ /* Parameter registers are ignored */
+ " .insn rrf,0xb9390000,2,4,6,0\n"
+ : [query] "=R" (*query)
+ :
+ : "cc", "0", "1");
+}
-static void kvm_s390_cpu_feat_init(void)
+static void __init kvm_s390_cpu_feat_init(void)
{
int i;
@@ -426,18 +437,21 @@ static void kvm_s390_cpu_feat_init(void)
kvm_s390_available_subfunc.kdsa);
if (test_facility(150)) /* SORTL */
- __insn32_query(INSN_SORTL, kvm_s390_available_subfunc.sortl);
+ __sortl_query(&kvm_s390_available_subfunc.sortl);
if (test_facility(151)) /* DFLTCC */
- __insn32_query(INSN_DFLTCC, kvm_s390_available_subfunc.dfltcc);
+ __dfltcc_query(&kvm_s390_available_subfunc.dfltcc);
+
+ 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);
@@ -477,7 +491,7 @@ static void kvm_s390_cpu_feat_init(void)
*/
}
-int kvm_arch_init(void *opaque)
+static int __init __kvm_s390_init(void)
{
int rc = -ENOMEM;
@@ -487,11 +501,11 @@ int kvm_arch_init(void *opaque)
kvm_s390_dbf_uv = debug_register("kvm-uv", 32, 1, 7 * sizeof(long));
if (!kvm_s390_dbf_uv)
- goto out;
+ goto err_kvm_uv;
if (debug_register_view(kvm_s390_dbf, &debug_sprintf_view) ||
debug_register_view(kvm_s390_dbf_uv, &debug_sprintf_view))
- goto out;
+ goto err_debug_view;
kvm_s390_cpu_feat_init();
@@ -499,23 +513,52 @@ int kvm_arch_init(void *opaque)
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;
+ goto err_flic;
+ }
+
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
+ rc = kvm_s390_pci_init();
+ if (rc) {
+ pr_err("Unable to allocate AIFT for PCI\n");
+ goto err_pci;
+ }
}
rc = kvm_s390_gib_init(GAL_ISC);
if (rc)
- goto out;
+ goto err_gib;
+
+ 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;
-out:
- kvm_arch_exit();
+err_gib:
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+ kvm_s390_pci_exit();
+err_pci:
+err_flic:
+err_debug_view:
+ debug_unregister(kvm_s390_dbf_uv);
+err_kvm_uv:
+ debug_unregister(kvm_s390_dbf);
return rc;
}
-void kvm_arch_exit(void)
+static void __kvm_s390_exit(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);
+
kvm_s390_gib_destroy();
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+ kvm_s390_pci_exit();
debug_unregister(kvm_s390_dbf);
debug_unregister(kvm_s390_dbf_uv);
}
@@ -546,7 +589,6 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
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:
@@ -563,7 +605,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_VCPU_RESETS:
case KVM_CAP_SET_GUEST_DEBUG:
case KVM_CAP_S390_DIAG318:
- case KVM_CAP_S390_MEM_OP_EXTENSION:
+ case KVM_CAP_IRQFD_RESAMPLE:
r = 1;
break;
case KVM_CAP_SET_GUEST_DEBUG2:
@@ -571,12 +613,21 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_S390_HPAGE_1M:
r = 0;
- if (hpage && !kvm_is_ucontrol(kvm))
+ if (hpage && !(kvm && kvm_is_ucontrol(kvm)))
r = 1;
break;
case KVM_CAP_S390_MEM_OP:
r = MEM_OP_MAX_SIZE;
break;
+ case KVM_CAP_S390_MEM_OP_EXTENSION:
+ /*
+ * Flag bits indicating which extensions are supported.
+ * If r > 0, the base extension must also be supported/indicated,
+ * in order to maintain backwards compatibility.
+ */
+ r = KVM_S390_MEMOP_EXTENSION_CAP_BASE |
+ KVM_S390_MEMOP_EXTENSION_CAP_CMPXCHG;
+ break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
case KVM_CAP_MAX_VCPU_ID:
@@ -589,10 +640,10 @@ 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 = MACHINE_HAS_VX;
+ r = test_facility(129);
break;
case KVM_CAP_S390_RI:
r = test_facility(64);
@@ -603,9 +654,38 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_BPB:
r = test_facility(82);
break;
+ case KVM_CAP_S390_PROTECTED_ASYNC_DISABLE:
+ r = async_destroy && is_prot_virt_host();
+ break;
case KVM_CAP_S390_PROTECTED:
r = is_prot_virt_host();
break;
+ case KVM_CAP_S390_PROTECTED_DUMP: {
+ u64 pv_cmds_dump[] = {
+ BIT_UVC_CMD_DUMP_INIT,
+ BIT_UVC_CMD_DUMP_CONFIG_STOR_STATE,
+ BIT_UVC_CMD_DUMP_CPU,
+ BIT_UVC_CMD_DUMP_COMPLETE,
+ };
+ int i;
+
+ r = is_prot_virt_host();
+
+ for (i = 0; i < ARRAY_SIZE(pv_cmds_dump); i++) {
+ if (!test_bit_inv(pv_cmds_dump[i],
+ (unsigned long *)&uv_info.inst_calls_list)) {
+ r = 0;
+ break;
+ }
+ }
+ break;
+ }
+ case KVM_CAP_S390_ZPCI_OP:
+ r = kvm_s390_pci_interp_allowed();
+ break;
+ case KVM_CAP_S390_CPU_TOPOLOGY:
+ r = test_facility(11);
+ break;
default:
r = 0;
}
@@ -712,7 +792,7 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
mutex_lock(&kvm->lock);
if (kvm->created_vcpus) {
r = -EBUSY;
- } else if (MACHINE_HAS_VX) {
+ } else if (cpu_has_vx()) {
set_kvm_facility(kvm->arch.model.fac_mask, 129);
set_kvm_facility(kvm->arch.model.fac_list, 129);
if (test_facility(134)) {
@@ -735,6 +815,14 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
set_kvm_facility(kvm->arch.model.fac_mask, 192);
set_kvm_facility(kvm->arch.model.fac_list, 192);
}
+ if (test_facility(198)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 198);
+ set_kvm_facility(kvm->arch.model.fac_list, 198);
+ }
+ if (test_facility(199)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 199);
+ set_kvm_facility(kvm->arch.model.fac_list, 199);
+ }
r = 0;
} else
r = -EINVAL;
@@ -817,6 +905,20 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
icpt_operexc_on_all_vcpus(kvm);
r = 0;
break;
+ case KVM_CAP_S390_CPU_TOPOLOGY:
+ r = -EINVAL;
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus) {
+ r = -EBUSY;
+ } else if (test_facility(11)) {
+ set_kvm_facility(kvm->arch.model.fac_mask, 11);
+ set_kvm_facility(kvm->arch.model.fac_list, 11);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ VM_EVENT(kvm, 3, "ENABLE: CAP_S390_CPU_TOPOLOGY %s",
+ r ? "(not available)" : "(success)");
+ break;
default:
r = -EINVAL;
break;
@@ -920,7 +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;
}
@@ -1019,6 +1121,42 @@ static int kvm_s390_vm_set_crypto(struct kvm *kvm, struct kvm_device_attr *attr)
return 0;
}
+static void kvm_s390_vcpu_pci_setup(struct kvm_vcpu *vcpu)
+{
+ /* Only set the ECB bits after guest requests zPCI interpretation */
+ if (!vcpu->kvm->arch.use_zpci_interp)
+ return;
+
+ vcpu->arch.sie_block->ecb2 |= ECB2_ZPCI_LSI;
+ vcpu->arch.sie_block->ecb3 |= ECB3_AISII + ECB3_AISI;
+}
+
+void kvm_s390_vcpu_pci_enable_interp(struct kvm *kvm)
+{
+ struct kvm_vcpu *vcpu;
+ unsigned long i;
+
+ lockdep_assert_held(&kvm->lock);
+
+ if (!kvm_s390_pci_interp_allowed())
+ return;
+
+ /*
+ * If host is configured for PCI and the necessary facilities are
+ * available, turn on interpretation for the life of this guest
+ */
+ kvm->arch.use_zpci_interp = 1;
+
+ kvm_s390_vcpu_block_all(kvm);
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ kvm_s390_vcpu_pci_setup(vcpu);
+ kvm_s390_sync_request(KVM_REQ_VSIE_RESTART, vcpu);
+ }
+
+ kvm_s390_vcpu_unblock_all(kvm);
+}
+
static void kvm_s390_sync_request_broadcast(struct kvm *kvm, int req)
{
unsigned long cx;
@@ -1118,6 +1256,8 @@ static int kvm_s390_vm_get_migration(struct kvm *kvm,
return 0;
}
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod);
+
static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
{
struct kvm_s390_vm_tod_clock gtod;
@@ -1127,7 +1267,7 @@ static int kvm_s390_set_tod_ext(struct kvm *kvm, struct kvm_device_attr *attr)
if (!test_kvm_facility(kvm, 139) && gtod.epoch_idx)
return -EINVAL;
- kvm_s390_set_tod_clock(kvm, &gtod);
+ __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);
@@ -1158,7 +1298,7 @@ static int kvm_s390_set_tod_low(struct kvm *kvm, struct kvm_device_attr *attr)
sizeof(gtod.tod)))
return -EFAULT;
- kvm_s390_set_tod_clock(kvm, &gtod);
+ __kvm_s390_set_tod_clock(kvm, &gtod);
VM_EVENT(kvm, 3, "SET: TOD base: 0x%llx", gtod.tod);
return 0;
}
@@ -1170,6 +1310,16 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
if (attr->flags)
return -EINVAL;
+ mutex_lock(&kvm->lock);
+ /*
+ * For protected guests, the TOD is managed by the ultravisor, so trying
+ * to change it will never bring the expected results.
