aboutsummaryrefslogtreecommitdiffstats
path: root/arch/s390/kvm/kvm-s390.c
diff options
context:
space:
mode:
Diffstat (limited to '')
-rw-r--r--arch/s390/kvm/kvm-s390.c859
1 files changed, 705 insertions, 154 deletions
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 14a18ba5ff2c..bc491a73815c 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -6,7 +6,6 @@
*
* 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>
*/
@@ -32,6 +31,7 @@
#include <linux/sched/signal.h>
#include <linux/string.h>
#include <linux/pgtable.h>
+#include <linux/mmu_notifier.h>
#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
@@ -48,6 +48,7 @@
#include <asm/fpu/api.h>
#include "kvm-s390.h"
#include "gaccess.h"
+#include "pci.h"
#define CREATE_TRACE_POINTS
#include "trace.h"
@@ -64,7 +65,8 @@ 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)
};
const struct kvm_stats_header kvm_vm_stats_header = {
@@ -295,7 +297,7 @@ static int kvm_clock_sync(struct notifier_block *notifier, unsigned long val,
{
struct kvm *kvm;
struct kvm_vcpu *vcpu;
- int i;
+ unsigned long i;
unsigned long long *delta = v;
list_for_each_entry(kvm, &vm_list, vm_list) {
@@ -503,6 +505,14 @@ int kvm_arch_init(void *opaque)
goto out;
}
+ 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 out;
+ }
+ }
+
rc = kvm_s390_gib_init(GAL_ISC);
if (rc)
goto out;
@@ -517,6 +527,8 @@ out:
void kvm_arch_exit(void)
{
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);
}
@@ -564,6 +576,7 @@ 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:
r = 1;
break;
case KVM_CAP_SET_GUEST_DEBUG2:
@@ -606,6 +619,32 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
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;
}
@@ -682,7 +721,7 @@ out:
static void icpt_operexc_on_all_vcpus(struct kvm *kvm)
{
- unsigned int i;
+ unsigned long i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -817,6 +856,20 @@ 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;
@@ -936,7 +989,7 @@ 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;
+ unsigned long i;
kvm_s390_vcpu_block_all(kvm);
@@ -1019,9 +1072,45 @@ 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)
{
- int cx;
+ unsigned long cx;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(cx, vcpu, kvm)
@@ -1037,13 +1126,13 @@ 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;
+ int bkt;
/* migration mode already enabled */
if (kvm->arch.migration_mode)
return 0;
slots = kvm_memslots(kvm);
- if (!slots || !slots->used_slots)
+ if (!slots || kvm_memslots_empty(slots))
return -EINVAL;
if (!kvm->arch.use_cmma) {
@@ -1051,8 +1140,7 @@ static int kvm_s390_vm_start_migration(struct kvm *kvm)
return 0;
}
/* mark all the pages in active slots as dirty */
- for (slotnr = 0; slotnr < slots->used_slots; slotnr++) {
- ms = slots->memslots + slotnr;
+ kvm_for_each_memslot(ms, bkt, slots) {
if (!ms->dirty_bitmap)
return -EINVAL;
/*
@@ -1119,6 +1207,8 @@ 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;
@@ -1128,7 +1218,7 @@ 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);
@@ -1159,7 +1249,7 @@ 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;
}
@@ -1171,6 +1261,16 @@ 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);
@@ -1185,6 +1285,9 @@ 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;
}
@@ -1333,8 +1436,7 @@ static int kvm_s390_set_processor_feat(struct kvm *kvm,
mutex_unlock(&kvm->lock);
return -EBUSY;
}
- bitmap_copy(kvm->arch.cpu_feat, (unsigned long *) data.feat,
- KVM_S390_VM_CPU_FEAT_NR_BITS);
+ bitmap_from_arr64(kvm->arch.cpu_feat, 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],
@@ -1505,8 +1607,7 @@ static int kvm_s390_get_processor_feat(struct kvm *kvm,
{
struct kvm_s390_vm_cpu_feat data;
- bitmap_copy((unsigned long *) data.feat, kvm->arch.cpu_feat,
- KVM_S390_VM_CPU_FEAT_NR_BITS);
+ bitmap_to_arr64(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",
@@ -1521,9 +1622,7 @@ static int kvm_s390_get_machine_feat(struct kvm *kvm,
{
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);
+ bitmap_to_arr64(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",