+ */
+ if (kvm_s390_pv_is_protected(kvm)) {
+ ret = -EOPNOTSUPP;
+ goto out_unlock;
+ }
+
switch (attr->attr) {
case KVM_S390_VM_TOD_EXT:
ret = kvm_s390_set_tod_ext(kvm, attr);
@@ -1184,6 +1334,9 @@ static int kvm_s390_set_tod(struct kvm *kvm, struct kvm_device_attr *attr)
ret = -ENXIO;
break;
}
+
+out_unlock:
+ mutex_unlock(&kvm->lock);
return ret;
}
@@ -1414,6 +1567,42 @@ static int kvm_s390_set_processor_subfunc(struct kvm *kvm,
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
+ VM_EVENT(kvm, 3, "GET: guest PFCR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]);
+
+ return 0;
+}
+
+#define KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK \
+( \
+ ((struct kvm_s390_vm_cpu_uv_feat){ \
+ .ap = 1, \
+ .ap_intr = 1, \
+ }) \
+ .feat \
+)
+
+static int kvm_s390_set_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_uv_feat __user *ptr = (void __user *)attr->addr;
+ unsigned long data, filter;
+
+ filter = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK;
+ if (get_user(data, &ptr->feat))
+ return -EFAULT;
+ if (!bitmap_subset(&data, &filter, KVM_S390_VM_CPU_UV_FEAT_NR_BITS))
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+ if (kvm->created_vcpus) {
+ mutex_unlock(&kvm->lock);
+ return -EBUSY;
+ }
+ kvm->arch.model.uv_feat_guest.feat = data;
+ mutex_unlock(&kvm->lock);
+
+ VM_EVENT(kvm, 3, "SET: guest UV-feat: 0x%16.16lx", data);
return 0;
}
@@ -1432,6 +1621,9 @@ static int kvm_s390_set_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
ret = kvm_s390_set_processor_subfunc(kvm, attr);
break;
+ case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
+ ret = kvm_s390_set_uv_feat(kvm, attr);
+ break;
}
return ret;
}
@@ -1592,6 +1784,9 @@ static int kvm_s390_get_processor_subfunc(struct kvm *kvm,
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[1],
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[2],
((unsigned long *) &kvm->arch.model.subfuncs.dfltcc)[3]);
+ VM_EVENT(kvm, 3, "GET: guest PFCR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]);
return 0;
}
@@ -1660,6 +1855,36 @@ static int kvm_s390_get_machine_subfunc(struct kvm *kvm,
((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[1],
((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[2],
((unsigned long *) &kvm_s390_available_subfunc.dfltcc)[3]);
+ VM_EVENT(kvm, 3, "GET: host PFCR subfunc 0x%16.16lx.%16.16lx",
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[0],
+ ((unsigned long *) &kvm_s390_available_subfunc.pfcr)[1]);
+
+ return 0;
+}
+
+static int kvm_s390_get_processor_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr;
+ unsigned long feat = kvm->arch.model.uv_feat_guest.feat;
+
+ if (put_user(feat, &dst->feat))
+ return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat);
+
+ return 0;
+}
+
+static int kvm_s390_get_machine_uv_feat(struct kvm *kvm, struct kvm_device_attr *attr)
+{
+ struct kvm_s390_vm_cpu_uv_feat __user *dst = (void __user *)attr->addr;
+ unsigned long feat;
+
+ BUILD_BUG_ON(sizeof(*dst) != sizeof(uv_info.uv_feature_indications));
+
+ feat = uv_info.uv_feature_indications & KVM_S390_VM_CPU_UV_FEAT_GUEST_MASK;
+ if (put_user(feat, &dst->feat))
+ return -EFAULT;
+ VM_EVENT(kvm, 3, "GET: guest UV-feat: 0x%16.16lx", feat);
return 0;
}
@@ -1687,10 +1912,67 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
ret = kvm_s390_get_machine_subfunc(kvm, attr);
break;
+ case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
+ ret = kvm_s390_get_processor_uv_feat(kvm, attr);
+ break;
+ case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST:
+ ret = kvm_s390_get_machine_uv_feat(kvm, attr);
+ break;
}
return ret;
}
+/**
+ * kvm_s390_update_topology_change_report - update CPU topology change report
+ * @kvm: guest KVM description
+ * @val: set or clear the MTCR bit
+ *
+ * Updates the Multiprocessor Topology-Change-Report bit to signal
+ * the guest with a topology change.
+ * This is only relevant if the topology facility is present.
+ *
+ * The SCA version, bsca or esca, doesn't matter as offset is the same.
+ */
+static void kvm_s390_update_topology_change_report(struct kvm *kvm, bool val)
+{
+ union sca_utility new, old;
+ struct bsca_block *sca;
+
+ read_lock(&kvm->arch.sca_lock);
+ sca = kvm->arch.sca;
+ old = READ_ONCE(sca->utility);
+ do {
+ new = old;
+ new.mtcr = val;
+ } while (!try_cmpxchg(&sca->utility.val, &old.val, new.val));
+ read_unlock(&kvm->arch.sca_lock);
+}
+
+static int kvm_s390_set_topo_change_indication(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+{
+ if (!test_kvm_facility(kvm, 11))
+ return -ENXIO;
+
+ kvm_s390_update_topology_change_report(kvm, !!attr->attr);
+ return 0;
+}
+
+static int kvm_s390_get_topo_change_indication(struct kvm *kvm,
+ struct kvm_device_attr *attr)
+{
+ u8 topo;
+
+ if (!test_kvm_facility(kvm, 11))
+ return -ENXIO;
+
+ read_lock(&kvm->arch.sca_lock);
+ topo = ((struct bsca_block *)kvm->arch.sca)->utility.mtcr;
+ read_unlock(&kvm->arch.sca_lock);
+
+ return put_user(topo, (u8 __user *)attr->addr);
+}
+
static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
{
int ret;
@@ -1711,6 +1993,9 @@ static int kvm_s390_vm_set_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_MIGRATION:
ret = kvm_s390_vm_set_migration(kvm, attr);
break;
+ case KVM_S390_VM_CPU_TOPOLOGY:
+ ret = kvm_s390_set_topo_change_indication(kvm, attr);
+ break;
default:
ret = -ENXIO;
break;
@@ -1736,6 +2021,9 @@ static int kvm_s390_vm_get_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_MIGRATION:
ret = kvm_s390_vm_get_migration(kvm, attr);
break;
+ case KVM_S390_VM_CPU_TOPOLOGY:
+ ret = kvm_s390_get_topo_change_indication(kvm, attr);
+ break;
default:
ret = -ENXIO;
break;
@@ -1782,6 +2070,8 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_CPU_MACHINE_FEAT:
case KVM_S390_VM_CPU_MACHINE_SUBFUNC:
case KVM_S390_VM_CPU_PROCESSOR_SUBFUNC:
+ case KVM_S390_VM_CPU_MACHINE_UV_FEAT_GUEST:
+ case KVM_S390_VM_CPU_PROCESSOR_UV_FEAT_GUEST:
ret = 0;
break;
default:
@@ -1809,6 +2099,9 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
case KVM_S390_VM_MIGRATION:
ret = 0;
break;
+ case KVM_S390_VM_CPU_TOPOLOGY:
+ ret = test_kvm_facility(kvm, 11) ? 0 : -ENXIO;
+ break;
default:
ret = -ENXIO;
break;
@@ -1817,7 +2110,7 @@ static int kvm_s390_vm_has_attr(struct kvm *kvm, struct kvm_device_attr *attr)
return ret;
}
-static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+static int kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
uint8_t *keys;
uint64_t hva;
@@ -1865,7 +2158,7 @@ static long kvm_s390_get_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
return r;
}
-static long kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
+static int kvm_s390_set_skeys(struct kvm *kvm, struct kvm_s390_skeys *args)
{
uint8_t *keys;
uint64_t hva;
@@ -1983,6 +2276,10 @@ static unsigned long kvm_s390_next_dirty_cmma(struct kvm_memslots *slots,
ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
ofs = 0;
}
+
+ if (cur_gfn < ms->base_gfn)
+ ofs = 0;
+
ofs = find_next_bit(kvm_second_dirty_bitmap(ms), ms->npages, ofs);
while (ofs >= ms->npages && (mnode = rb_next(mnode))) {
ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
@@ -2166,12 +2463,25 @@ out:
return r;
}
-static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
+/**
+ * kvm_s390_cpus_from_pv - Convert all protected vCPUs in a protected VM to
+ * non protected.
+ * @kvm: the VM whose protected vCPUs are to be converted
+ * @rc: return value for the RC field of the UVC (in case of error)
+ * @rrc: return value for the RRC field of the UVC (in case of error)
+ *
+ * Does not stop in case of error, tries to convert as many
+ * CPUs as possible. In case of error, the RC and RRC of the last error are
+ * returned.
+ *
+ * Return: 0 in case of success, otherwise -EIO
+ */
+int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
{
struct kvm_vcpu *vcpu;
- u16 rc, rrc;
- int ret = 0;
unsigned long i;
+ u16 _rc, _rrc;
+ int ret = 0;
/*
* We ignore failures and try to destroy as many CPUs as possible.
@@ -2183,9 +2493,9 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
*/
kvm_for_each_vcpu(i, vcpu, kvm) {
mutex_lock(&vcpu->mutex);
- if (kvm_s390_pv_destroy_cpu(vcpu, &rc, &rrc) && !ret) {
- *rcp = rc;
- *rrcp = rrc;
+ if (kvm_s390_pv_destroy_cpu(vcpu, &_rc, &_rrc) && !ret) {
+ *rc = _rc;
+ *rrc = _rrc;
ret = -EIO;
}
mutex_unlock(&vcpu->mutex);
@@ -2196,6 +2506,17 @@ static int kvm_s390_cpus_from_pv(struct kvm *kvm, u16 *rcp, u16 *rrcp)
return ret;
}
+/**
+ * kvm_s390_cpus_to_pv - Convert all non-protected vCPUs in a protected VM
+ * to protected.
+ * @kvm: the VM whose protected vCPUs are to be converted
+ * @rc: return value for the RC field of the UVC (in case of error)
+ * @rrc: return value for the RRC field of the UVC (in case of error)
+ *
+ * Tries to undo the conversion in case of error.
+ *
+ * Return: 0 in case of success, otherwise -EIO
+ */
static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
{
unsigned long i;
@@ -2205,7 +2526,7 @@ static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
struct kvm_vcpu *vcpu;
/* Disable the GISA if the ultravisor does not support AIV. */
- if (!test_bit_inv(BIT_UV_FEAT_AIV, &uv_info.uv_feature_indications))
+ if (!uv_has_feature(BIT_UV_FEAT_AIV))
kvm_s390_gisa_disable(kvm);
kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -2220,11 +2541,124 @@ static int kvm_s390_cpus_to_pv(struct kvm *kvm, u16 *rc, u16 *rrc)
return r;
}
+/*
+ * Here we provide user space with a direct interface to query UV
+ * related data like UV maxima and available features as well as
+ * feature specific data.
+ *
+ * To facilitate future extension of the data structures we'll try to
+ * write data up to the maximum requested length.
+ */
+static ssize_t kvm_s390_handle_pv_info(struct kvm_s390_pv_info *info)
+{
+ ssize_t len_min;
+
+ switch (info->header.id) {
+ case KVM_PV_INFO_VM: {
+ len_min = sizeof(info->header) + sizeof(info->vm);
+
+ if (info->header.len_max < len_min)
+ return -EINVAL;
+
+ memcpy(info->vm.inst_calls_list,
+ uv_info.inst_calls_list,
+ sizeof(uv_info.inst_calls_list));
+
+ /* It's max cpuid not max cpus, so it's off by one */
+ info->vm.max_cpus = uv_info.max_guest_cpu_id + 1;
+ info->vm.max_guests = uv_info.max_num_sec_conf;
+ info->vm.max_guest_addr = uv_info.max_sec_stor_addr;
+ info->vm.feature_indication = uv_info.uv_feature_indications;
+
+ return len_min;
+ }
+ case KVM_PV_INFO_DUMP: {
+ len_min = sizeof(info->header) + sizeof(info->dump);
+
+ if (info->header.len_max < len_min)
+ return -EINVAL;
+
+ info->dump.dump_cpu_buffer_len = uv_info.guest_cpu_stor_len;
+ info->dump.dump_config_mem_buffer_per_1m = uv_info.conf_dump_storage_state_len;
+ info->dump.dump_config_finalize_len = uv_info.conf_dump_finalize_len;
+ return len_min;
+ }
+ default:
+ return -EINVAL;
+ }
+}
+
+static int kvm_s390_pv_dmp(struct kvm *kvm, struct kvm_pv_cmd *cmd,
+ struct kvm_s390_pv_dmp dmp)
+{
+ int r = -EINVAL;
+ void __user *result_buff = (void __user *)dmp.buff_addr;
+
+ switch (dmp.subcmd) {
+ case KVM_PV_DUMP_INIT: {
+ if (kvm->arch.pv.dumping)
+ break;
+
+ /*
+ * Block SIE entry as concurrent dump UVCs could lead
+ * to validities.
+ */
+ kvm_s390_vcpu_block_all(kvm);
+
+ r = uv_cmd_nodata(kvm_s390_pv_get_handle(kvm),
+ UVC_CMD_DUMP_INIT, &cmd->rc, &cmd->rrc);
+ KVM_UV_EVENT(kvm, 3, "PROTVIRT DUMP INIT: rc %x rrc %x",
+ cmd->rc, cmd->rrc);
+ if (!r) {
+ kvm->arch.pv.dumping = true;
+ } else {
+ kvm_s390_vcpu_unblock_all(kvm);
+ r = -EINVAL;
+ }
+ break;
+ }
+ case KVM_PV_DUMP_CONFIG_STOR_STATE: {
+ if (!kvm->arch.pv.dumping)
+ break;
+
+ /*
+ * gaddr is an output parameter since we might stop
+ * early. As dmp will be copied back in our caller, we
+ * don't need to do it ourselves.
+ */
+ r = kvm_s390_pv_dump_stor_state(kvm, result_buff, &dmp.gaddr, dmp.buff_len,
+ &cmd->rc, &cmd->rrc);
+ break;
+ }
+ case KVM_PV_DUMP_COMPLETE: {
+ if (!kvm->arch.pv.dumping)
+ break;
+
+ r = -EINVAL;
+ if (dmp.buff_len < uv_info.conf_dump_finalize_len)
+ break;
+
+ r = kvm_s390_pv_dump_complete(kvm, result_buff,
+ &cmd->rc, &cmd->rrc);
+ break;
+ }
+ default:
+ r = -ENOTTY;
+ break;
+ }
+
+ return r;
+}
+
static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
{
+ const bool need_lock = (cmd->cmd != KVM_PV_ASYNC_CLEANUP_PERFORM);
+ void __user *argp = (void __user *)cmd->data;
int r = 0;
u16 dummy;
- void __user *argp = (void __user *)cmd->data;
+
+ if (need_lock)
+ mutex_lock(&kvm->lock);
switch (cmd->cmd) {
case KVM_PV_ENABLE: {
@@ -2240,9 +2674,9 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
if (r)
break;
- mmap_write_lock(current->mm);
- r = gmap_mark_unmergeable();
- mmap_write_unlock(current->mm);
+ mmap_write_lock(kvm->mm);
+ r = gmap_helper_disable_cow_sharing();
+ mmap_write_unlock(kvm->mm);
if (r)
break;
@@ -2258,6 +2692,31 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
set_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
break;
}
+ case KVM_PV_ASYNC_CLEANUP_PREPARE:
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm) || !async_destroy)
+ break;
+
+ r = kvm_s390_cpus_from_pv(kvm, &cmd->rc, &cmd->rrc);
+ /*
+ * If a CPU could not be destroyed, destroy VM will also fail.
+ * There is no point in trying to destroy it. Instead return
+ * the rc and rrc from the first CPU that failed destroying.
+ */
+ if (r)
+ break;
+ r = kvm_s390_pv_set_aside(kvm, &cmd->rc, &cmd->rrc);
+
+ /* no need to block service interrupts any more */
+ clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
+ break;
+ case KVM_PV_ASYNC_CLEANUP_PERFORM:
+ r = -EINVAL;
+ if (!async_destroy)
+ break;
+ /* kvm->lock must not be held; this is asserted inside the function. */
+ r = kvm_s390_pv_deinit_aside_vm(kvm, &cmd->rc, &cmd->rrc);
+ break;
case KVM_PV_DISABLE: {
r = -EINVAL;
if (!kvm_s390_pv_is_protected(kvm))
@@ -2271,7 +2730,7 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
*/
if (r)
break;
- r = kvm_s390_pv_deinit_vm(kvm, &cmd->rc, &cmd->rrc);
+ r = kvm_s390_pv_deinit_cleanup_all(kvm, &cmd->rc, &cmd->rrc);
/* no need to block service interrupts any more */
clear_bit(IRQ_PEND_EXT_SERVICE, &kvm->arch.float_int.masked_irqs);
@@ -2356,47 +2815,104 @@ static int kvm_s390_handle_pv(struct kvm *kvm, struct kvm_pv_cmd *cmd)
cmd->rc, cmd->rrc);
break;
}
+ case KVM_PV_INFO: {
+ struct kvm_s390_pv_info info = {};
+ ssize_t data_len;
+
+ /*
+ * No need to check the VM protection here.
+ *
+ * Maybe user space wants to query some of the data
+ * when the VM is still unprotected. If we see the
+ * need to fence a new data command we can still
+ * return an error in the info handler.
+ */
+
+ r = -EFAULT;
+ if (copy_from_user(&info, argp, sizeof(info.header)))
+ break;
+
+ r = -EINVAL;
+ if (info.header.len_max < sizeof(info.header))
+ break;
+
+ data_len = kvm_s390_handle_pv_info(&info);
+ if (data_len < 0) {
+ r = data_len;
+ break;
+ }
+ /*
+ * If a data command struct is extended (multiple
+ * times) this can be used to determine how much of it
+ * is valid.