@@ -1696,6 +1795,57 @@ static int kvm_s390_get_cpu_model(struct kvm *kvm, struct kvm_device_attr *attr)
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;
+ do {
+ old = READ_ONCE(sca->utility);
+ new = old;
+ new.mtcr = val;
+ } while (cmpxchg(&sca->utility.val, old.val, new.val) != old.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;
@@ -1716,6 +1866,9 @@ 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;
@@ -1741,6 +1894,9 @@ 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;
@@ -1814,6 +1970,9 @@ 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;
@@ -1943,41 +2102,6 @@ out:
/* 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->last_used_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 (start >= slots->used_slots)
- return slots->used_slots - 1;
-
- if (gfn >= memslots[start].base_gfn &&
- gfn < memslots[start].base_gfn + memslots[start].npages) {
- atomic_set(&slots->last_used_slot, start);
- }
-
- return start;
-}
-
static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
u8 *res, unsigned long bufsize)
{
@@ -2001,27 +2125,32 @@ static int kvm_s390_peek_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
return 0;
}
+static struct kvm_memory_slot *gfn_to_memslot_approx(struct kvm_memslots *slots,
+ gfn_t gfn)
+{
+ return ____gfn_to_memslot(slots, gfn, true);
+}
+
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;
+ struct kvm_memory_slot *ms = gfn_to_memslot_approx(slots, cur_gfn);
unsigned long ofs = cur_gfn - ms->base_gfn;
+ struct rb_node *mnode = &ms->gfn_node[slots->node_idx];
if (ms->base_gfn + ms->npages <= cur_gfn) {
- slotidx--;
+ mnode = rb_next(mnode);
/* If we are above the highest slot, wrap around */
- if (slotidx < 0)
- slotidx = slots->used_slots - 1;
+ if (!mnode)
+ mnode = rb_first(&slots->gfn_tree);
- ms = slots->memslots + slotidx;
+ ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
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);
+ while (ofs >= ms->npages && (mnode = rb_next(mnode))) {
+ ms = container_of(mnode, struct kvm_memory_slot, gfn_node[slots->node_idx]);
+ ofs = find_first_bit(kvm_second_dirty_bitmap(ms), ms->npages);
}
return ms->base_gfn + ofs;
}
@@ -2033,7 +2162,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
struct kvm_memslots *slots = kvm_memslots(kvm);
struct kvm_memory_slot *ms;
- if (unlikely(!slots->used_slots))
+ if (unlikely(kvm_memslots_empty(slots)))
return 0;
cur_gfn = kvm_s390_next_dirty_cmma(slots, args->start_gfn);
@@ -2043,7 +2172,7 @@ static int kvm_s390_get_cmma(struct kvm *kvm, struct kvm_s390_cmma_log *args,
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;
+ mem_end = kvm_s390_get_gfn_end(slots);
while (args->count < bufsize) {
hva = gfn_to_hva(kvm, cur_gfn);
@@ -2201,12 +2330,25 @@ 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;
+ unsigned long i;
+ u16 _rc, _rrc;
int ret = 0;
- int i;
/*
* We ignore failures and try to destroy as many CPUs as possible.
@@ -2218,23 +2360,42 @@ 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);
}
+ /* Ensure that we re-enable gisa if the non-PV guest used it but the PV guest did not. */
+ if (use_gisa)
+ kvm_s390_gisa_enable(kvm);
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)
{
- int i, r = 0;
+ unsigned long i;
+ int r = 0;
u16 dummy;
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))
+ kvm_s390_gisa_disable(kvm);
+
kvm_for_each_vcpu(i, vcpu, kvm) {
mutex_lock(&vcpu->mutex);
r = kvm_s390_pv_create_cpu(vcpu, rc, rrc);
@@ -2247,6 +2408,115 @@ 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)
{
int r = 0;
@@ -2383,12 +2653,160 @@ 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;
}
+static bool access_key_invalid(u8 access_key)
+{
+ return access_key > 0xf;
+}
+
+static int kvm_s390_vm_mem_op(struct kvm *kvm, struct kvm_s390_mem_op *mop)
+{
+ 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))
+ return -EINVAL;
+ } else {
+ mop->key = 0;
+ }
+ if (!(mop->flags & KVM_S390_MEMOP_F_CHECK_ONLY)) {
+ tmpbuf = vmalloc(mop->size);
+ if (!tmpbuf)
+ return -ENOMEM;
+ }
+
+ srcu_idx = srcu_read_lock(&kvm->srcu);