+ */
+ info.header.len_written = data_len;
+
+ r = -EFAULT;
+ if (copy_to_user(argp, &info, data_len))
+ break;
+
+ r = 0;
+ break;
+ }
+ case KVM_PV_DUMP: {
+ struct kvm_s390_pv_dmp dmp;
+
+ r = -EINVAL;
+ if (!kvm_s390_pv_is_protected(kvm))
+ break;
+
+ r = -EFAULT;
+ if (copy_from_user(&dmp, argp, sizeof(dmp)))
+ break;
+
+ r = kvm_s390_pv_dmp(kvm, cmd, dmp);
+ if (r)
+ break;
+
+ if (copy_to_user(argp, &dmp, sizeof(dmp))) {
+ r = -EFAULT;
+ break;
+ }
+
+ break;
+ }
default:
r = -ENOTTY;
}
- return r;
-}
+ if (need_lock)
+ mutex_unlock(&kvm->lock);
-static bool access_key_invalid(u8 access_key)
-{
- return access_key > 0xf;
+ return r;
}
-static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+static int mem_op_validate_common(struct kvm_s390_mem_op *mop, u64 supported_flags)
{
- void __user *uaddr = (void __user *)mop->buf;
- u64 supported_flags;
- void *tmpbuf = NULL;
- int r, srcu_idx;
-
- supported_flags = KVM_S390_MEMOP_F_SKEY_PROTECTION
- | KVM_S390_MEMOP_F_CHECK_ONLY;
if (mop->flags & ~supported_flags || !mop->size)
return -EINVAL;
if (mop->size > MEM_OP_MAX_SIZE)
return -E2BIG;
- /*
- * This is technically a heuristic only, if the kvm->lock is not
- * taken, it is not guaranteed that the vm is/remains non-protected.
- * This is ok from a kernel perspective, wrongdoing is detected
- * on the access, -EFAULT is returned and the vm may crash the
- * next time it accesses the memory in question.
- * There is no sane usecase to do switching and a memop on two
- * different CPUs at the same time.
- */
- if (kvm_s390_pv_get_handle(kvm))
- return -EINVAL;
if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) {
- if (access_key_invalid(mop->key))
+ if (mop->key > 0xf)
return -EINVAL;
} else {
mop->key = 0;
}
+ return 0;
+}
+
+static int kvm_s390_vm_mem_op_abs(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+ void __user *uaddr = (void __user *)mop->buf;
+ enum gacc_mode acc_mode;
+ void *tmpbuf = NULL;
+ int r, srcu_idx;
+
+ r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION |
+ KVM_S390_MEMOP_F_CHECK_ONLY);
+ if (r)
+ return r;
+
if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
tmpbuf = vmalloc(mop->size);
if (!tmpbuf)
@@ -2405,40 +2921,30 @@ static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
srcu_idx = srcu_read_lock(&kvm->srcu);
- if (kvm_is_error_gpa(kvm, mop->gaddr)) {
+ if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) {
r = PGM_ADDRESSING;
goto out_unlock;
}
- switch (mop->op) {
- case KVM_S390_MEMOP_ABSOLUTE_READ: {
- if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_FETCH, mop->key);
- } else {
- r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
- mop->size, GACC_FETCH, mop->key);
- if (r == 0) {
- if (copy_to_user(uaddr, tmpbuf, mop->size))
- r = -EFAULT;
- }
- }
- break;
+ acc_mode = mop->op == KVM_S390_MEMOP_ABSOLUTE_READ ? GACC_FETCH : GACC_STORE;
+ if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
+ r = check_gpa_range(kvm, mop->gaddr, mop->size, acc_mode, mop->key);
+ goto out_unlock;
}
- case KVM_S390_MEMOP_ABSOLUTE_WRITE: {
- if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gpa_range(kvm, mop->gaddr, mop->size, GACC_STORE, mop->key);
- } else {
- if (copy_from_user(tmpbuf, uaddr, mop->size)) {
- r = -EFAULT;
- break;
- }
- r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
- mop->size, GACC_STORE, mop->key);
+ if (acc_mode == GACC_FETCH) {
+ r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+ mop->size, GACC_FETCH, mop->key);
+ if (r)
+ goto out_unlock;
+ if (copy_to_user(uaddr, tmpbuf, mop->size))
+ r = -EFAULT;
+ } else {
+ if (copy_from_user(tmpbuf, uaddr, mop->size)) {
+ r = -EFAULT;
+ goto out_unlock;
}
- break;
- }
- default:
- r = -EINVAL;
+ r = access_guest_abs_with_key(kvm, mop->gaddr, tmpbuf,
+ mop->size, GACC_STORE, mop->key);
}
out_unlock:
@@ -2448,8 +2954,76 @@ out_unlock:
return r;
}
-long kvm_arch_vm_ioctl(struct file *filp,
- unsigned int ioctl, unsigned long arg)
+static int kvm_s390_vm_mem_op_cmpxchg(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+ void __user *uaddr = (void __user *)mop->buf;
+ void __user *old_addr = (void __user *)mop->old_addr;
+ union {
+ __uint128_t quad;
+ char raw[sizeof(__uint128_t)];
+ } old = { .quad = 0}, new = { .quad = 0 };
+ unsigned int off_in_quad = sizeof(new) - mop->size;
+ int r, srcu_idx;
+ bool success;
+
+ r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_SKEY_PROTECTION);
+ if (r)
+ return r;
+ /*
+ * This validates off_in_quad. Checking that size is a power
+ * of two is not necessary, as cmpxchg_guest_abs_with_key
+ * takes care of that
+ */
+ if (mop->size > sizeof(new))
+ return -EINVAL;
+ if (copy_from_user(&new.raw[off_in_quad], uaddr, mop->size))
+ return -EFAULT;
+ if (copy_from_user(&old.raw[off_in_quad], old_addr, mop->size))
+ return -EFAULT;
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+
+ if (!kvm_is_gpa_in_memslot(kvm, mop->gaddr)) {
+ r = PGM_ADDRESSING;
+ goto out_unlock;
+ }
+
+ r = cmpxchg_guest_abs_with_key(kvm, mop->gaddr, mop->size, &old.quad,
+ new.quad, mop->key, &success);
+ if (!success && copy_to_user(old_addr, &old.raw[off_in_quad], mop->size))
+ r = -EFAULT;
+
+out_unlock:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+ return r;
+}
+
+static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+ /*
+ * This is technically a heuristic only, if the kvm->lock is not
+ * taken, it is not guaranteed that the vm is/remains non-protected.
+ * This is ok from a kernel perspective, wrongdoing is detected
+ * on the access, -EFAULT is returned and the vm may crash the
+ * next time it accesses the memory in question.
+ * There is no sane usecase to do switching and a memop on two
+ * different CPUs at the same time.
+ */
+ if (kvm_s390_pv_get_handle(kvm))
+ return -EINVAL;
+
+ switch (mop->op) {
+ case KVM_S390_MEMOP_ABSOLUTE_READ:
+ case KVM_S390_MEMOP_ABSOLUTE_WRITE:
+ return kvm_s390_vm_mem_op_abs(kvm, mop);
+ case KVM_S390_MEMOP_ABSOLUTE_CMPXCHG:
+ return kvm_s390_vm_mem_op_cmpxchg(kvm, mop);
+ default:
+ return -EINVAL;
+ }
+}
+
+int 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;
@@ -2467,14 +3041,9 @@ long kvm_arch_vm_ioctl(struct file *filp,
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);
- }
+ if (kvm->arch.use_irqchip)
+ r = 0;
break;
}
case KVM_SET_DEVICE_ATTR: {
@@ -2563,9 +3132,8 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EINVAL;
break;
}
- mutex_lock(&kvm->lock);
+ /* must be called without kvm->lock */
r = kvm_s390_handle_pv(kvm, &args);
- mutex_unlock(&kvm->lock);
if (copy_to_user(argp, &args, sizeof(args))) {
r = -EFAULT;
break;
@@ -2581,6 +3149,19 @@ long kvm_arch_vm_ioctl(struct file *filp,
r = -EFAULT;
break;
}
+ case KVM_S390_ZPCI_OP: {
+ struct kvm_s390_zpci_op args;
+
+ r = -EINVAL;
+ if (!IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+ break;
+ if (copy_from_user(&args, argp, sizeof(args))) {
+ r = -EFAULT;
+ break;
+ }
+ r = kvm_s390_pci_zpci_op(kvm, &args);
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -2610,7 +3191,7 @@ static int kvm_s390_apxa_installed(void)
*/
static void kvm_s390_set_crycb_format(struct kvm *kvm)
{
- kvm->arch.crypto.crycbd = (__u32)(unsigned long) kvm->arch.crypto.crycb;
+ kvm->arch.crypto.crycbd = virt_to_phys(kvm->arch.crypto.crycb);
/* Clear the CRYCB format bits - i.e., set format 0 by default */
kvm->arch.crypto.crycbd &= ~(CRYCB_FORMAT_MASK);
@@ -2742,6 +3323,14 @@ static void sca_dispose(struct kvm *kvm)
kvm->arch.sca = NULL;
}
+void kvm_arch_free_vm(struct kvm *kvm)
+{
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM))
+ kvm_s390_pci_clear_list(kvm);
+
+ __kvm_arch_free_vm(kvm);
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
gfp_t alloc_flags = GFP_KERNEL_ACCOUNT;
@@ -2811,7 +3400,7 @@ 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);
}
@@ -2822,8 +3411,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.model.cpuid = kvm_s390_get_initial_cpuid();
kvm->arch.model.ibc = sclp.ibc & 0x0fff;
+ kvm->arch.model.uv_feat_guest.feat = 0;
+
kvm_s390_crypto_init(kvm);
+ if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV_KVM)) {
+ mutex_lock(&kvm->lock);
+ kvm_s390_pci_init_list(kvm);
+ kvm_s390_vcpu_pci_enable_interp(kvm);
+ mutex_unlock(&kvm->lock);
+ }
+
mutex_init(&kvm->arch.float_int.ais_lock);
spin_lock_init(&kvm->arch.float_int.lock);
for (i = 0; i < FIRQ_LIST_COUNT; i++)
@@ -2835,8 +3433,20 @@ 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;
@@ -2856,7 +3466,9 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm_s390_vsie_init(kvm);
if (use_gisa)
kvm_s390_gisa_init(kvm);
- KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
+ INIT_LIST_HEAD(&kvm->arch.pv.need_cleanup);
+ kvm->arch.pv.set_aside = NULL;
+ KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
return 0;
out_err:
@@ -2877,6 +3489,7 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
kvm_clear_async_pf_completion_queue(vcpu);
if (!kvm_is_ucontrol(vcpu->kvm))
sca_del_vcpu(vcpu);
+ kvm_s390_update_topology_change_report(vcpu->kvm, 1);
if (kvm_is_ucontrol(vcpu->kvm))
gmap_remove(vcpu->arch.gmap);
@@ -2899,11 +3512,18 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
/*
* We are already at the end of life and kvm->lock is not taken.
* This is ok as the file descriptor is closed by now and nobody
- * can mess with the pv state. To avoid lockdep_assert_held from
- * complaining we do not use kvm_s390_pv_is_protected.
+ * can mess with the pv state.
*/
- if (kvm_s390_pv_get_handle(kvm))
- kvm_s390_pv_deinit_vm(kvm, &rc, &rrc);
+ kvm_s390_pv_deinit_cleanup_all(kvm, &rc, &rrc);
+ /*
+ * Remove the mmu notifier only when the whole KVM VM is torn down,
+ * and only if one was registered to begin with. If the VM is
+ * currently not protected, but has been previously been protected,
+ * then it's possible that the notifier is still registered.
+ */
+ if (kvm->arch.pv.mmu_notifier.ops)
+ mmu_notifier_unregister(&kvm->arch.pv.mmu_notifier, kvm->mm);
+
debug_unregister(kvm->arch.dbf);
free_page((unsigned long)kvm->arch.sie_page2);
if (!kvm_is_ucontrol(kvm))
@@ -2911,7 +3531,7 @@ 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 */
@@ -2947,28 +3567,30 @@ static void sca_del_vcpu(struct kvm_vcpu *vcpu)
static void sca_add_vcpu(struct kvm_vcpu *vcpu)
{
if (!kvm_s390_use_sca_entries()) {
- struct bsca_block *sca = vcpu->kvm->arch.sca;
+ phys_addr_t sca_phys = virt_to_phys(vcpu->kvm->arch.sca);
/* we still need the basic sca for the ipte control */
- vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ vcpu->arch.sie_block->scaoh = sca_phys >> 32;
+ vcpu->arch.sie_block->scaol = sca_phys;
return;
}
read_lock(&vcpu->kvm->arch.sca_lock);
if (vcpu->kvm->arch.use_esca) {
struct esca_block *sca = vcpu->kvm->arch.sca;
+ phys_addr_t sca_phys = virt_to_phys(sca);
- sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
- vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)sca & ~0x3fU;
+ sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block);
+ vcpu->arch.sie_block->scaoh = sca_phys >> 32;
+ vcpu->arch.sie_block->scaol = sca_phys & ESCA_SCAOL_MASK;
vcpu->arch.sie_block->ecb2 |= ECB2_ESCA;
set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
} else {
struct bsca_block *sca = vcpu->kvm->arch.sca;
+ phys_addr_t sca_phys = virt_to_phys(sca);
- sca->cpu[vcpu->vcpu_id].sda = (__u64) vcpu->arch.sie_block;
- vcpu->arch.sie_block->scaoh = (__u32)(((__u64)sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)sca;
+ sca->cpu[vcpu->vcpu_id].sda = virt_to_phys(vcpu->arch.sie_block);
+ vcpu->arch.sie_block->scaoh = sca_phys >> 32;
+ vcpu->arch.sie_block->scaol = sca_phys;
set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
}
read_unlock(&vcpu->kvm->arch.sca_lock);
@@ -2999,6 +3621,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
struct kvm_vcpu *vcpu;
unsigned long vcpu_idx;
u32 scaol, scaoh;
+ phys_addr_t new_sca_phys;
if (kvm->arch.use_esca)
return 0;
@@ -3007,8 +3630,9 @@ static int sca_switch_to_extended(struct kvm *kvm)
if (!new_sca)
return -ENOMEM;
- scaoh = (u32)((u64)(new_sca) >> 32);
- scaol = (u32)(u64)(new_sca) & ~0x3fU;
+ new_sca_phys = virt_to_phys(new_sca);
+ scaoh = new_sca_phys >> 32;
+ scaol = new_sca_phys & ESCA_SCAOL_MASK;
kvm_s390_vcpu_block_all(kvm);
write_lock(&kvm->arch.sca_lock);
@@ -3028,7 +3652,7 @@ 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;
}
@@ -3047,9 +3671,7 @@ static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
if (!sclp.has_esca || !sclp.has_64bscao)
return false;
- mutex_lock(&kvm->lock);
rc = kvm->arch.use_esca ? 0 : sca_switch_to_extended(kvm);
- mutex_unlock(&kvm->lock);
return rc == 0 && id < KVM_S390_ESCA_CPU_SLOTS;
}
@@ -3144,7 +3766,6 @@ __u64 kvm_s390_get_cpu_timer(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
- gmap_enable(vcpu->arch.enabled_gmap);
kvm_s390_set_cpuflags(vcpu, CPUSTAT_RUNNING);
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__start_cpu_timer_accounting(vcpu);
@@ -3157,8 +3778,6 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
if (vcpu->arch.cputm_enabled && !is_vcpu_idle(vcpu))
__stop_cpu_timer_accounting(vcpu);
kvm_s390_clear_cpuflags(vcpu, CPUSTAT_RUNNING);
- vcpu->arch.enabled_gmap = gmap_get_enabled();
- gmap_disable(vcpu->arch.enabled_gmap);
}
@@ -3176,8 +3795,6 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
}
if (test_kvm_facility(vcpu->kvm, 74) || vcpu->kvm->arch.user_instr0)
vcpu->arch.sie_block->ictl |= ICTL_OPEREXC;
- /* make vcpu_load load the right gmap on the first trigger */
- vcpu->arch.enabled_gmap = vcpu->arch.gmap;
}
static bool kvm_has_pckmo_subfunc(struct kvm *kvm, unsigned long nr)
@@ -3199,6 +3816,13 @@ static bool kvm_has_pckmo_ecc(struct kvm *kvm)
}
+static bool kvm_has_pckmo_hmac(struct kvm *kvm)
+{
+ /* At least one HMAC subfunction must be present */
+ return kvm_has_pckmo_subfunc(kvm, 118) ||
+ kvm_has_pckmo_subfunc(kvm, 122);
+}
+
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
{
/*
@@ -3211,7 +3835,7 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->crycbd = vcpu->kvm->arch.crypto.crycbd;
vcpu->arch.sie_block->ecb3 &= ~(ECB3_AES | ECB3_DEA);
vcpu->arch.sie_block->eca &= ~ECA_APIE;
- vcpu->arch.sie_block->ecd &= ~ECD_ECC;
+ vcpu->arch.sie_block->ecd &= ~(ECD_ECC | ECD_HMAC);
if (vcpu->kvm->arch.crypto.apie)
vcpu->arch.sie_block->eca |= ECA_APIE;
@@ -3219,9 +3843,11 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
/* Set up protected key support */
if (vcpu->kvm->arch.crypto.aes_kw) {
vcpu->arch.sie_block->ecb3 |= ECB3_AES;
- /* ecc is also wrapped with AES key */
+ /* ecc/hmac is also wrapped with AES key */
if (kvm_has_pckmo_ecc(vcpu->kvm))
vcpu->arch.sie_block->ecd |= ECD_ECC;
+ if (kvm_has_pckmo_hmac(vcpu->kvm))
+ vcpu->arch.sie_block->ecd |= ECD_HMAC;
}
if (vcpu->kvm->arch.crypto.dea_kw)
@@ -3230,15 +3856,18 @@ static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
void kvm_s390_vcpu_unsetup_cmma(struct kvm_vcpu *vcpu)
{
- free_page(vcpu->arch.sie_block->cbrlo);
+ free_page((unsigned long)phys_to_virt(vcpu->arch.sie_block->cbrlo));
vcpu->arch.sie_block->cbrlo = 0;
}
int kvm_s390_vcpu_setup_cmma(struct kvm_vcpu *vcpu)
{
- vcpu->arch.sie_block->cbrlo = get_zeroed_page(GFP_KERNEL_ACCOUNT);
- if (!vcpu->arch.sie_block->cbrlo)
+ void *cbrlo_page = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+
+ if (!cbrlo_page)
return -ENOMEM;
+
+ vcpu->arch.sie_block->cbrlo = virt_to_phys(cbrlo_page);
return 0;
}
@@ -3248,7 +3877,7 @@ static void kvm_s390_vcpu_setup_model(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->ibc = model->ibc;
if (test_kvm_facility(vcpu->kvm, 7))
- vcpu->arch.sie_block->fac = (u32)(u64) model->fac_list;
+ vcpu->arch.sie_block->fac = virt_to_phys(model->fac_list);
}
static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
@@ -3267,11 +3896,13 @@ 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;
+ if (test_kvm_facility(vcpu->kvm, 11))
+ vcpu->arch.sie_block->ecb |= ECB_PTF;
if (test_kvm_facility(vcpu->kvm, 73))
vcpu->arch.sie_block->ecb |= ECB_TE;
if (!kvm_is_ucontrol(vcpu->kvm))
@@ -3303,9 +3934,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 3, "AIV gisa format-%u enabled for cpu %03u",
vcpu->arch.sie_block->gd & 0x3, vcpu->vcpu_id);
}
- vcpu->arch.sie_block->sdnxo = ((unsigned long) &vcpu->run->s.regs.sdnx)
- | SDNXC;
- vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
+ vcpu->arch.sie_block->sdnxo = virt_to_phys(&vcpu->run->s.regs.sdnx) | SDNXC;
+ vcpu->arch.sie_block->riccbd = virt_to_phys(&vcpu->run->s.regs.riccb);
if (sclp.has_kss)
kvm_s390_set_cpuflags(vcpu, CPUSTAT_KSS);
@@ -3317,13 +3947,15 @@ 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;
kvm_s390_vcpu_crypto_setup(vcpu);
+ kvm_s390_vcpu_pci_setup(vcpu);
+
mutex_lock(&vcpu->kvm->lock);
if (kvm_s390_pv_is_protected(vcpu->kvm)) {
rc = kvm_s390_pv_create_cpu(vcpu, &uvrc, &uvrrc);
@@ -3353,7 +3985,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
return -ENOMEM;
vcpu->arch.sie_block = &sie_page->sie_block;
- vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
+ vcpu->arch.sie_block->itdba = virt_to_phys(&sie_page->itdb);
/* the real guest size will always be smaller than msl */
vcpu->arch.sie_block->mso = 0;
@@ -3373,6 +4005,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT |
KVM_SYNC_DIAG318;
+ vcpu->arch.acrs_loaded = false;
kvm_s390_set_prefix(vcpu, 0);
if (test_kvm_facility(vcpu->kvm, 64))
vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
@@ -3383,9 +4016,9 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
if (test_kvm_facility(vcpu->kvm, 156))
vcpu->run->kvm_valid_regs |= KVM_SYNC_ETOKEN;
/* fprs can be synchronized via vrs, even if the guest has no vx. With
- * MACHINE_HAS_VX, (load|store)_fpu_regs() will work with vrs format.