+
+ if (kvm_is_error_gpa(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;
+ }
+ 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);
+ }
+ break;
+ }
+ default:
+ r = -EINVAL;
+ }
+
+out_unlock:
+ srcu_read_unlock(&kvm->srcu, srcu_idx);
+
+ vfree(tmpbuf);
+ return r;
+}
+
long kvm_arch_vm_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
@@ -2513,6 +2931,28 @@ long kvm_arch_vm_ioctl(struct file *filp,
}
break;
}
+ case KVM_S390_MEM_OP: {
+ struct kvm_s390_mem_op mem_op;
+
+ if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
+ r = kvm_s390_vm_mem_op(kvm, &mem_op);
+ else
+ 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;
}
@@ -2674,6 +3114,14 @@ 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;
@@ -2756,6 +3204,13 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
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++)
@@ -2809,6 +3264,7 @@ 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);
@@ -2821,27 +3277,11 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
free_page((unsigned long)(vcpu->arch.sie_block));
}
-static void kvm_free_vcpus(struct kvm *kvm)
-{
- unsigned int i;
- struct kvm_vcpu *vcpu;
-
- kvm_for_each_vcpu(i, vcpu, kvm)
- kvm_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)
{
u16 rc, rrc;
- kvm_free_vcpus(kvm);
+ kvm_destroy_vcpus(kvm);
sca_dispose(kvm);
kvm_s390_gisa_destroy(kvm);
/*
@@ -2852,6 +3292,15 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
*/
if (kvm_s390_pv_get_handle(kvm))
kvm_s390_pv_deinit_vm(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))
@@ -2945,7 +3394,7 @@ static int sca_switch_to_extended(struct kvm *kvm)
struct bsca_block *old_sca = kvm->arch.sca;
struct esca_block *new_sca;
struct kvm_vcpu *vcpu;
- unsigned int vcpu_idx;
+ unsigned long vcpu_idx;
u32 scaol, scaoh;
if (kvm->arch.use_esca)
@@ -2995,9 +3444,7 @@ 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;
}
@@ -3220,6 +3667,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
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))
@@ -3272,6 +3721,8 @@ static int kvm_s390_vcpu_setup(struct kvm_vcpu *vcpu)
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);
@@ -3309,9 +3760,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->icpua = vcpu->vcpu_id;
spin_lock_init(&vcpu->arch.local_int.lock);
- vcpu->arch.sie_block->gd = (u32)(u64)vcpu->kvm->arch.gisa_int.origin;
- if (vcpu->arch.sie_block->gd && sclp.has_gisaf)
- vcpu->arch.sie_block->gd |= GISA_FORMAT1;
+ vcpu->arch.sie_block->gd = kvm_s390_get_gisa_desc(vcpu->kvm);
seqcount_init(&vcpu->arch.cputm_seqcount);
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -3353,6 +3802,8 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
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:
@@ -3417,7 +3868,7 @@ void exit_sie(struct kvm_vcpu *vcpu)
/* Kick a guest cpu out of SIE to process a request synchronously */
void kvm_s390_sync_request(int req, struct kvm_vcpu *vcpu)
{
- kvm_make_request(req, vcpu);
+ __kvm_make_request(req, vcpu);
kvm_s390_vcpu_request(vcpu);
}
@@ -3427,7 +3878,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
struct kvm *kvm = gmap->private;
struct kvm_vcpu *vcpu;
unsigned long prefix;
- int i;
+ unsigned long i;
if (gmap_is_shadow(gmap))
return;
@@ -3440,7 +3891,7 @@ static void kvm_gmap_notifier(struct gmap *gmap, unsigned long start,
if (prefix <= end && start <= prefix + 2*PAGE_SIZE - 1) {
VCPU_EVENT(vcpu, 2, "gmap notifier for %lx-%lx",
start, end);
- kvm_s390_sync_request(KVM_REQ_MMU_RELOAD, vcpu);
+ kvm_s390_sync_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
}
}
}
@@ -3449,7 +3900,7 @@ 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) >=
- halt_poll_max_steal) {
+ READ_ONCE(halt_poll_max_steal)) {
vcpu->stat.halt_no_poll_steal++;
return true;
}
@@ -3842,19 +4293,19 @@ retry:
if (!kvm_request_pending(vcpu))
return 0;
/*
- * We use MMU_RELOAD just to re-arm the ipte notifier for the
+ * If the guest prefix changed, re-arm the ipte notifier for the
* guest prefix page. gmap_mprotect_notify will wait on the ptl lock.