+ * cpu_has_vx(), (load|store)_fpu_regs() will work with vrs format.
*/
- if (MACHINE_HAS_VX)
+ if (cpu_has_vx())
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
else
vcpu->run->kvm_valid_regs |= KVM_SYNC_FPRS;
@@ -3396,13 +4029,15 @@ 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);
rc = kvm_s390_vcpu_setup(vcpu);
if (rc)
goto out_ucontrol_uninit;
+
+ kvm_s390_update_topology_change_report(vcpu->kvm, 1);
return 0;
out_ucontrol_uninit:
@@ -3479,6 +4114,8 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
unsigned long prefix;
unsigned long i;
+ trace_kvm_s390_gmap_notifier(start, end, gmap_is_shadow(gmap));
+
if (gmap_is_shadow(gmap))
return;
if (start >= 1UL << 31)
@@ -3498,7 +4135,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
{
/* do not poll with more than halt_poll_max_steal percent of steal time */
- if (S390_lowcore.avg_steal_timer * 100 / (TICK_USEC << 12) >=
+ if (get_lowcore()->avg_steal_timer * 100 / (TICK_USEC << 12) >=
READ_ONCE(halt_poll_max_steal)) {
vcpu->stat.halt_no_poll_steal++;
return true;
@@ -3660,7 +4297,7 @@ static void kvm_arch_vcpu_ioctl_initial_reset(struct kvm_vcpu *vcpu)
vcpu->run->s.regs.fpc = 0;
/*
* Do not reset these registers in the protected case, as some of
- * them are overlayed and they are not accessible in this case
+ * them are overlaid and they are not accessible in this case
* anyway.
*/
if (!kvm_s390_pv_cpu_is_protected(vcpu)) {
@@ -3733,18 +4370,13 @@ int kvm_arch_vcpu_ioctl_set_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
vcpu_load(vcpu);
- if (test_fp_ctl(fpu->fpc)) {
- ret = -EINVAL;
- goto out;
- }
vcpu->run->s.regs.fpc = fpu->fpc;
- if (MACHINE_HAS_VX)
+ if (cpu_has_vx())
convert_fp_to_vx((__vector128 *) vcpu->run->s.regs.vrs,
(freg_t *) fpu->fprs);
else
memcpy(vcpu->run->s.regs.fprs, &fpu->fprs, sizeof(fpu->fprs));
-out:
vcpu_put(vcpu);
return ret;
}
@@ -3753,9 +4385,7 @@ int kvm_arch_vcpu_ioctl_get_fpu(struct kvm_vcpu *vcpu, struct kvm_fpu *fpu)
{
vcpu_load(vcpu);
- /* make sure we have the latest values */
- save_fpu_regs();
- if (MACHINE_HAS_VX)
+ if (cpu_has_vx())
convert_vx_to_fp((freg_t *) fpu->fprs,
(__vector128 *) vcpu->run->s.regs.vrs);
else
@@ -3885,6 +4515,75 @@ 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:
@@ -3900,9 +4599,8 @@ 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;
@@ -3957,8 +4655,6 @@ retry:
goto retry;
}
- /* nothing to do, just clear the request */
- kvm_clear_request(KVM_REQ_UNHALT, vcpu);
/* we left the vsie handler, nothing to do, just clear the request */
kvm_clear_request(KVM_REQ_VSIE_RESTART, vcpu);
@@ -3993,13 +4689,6 @@ static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_t
preempt_enable();
}
-void kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
-{
- mutex_lock(&kvm->lock);
- __kvm_s390_set_tod_clock(kvm, gtod);
- mutex_unlock(&kvm->lock);
-}
-
int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
{
if (!mutex_trylock(&kvm->lock))
@@ -4009,22 +4698,6 @@ int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clo
return 1;
}
-/**
- * kvm_arch_fault_in_page - fault-in guest page if necessary
- * @vcpu: The corresponding virtual cpu
- * @gpa: Guest physical address
- * @writable: Whether the page should be writable or not
- *
- * Make sure that a guest page has been faulted-in on the host.
- *
- * Return: Zero on success, negative error code otherwise.
- */
-long kvm_arch_fault_in_page(struct kvm_vcpu *vcpu, gpa_t gpa, int writable)
-{
- return gmap_fault(vcpu->arch.gmap, gpa,
- writable ? FAULT_FLAG_WRITE : 0);
-}
-
static void __kvm_inject_pfault_token(struct kvm_vcpu *vcpu, bool start_token,
unsigned long token)
{
@@ -4092,12 +4765,11 @@ static bool kvm_arch_setup_async_pf(struct kvm_vcpu *vcpu)
if (!vcpu->arch.gmap->pfault_enabled)
return false;
- hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(current->thread.gmap_addr));
- hva += current->thread.gmap_addr & ~PAGE_MASK;
+ hva = gfn_to_hva(vcpu->kvm, current->thread.gmap_teid.addr);
if (read_guest_real(vcpu, vcpu->arch.pfault_token, &arch.pfault_token, 8))
return false;
- return kvm_setup_async_pf(vcpu, current->thread.gmap_addr, hva, &arch);
+ return kvm_setup_async_pf(vcpu, current->thread.gmap_teid.addr * PAGE_SIZE, hva, &arch);
}
static int vcpu_pre_run(struct kvm_vcpu *vcpu)
@@ -4119,7 +4791,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
if (!kvm_is_ucontrol(vcpu->kvm)) {
rc = kvm_s390_deliver_pending_interrupts(vcpu);
- if (rc)
+ if (rc || guestdbg_exit_pending(vcpu))
return rc;
}
@@ -4135,6 +4807,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
clear_bit(vcpu->vcpu_idx, vcpu->kvm->arch.gisa_int.kicked_mask);
vcpu->arch.sie_block->icptcode = 0;
+ current->thread.gmap_int_code = 0;
cpuflags = atomic_read(&vcpu->arch.sie_block->cpuflags);
VCPU_EVENT(vcpu, 6, "entering sie flags %x", cpuflags);
trace_kvm_s390_sie_enter(vcpu, cpuflags);
@@ -4142,7 +4815,7 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
return 0;
}
-static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
+static int vcpu_post_run_addressing_exception(struct kvm_vcpu *vcpu)
{
struct kvm_s390_pgm_info pgm_info = {
.code = PGM_ADDRESSING,
@@ -4178,10 +4851,182 @@ static int vcpu_post_run_fault_in_sie(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;
+
+ gaddr = current->thread.gmap_teid.addr * PAGE_SIZE;
+ if (kvm_s390_cur_gmap_fault_is_write())
+ flags = FAULT_FLAG_WRITE;
+
+ switch (current->thread.gmap_int_code & PGM_INT_CODE_MASK) {
+ case 0:
+ vcpu->stat.exit_null++;
+ break;
+ case PGM_SECURE_STORAGE_ACCESS:
+ case PGM_SECURE_STORAGE_VIOLATION:
+ 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
+ * previous protected guest. The old pages need to be destroyed
+ * so the new guest can use them.
+ */
+ if (kvm_s390_pv_destroy_page(vcpu->kvm, gaddr)) {
+ /*
+ * Either KVM messed up the secure guest mapping or the
+ * same page is mapped into multiple secure guests.
+ *
+ * This exception is only triggered when a guest 2 is
+ * running and can therefore never occur in kernel
+ * context.
+ */
+ pr_warn_ratelimited("Secure storage violation (%x) in task: %s, pid %d\n",
+ current->thread.gmap_int_code, current->comm,
+ current->pid);
+ 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 = kvm_s390_pv_convert_to_secure(vcpu->kvm, 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:
+ case PGM_ASCE_TYPE:
+ case PGM_REGION_FIRST_TRANS:
+ case PGM_REGION_SECOND_TRANS:
+ case PGM_REGION_THIRD_TRANS:
+ 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 0;
+}
+
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
struct mcck_volatile_info *mcck_info;
struct sie_page *sie_page;
+ int rc;
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
@@ -4203,7 +5048,7 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
}
if (vcpu->arch.sie_block->icptcode > 0) {
- int rc = kvm_handle_sie_intercept(vcpu);
+ rc = kvm_handle_sie_intercept(vcpu);
if (rc != -EOPNOTSUPP)
return rc;
@@ -4212,24 +5057,9 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
vcpu->run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
vcpu->run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
return -EREMOTE;
- } else if (exit_reason != -EFAULT) {
- vcpu->stat.exit_null++;
- return 0;
- } else if (kvm_is_ucontrol(vcpu->kvm)) {
- vcpu->run->exit_reason = KVM_EXIT_S390_UCONTROL;
- vcpu->run->s390_ucontrol.trans_exc_code =
- current->thread.gmap_addr;
- vcpu->run->s390_ucontrol.pgm_code = 0x10;
- return -EREMOTE;
- } else if (current->thread.gmap_pfault) {
- trace_kvm_s390_major_guest_pfault(vcpu);
- current->thread.gmap_pfault = 0;
- if (kvm_arch_setup_async_pf(vcpu))
- return 0;
- vcpu->stat.pfault_sync++;
- return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
}
- return vcpu_post_run_fault_in_sie(vcpu);
+
+ return vcpu_post_run_handle_fault(vcpu);
}
#define PSW_INT_MASK (PSW_MASK_EXT | PSW_MASK_IO | PSW_MASK_MCHECK)
@@ -4246,7 +5076,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
do {
rc = vcpu_pre_run(vcpu);
- if (rc)
+ if (rc || guestdbg_exit_pending(vcpu))
break;
kvm_vcpu_srcu_read_unlock(vcpu);
@@ -4263,10 +5093,9 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
vcpu->run->s.regs.gprs,
sizeof(sie_page->pv_grregs));
}
- if (test_cpu_flag(CIF_FPU))
- load_fpu_regs();
exit_reason = sie64a(vcpu->arch.sie_block,
- vcpu->run->s.regs.gprs);
+ vcpu->run->s.regs.gprs,
+ vcpu->arch.gmap->asce);
if (kvm_s390_pv_cpu_is_protected(vcpu)) {
memcpy(vcpu->run->s.regs.gprs,
sie_page->pv_grregs,
@@ -4351,9 +5180,9 @@ 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();
- __ctl_set_bit(2, 4);
+ local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
if (current->thread.gs_cb) {
vcpu->arch.host_gscb = current->thread.gs_cb;
save_gs_cb(vcpu->arch.host_gscb);
@@ -4385,19 +5214,8 @@ static void sync_regs(struct kvm_vcpu *vcpu)
}
save_access_regs(vcpu->arch.host_acrs);
restore_access_regs(vcpu->run->s.regs.acrs);
- /* save host (userspace) fprs/vrs */
- save_fpu_regs();
- vcpu->arch.host_fpregs.fpc = current->thread.fpu.fpc;
- vcpu->arch.host_fpregs.regs = current->thread.fpu.regs;
- if (MACHINE_HAS_VX)
- current->thread.fpu.regs = vcpu->run->s.regs.vrs;
- else
- current->thread.fpu.regs = vcpu->run->s.regs.fprs;
- current->thread.fpu.fpc = vcpu->run->s.regs.fpc;
- if (test_fp_ctl(current->thread.fpu.fpc))
- /* User space provided an invalid FPC, let's clear it */
- current->thread.fpu.fpc = 0;
-
+ vcpu->arch.acrs_loaded = true;
+ kvm_s390_fpu_load(vcpu->run);
/* Sync fmt2 only data */
if (likely(!kvm_s390_pv_cpu_is_protected(vcpu))) {
sync_regs_fmt2(vcpu);
@@ -4428,15 +5246,15 @@ 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();
- __ctl_set_bit(2, 4);
+ local_ctl_set_bit(2, CR2_GUARDED_STORAGE_BIT);
if (vcpu->arch.gs_enabled)
save_gs_cb(current->thread.gs_cb);
current->thread.gs_cb = vcpu->arch.host_gscb;
restore_gs_cb(vcpu->arch.host_gscb);
if (!vcpu->arch.host_gscb)
- __ctl_clear_bit(2, 4);
+ local_ctl_clear_bit(2, CR2_GUARDED_STORAGE_BIT);
vcpu->arch.host_gscb = NULL;
preempt_enable();
}
@@ -4458,12 +5276,8 @@ static void store_regs(struct kvm_vcpu *vcpu)
kvm_run->s.regs.pfc = vcpu->arch.pfault_compare;
save_access_regs(vcpu->run->s.regs.acrs);
restore_access_regs(vcpu->arch.host_acrs);
- /* Save guest register state */
- save_fpu_regs();
- vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
- /* Restore will be done lazily at return */
- current->thread.fpu.fpc = vcpu->arch.host_fpregs.fpc;
- current->thread.fpu.regs = vcpu->arch.host_fpregs.regs;
+ vcpu->arch.acrs_loaded = false;
+ kvm_s390_fpu_store(vcpu->run);
if (likely(!kvm_s390_pv_cpu_is_protected(vcpu)))
store_regs_fmt2(vcpu);
}
@@ -4471,9 +5285,19 @@ static void store_regs(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_run *kvm_run = vcpu->run;
+ DECLARE_KERNEL_FPU_ONSTACK32(fpu);
int rc;
- if (kvm_run->immediate_exit)
+ /*
+ * Running a VM while dumping always has the potential to
+ * produce inconsistent dump data. But for PV vcpus a SIE
+ * entry while dumping could also lead to a fatal validity
+ * intercept which we absolutely want to avoid.
+ */
+ if (vcpu->kvm->arch.pv.dumping)
+ return -EINVAL;
+
+ if (!vcpu->wants_to_run)
return -EINTR;
if (kvm_run->kvm_valid_regs & ~KVM_SYNC_S390_VALID_FIELDS ||
@@ -4503,6 +5327,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
goto out;
}
+ kernel_fpu_begin(&fpu, KERNEL_FPC | KERNEL_VXR);
sync_regs(vcpu);
enable_cpu_timer_accounting(vcpu);
@@ -4526,6 +5351,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
disable_cpu_timer_accounting(vcpu);
store_regs(vcpu);
+ kernel_fpu_end(&fpu, KERNEL_FPC | KERNEL_VXR);
kvm_sigset_deactivate(vcpu);
@@ -4562,7 +5388,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
gpa -= __LC_FPREGS_SAVE_AREA;
/* manually convert vector registers if necessary */
- if (MACHINE_HAS_VX) {
+ if (cpu_has_vx()) {
convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
fprs, 128);
@@ -4600,8 +5426,7 @@ int kvm_s390_vcpu_store_status(struct kvm_vcpu *vcpu, unsigned long addr)
* switch in the run ioctl. Let's update our copies before we save
* it into the save area
*/
- save_fpu_regs();
- vcpu->run->s.regs.fpc = current->thread.fpu.fpc;
+ kvm_s390_fpu_store(vcpu->run);
save_access_regs(vcpu->run->s.regs.acrs);
return kvm_s390_store_status_unloaded(vcpu, addr);
@@ -4768,6 +5593,7 @@ static long kvm_s390_vcpu_sida_op(struct kvm_vcpu *vcpu,
struct kvm_s390_mem_op *mop)
{
void __user *uaddr = (void __user *)mop->buf;
+ void *sida_addr;
int r = 0;
if (mop->flags || !mop->size)
@@ -4779,16 +5605,16 @@ static long kvm_s390_vcpu_sida_op(struct kvm_vcpu *vcpu,
if (!kvm_s390_pv_cpu_is_protected(vcpu))
return -EINVAL;
+ sida_addr = (char *)sida_addr(vcpu->arch.sie_block) + mop->sida_offset;
+
switch (mop->op) {
case KVM_S390_MEMOP_SIDA_READ:
- if (copy_to_user(uaddr, (void *)(sida_origin(vcpu->arch.sie_block) +
- mop->sida_offset), mop->size))
+ if (copy_to_user(uaddr, sida_addr, mop->size))
r = -EFAULT;
break;
case KVM_S390_MEMOP_SIDA_WRITE:
- if (copy_from_user((void *)(sida_origin(vcpu->arch.sie_block) +
- mop->sida_offset), uaddr, mop->size))
+ if (copy_from_user(sida_addr, uaddr, mop->size))
r = -EFAULT;
break;
}
@@ -4799,62 +5625,54 @@ static long kvm_s390_vcpu_mem_op(struct kvm_vcpu *vcpu,
struct kvm_s390_mem_op *mop)
{
void __user *uaddr = (void __user *)mop->buf;
+ enum gacc_mode acc_mode;
void *tmpbuf = NULL;
- int r = 0;
- const u64 supported_flags = KVM_S390_MEMOP_F_INJECT_EXCEPTION
- | KVM_S390_MEMOP_F_CHECK_ONLY
- | KVM_S390_MEMOP_F_SKEY_PROTECTION;
+ int r;
- if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
+ r = mem_op_validate_common(mop, KVM_S390_MEMOP_F_INJECT_EXCEPTION |
+ KVM_S390_MEMOP_F_CHECK_ONLY |
+ KVM_S390_MEMOP_F_SKEY_PROTECTION);