* This ensures that the ipte instruction for this request has
* already finished. We might race against a second unmapper that
* wants to set the blocking bit. Lets just retry the request loop.
*/
- if (kvm_check_request(KVM_REQ_MMU_RELOAD, vcpu)) {
+ 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);
if (rc) {
- kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu);
+ kvm_make_request(KVM_REQ_REFRESH_GUEST_PREFIX, vcpu);
return rc;
}
goto retry;
@@ -3907,22 +4358,18 @@ 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);
return 0;
}
-void kvm_s390_set_tod_clock(struct kvm *kvm,
- const struct kvm_s390_vm_tod_clock *gtod)
+static void __kvm_s390_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
{
struct kvm_vcpu *vcpu;
union tod_clock clk;
- int i;
+ unsigned long i;
- mutex_lock(&kvm->lock);
preempt_disable();
store_tod_clock_ext(&clk);
@@ -3943,7 +4390,15 @@ void kvm_s390_set_tod_clock(struct kvm *kvm,
kvm_s390_vcpu_unblock_all(kvm);
preempt_enable();
+}
+
+int kvm_s390_try_set_tod_clock(struct kvm *kvm, const struct kvm_s390_vm_tod_clock *gtod)
+{
+ if (!mutex_trylock(&kvm->lock))
+ return 0;
+ __kvm_s390_set_tod_clock(kvm, gtod);
mutex_unlock(&kvm->lock);
+ return 1;
}
/**
@@ -4179,14 +4634,14 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
* We try to hold kvm->srcu during most of vcpu_run (except when run-
* ning the guest), so that memslots (and other stuff) are protected
*/
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ kvm_vcpu_srcu_read_lock(vcpu);
do {
rc = vcpu_pre_run(vcpu);
if (rc)
break;
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+ kvm_vcpu_srcu_read_unlock(vcpu);
/*
* As PF_VCPU will be used in fault handler, between
* guest_enter and guest_exit should be no uaccess.
@@ -4223,12 +4678,12 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
__enable_cpu_timer_accounting(vcpu);
guest_exit_irqoff();
local_irq_enable();
- vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
+ kvm_vcpu_srcu_read_lock(vcpu);
rc = vcpu_post_run(vcpu, exit_reason);
} while (!signal_pending(current) && !guestdbg_exit_pending(vcpu) && !rc);
- srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
+ kvm_vcpu_srcu_read_unlock(vcpu);
return rc;
}
@@ -4410,6 +4865,15 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
struct kvm_run *kvm_run = vcpu->run;
int rc;
+ /*
+ * 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 (kvm_run->immediate_exit)
return -EINTR;
@@ -4552,7 +5016,7 @@ static void __disable_ibs_on_vcpu(struct kvm_vcpu *vcpu)
static void __disable_ibs_on_all_vcpus(struct kvm *kvm)
{
- unsigned int i;
+ unsigned long i;
struct kvm_vcpu *vcpu;
kvm_for_each_vcpu(i, vcpu, kvm) {
@@ -4590,7 +5054,7 @@ int kvm_s390_vcpu_start(struct kvm_vcpu *vcpu)
}
for (i = 0; i < online_vcpus; i++) {
- if (!is_vcpu_stopped(vcpu->kvm->vcpus[i]))
+ if (!is_vcpu_stopped(kvm_get_vcpu(vcpu->kvm, i)))
started_vcpus++;
}
@@ -4645,16 +5109,23 @@ int kvm_s390_vcpu_stop(struct kvm_vcpu *vcpu)
}
}
- /* SIGP STOP and SIGP STOP AND STORE STATUS has been fully processed */
+ /*
+ * Set the VCPU to STOPPED and THEN clear the interrupt flag,
+ * now that the SIGP STOP and SIGP STOP AND STORE STATUS orders
+ * have been fully processed. This will ensure that the VCPU
+ * is kept BUSY if another VCPU is inquiring with SIGP SENSE.