+ if (r)
+ return r;
+ if (mop->ar >= NUM_ACRS)
return -EINVAL;
- if (mop->size > MEM_OP_MAX_SIZE)
- return -E2BIG;
if (kvm_s390_pv_cpu_is_protected(vcpu))
return -EINVAL;
- if (mop->flags & KVM_S390_MEMOP_F_SKEY_PROTECTION) {
- if (access_key_invalid(mop->key))
- return -EINVAL;
- } else {
- mop->key = 0;
- }
if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
tmpbuf = vmalloc(mop->size);
if (!tmpbuf)
return -ENOMEM;
}
- switch (mop->op) {
- case KVM_S390_MEMOP_LOGICAL_READ:
- if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
- GACC_FETCH, mop->key);
- break;
- }
+ acc_mode = mop->op == KVM_S390_MEMOP_LOGICAL_READ ? GACC_FETCH : GACC_STORE;
+ if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
+ acc_mode, mop->key);
+ goto out_inject;
+ }
+ if (acc_mode == GACC_FETCH) {
r = read_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf,
mop->size, mop->key);
- if (r == 0) {
- if (copy_to_user(uaddr, tmpbuf, mop->size))
- r = -EFAULT;
- }
- break;
- case KVM_S390_MEMOP_LOGICAL_WRITE:
- if (mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY) {
- r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
- GACC_STORE, mop->key);
- break;
+ if (r)
+ goto out_inject;
+ if (copy_to_user(uaddr, tmpbuf, mop->size)) {
+ r = -EFAULT;
+ goto out_free;
}
+ } else {
if (copy_from_user(tmpbuf, uaddr, mop->size)) {
r = -EFAULT;
- break;
+ goto out_free;
}
r = write_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf,
mop->size, mop->key);
- break;
}
+out_inject:
if (r > 0 && (mop->flags & KVM_S390_MEMOP_F_INJECT_EXCEPTION) != 0)
kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+out_free:
vfree(tmpbuf);
return r;
}
@@ -4889,6 +5707,7 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
+ int rc;
switch (ioctl) {
case KVM_S390_IRQ: {
@@ -4896,7 +5715,8 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
if (copy_from_user(&s390irq, argp, sizeof(s390irq)))
return -EFAULT;
- return kvm_s390_inject_vcpu(vcpu, &s390irq);
+ rc = kvm_s390_inject_vcpu(vcpu, &s390irq);
+ break;
}
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
@@ -4906,10 +5726,67 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
return -EFAULT;
if (s390int_to_s390irq(&s390int, &s390irq))
return -EINVAL;
- return kvm_s390_inject_vcpu(vcpu, &s390irq);
+ rc = kvm_s390_inject_vcpu(vcpu, &s390irq);
+ break;
}
+ default:
+ rc = -ENOIOCTLCMD;
+ break;
}
- return -ENOIOCTLCMD;
+
+ /*
+ * To simplify single stepping of userspace-emulated instructions,
+ * KVM_EXIT_S390_SIEIC exit sets KVM_GUESTDBG_EXIT_PENDING (see
+ * should_handle_per_ifetch()). However, if userspace emulation injects
+ * an interrupt, it needs to be cleared, so that KVM_EXIT_DEBUG happens
+ * after (and not before) the interrupt delivery.
+ */
+ if (!rc)
+ vcpu->guest_debug &= ~KVM_GUESTDBG_EXIT_PENDING;
+
+ return rc;
+}
+
+static int kvm_s390_handle_pv_vcpu_dump(struct kvm_vcpu *vcpu,
+ struct kvm_pv_cmd *cmd)
+{
+ struct kvm_s390_pv_dmp dmp;
+ void *data;
+ int ret;
+
+ /* Dump initialization is a prerequisite */
+ if (!vcpu->kvm->arch.pv.dumping)
+ return -EINVAL;
+
+ if (copy_from_user(&dmp, (__u8 __user *)cmd->data, sizeof(dmp)))
+ return -EFAULT;
+
+ /* We only handle this subcmd right now */
+ if (dmp.subcmd != KVM_PV_DUMP_CPU)
+ return -EINVAL;
+
+ /* CPU dump length is the same as create cpu storage donation. */
+ if (dmp.buff_len != uv_info.guest_cpu_stor_len)
+ return -EINVAL;
+
+ data = kvzalloc(uv_info.guest_cpu_stor_len, GFP_KERNEL);
+ if (!data)
+ return -ENOMEM;
+
+ ret = kvm_s390_pv_dump_cpu(vcpu, data, &cmd->rc, &cmd->rrc);
+
+ VCPU_EVENT(vcpu, 3, "PROTVIRT DUMP CPU %d rc %x rrc %x",
+ vcpu->vcpu_id, cmd->rc, cmd->rrc);
+
+ if (ret)
+ ret = -EINVAL;
+
+ /* On success copy over the dump data */
+ if (!ret && copy_to_user((__u8 __user *)dmp.buff_addr, data, uv_info.guest_cpu_stor_len))
+ ret = -EFAULT;
+
+ kvfree(data);
+ return ret;
}
long kvm_arch_vcpu_ioctl(struct file *filp,
@@ -5021,7 +5898,9 @@ 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:
@@ -5076,6 +5955,33 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
irq_state.len);
break;
}
+ case KVM_S390_PV_CPU_COMMAND: {
+ struct kvm_pv_cmd cmd;
+
+ r = -EINVAL;
+ if (!is_prot_virt_host())
+ break;
+
+ r = -EFAULT;
+ if (copy_from_user(&cmd, argp, sizeof(cmd)))
+ break;
+
+ r = -EINVAL;
+ if (cmd.flags)
+ break;
+
+ /* We only handle this cmd right now */
+ if (cmd.cmd != KVM_PV_DUMP)
+ break;
+
+ r = kvm_s390_handle_pv_vcpu_dump(vcpu, &cmd);
+
+ /* Always copy over UV rc / rrc data */
+ if (copy_to_user((__u8 __user *)argp, &cmd.rc,
+ sizeof(cmd.rc) + sizeof(cmd.rrc)))
+ r = -EFAULT;
+ break;
+ }
default:
r = -ENOTTY;
}
@@ -5097,6 +6003,11 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
return VM_FAULT_SIGBUS;
}
+bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
+{
+ return true;
+}
+
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
const struct kvm_memory_slot *old,
@@ -5105,27 +6016,47 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
{
gpa_t size;
+ if (kvm_is_ucontrol(kvm) && new->id < KVM_USER_MEM_SLOTS)
+ return -EINVAL;
+
/* When we are protected, we should not change the memory slots */
if (kvm_s390_pv_get_handle(kvm))
return -EINVAL;
- if (change == KVM_MR_DELETE || change == KVM_MR_FLAGS_ONLY)
- return 0;
+ if (change != KVM_MR_DELETE && change != KVM_MR_FLAGS_ONLY) {
+ /*
+ * A few sanity checks. We can have memory slots which have to be
+ * located/ended at a segment boundary (1MB). The memory in userland is
+ * ok to be fragmented into various different vmas. It is okay to mmap()
+ * and munmap() stuff in this slot after doing this call at any time
+ */
+
+ if (new->userspace_addr & 0xffffful)
+ return -EINVAL;
- /* A few sanity checks. We can have memory slots which have to be
- located/ended at a segment boundary (1MB). The memory in userland is
- ok to be fragmented into various different vmas. It is okay to mmap()
- and munmap() stuff in this slot after doing this call at any time */
+ size = new->npages * PAGE_SIZE;
+ if (size & 0xffffful)
+ return -EINVAL;
- if (new->userspace_addr & 0xffffful)
- return -EINVAL;
+ if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
+ return -EINVAL;
+ }
- size = new->npages * PAGE_SIZE;
- if (size & 0xffffful)
- return -EINVAL;
+ if (!kvm->arch.migration_mode)
+ return 0;
- if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
- return -EINVAL;
+ /*
+ * Turn off migration mode when:
+ * - userspace creates a new memslot with dirty logging off,
+ * - userspace modifies an existing memslot (MOVE or FLAGS_ONLY) and
+ * dirty logging is turned off.
+ * Migration mode expects dirty page logging being enabled to store
+ * its dirty bitmap.
+ */
+ if (change != KVM_MR_DELETE &&
+ !(new->flags & KVM_MEM_LOG_DIRTY_PAGES))
+ WARN(kvm_s390_vm_stop_migration(kvm),
+ "Failed to stop migration mode");
return 0;
}
@@ -5137,6 +6068,9 @@ 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,
@@ -5172,7 +6106,7 @@ static inline unsigned long nonhyp_mask(int i)
static int __init kvm_s390_init(void)
{
- int i;
+ int i, r;
if (!sclp.has_sief2) {
pr_info("SIE is not available\n");
@@ -5188,12 +6122,23 @@ static int __init kvm_s390_init(void)
kvm_s390_fac_base[i] |=
stfle_fac_list[i] & nonhyp_mask(i);
- return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+ r = __kvm_s390_init();
+ if (r)
+ return r;
+
+ r = kvm_init(sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+ if (r) {
+ __kvm_s390_exit();
+ return r;
+ }
+ return 0;
}
static void __exit kvm_s390_exit(void)
{
kvm_exit();
+
+ __kvm_s390_exit();
}
module_init(kvm_s390_init);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.