+ */
+ kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
kvm_s390_clear_stop_irq(vcpu);
- kvm_s390_set_cpuflags(vcpu, CPUSTAT_STOPPED);
__disable_ibs_on_vcpu(vcpu);
for (i = 0; i < online_vcpus; i++) {
- if (!is_vcpu_stopped(vcpu->kvm->vcpus[i])) {
+ struct kvm_vcpu *tmp = kvm_get_vcpu(vcpu->kvm, i);
+
+ if (!is_vcpu_stopped(tmp)) {
started_vcpus++;
- started_vcpu = vcpu->kvm->vcpus[i];
+ started_vcpu = tmp;
}
}
@@ -4694,8 +5165,8 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
return r;
}
-static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu,
- struct kvm_s390_mem_op *mop)
+static long kvm_s390_vcpu_sida_op(struct kvm_vcpu *vcpu,
+ struct kvm_s390_mem_op *mop)
{
void __user *uaddr = (void __user *)mop->buf;
int r = 0;
@@ -4706,6 +5177,8 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu,
return -EINVAL;
if (mop->size + mop->sida_offset > sida_size(vcpu->arch.sie_block))
return -E2BIG;
+ if (!kvm_s390_pv_cpu_is_protected(vcpu))
+ return -EINVAL;
switch (mop->op) {
case KVM_S390_MEMOP_SIDA_READ:
@@ -4722,24 +5195,29 @@ static long kvm_s390_guest_sida_op(struct kvm_vcpu *vcpu,
}
return r;
}
-static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
- struct kvm_s390_mem_op *mop)
+
+static long kvm_s390_vcpu_mem_op(struct kvm_vcpu *vcpu,
+ struct kvm_s390_mem_op *mop)
{
void __user *uaddr = (void __user *)mop->buf;
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_CHECK_ONLY
+ | KVM_S390_MEMOP_F_SKEY_PROTECTION;
if (mop->flags & ~supported_flags || mop->ar >= NUM_ACRS || !mop->size)
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)
@@ -4749,11 +5227,12 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
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);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
+ GACC_FETCH, mop->key);
break;
}
- r = read_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
+ 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;
@@ -4761,15 +5240,16 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
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);
+ r = check_gva_range(vcpu, mop->gaddr, mop->ar, mop->size,
+ GACC_STORE, mop->key);
break;
}
if (copy_from_user(tmpbuf, uaddr, mop->size)) {
r = -EFAULT;
break;
}
- r = write_guest(vcpu, mop->gaddr, mop->ar, tmpbuf, mop->size);
+ r = write_guest_with_key(vcpu, mop->gaddr, mop->ar, tmpbuf,
+ mop->size, mop->key);
break;
}
@@ -4780,8 +5260,8 @@ static long kvm_s390_guest_mem_op(struct kvm_vcpu *vcpu,
return r;
}
-static long kvm_s390_guest_memsida_op(struct kvm_vcpu *vcpu,
- struct kvm_s390_mem_op *mop)
+static long kvm_s390_vcpu_memsida_op(struct kvm_vcpu *vcpu,
+ struct kvm_s390_mem_op *mop)
{
int r, srcu_idx;
@@ -4790,12 +5270,12 @@ static long kvm_s390_guest_memsida_op(struct kvm_vcpu *vcpu,
switch (mop->op) {
case KVM_S390_MEMOP_LOGICAL_READ:
case KVM_S390_MEMOP_LOGICAL_WRITE:
- r = kvm_s390_guest_mem_op(vcpu, mop);
+ r = kvm_s390_vcpu_mem_op(vcpu, mop);
break;
case KVM_S390_MEMOP_SIDA_READ:
case KVM_S390_MEMOP_SIDA_WRITE:
/* we are locked against sida going away by the vcpu->mutex */
- r = kvm_s390_guest_sida_op(vcpu, mop);
+ r = kvm_s390_vcpu_sida_op(vcpu, mop);
break;
default:
r = -EINVAL;
@@ -4833,6 +5313,48 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
return -ENOIOCTLCMD;
}
+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,
unsigned int ioctl, unsigned long arg)
{
@@ -4958,7 +5480,7 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
struct kvm_s390_mem_op mem_op;
if (copy_from_user(&mem_op, argp, sizeof(mem_op)) == 0)
- r = kvm_s390_guest_memsida_op(vcpu, &mem_op);
+ r = kvm_s390_vcpu_memsida_op(vcpu, &mem_op);
else
r = -EFAULT;
break;
@@ -4997,6 +5519,33 @@ 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;
}
@@ -5020,32 +5569,38 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
/* Section: memory related */
int kvm_arch_prepare_memory_region(struct kvm *kvm,
- struct kvm_memory_slot *memslot,
- const struct kvm_userspace_memory_region *mem,
+ const struct kvm_memory_slot *old,
+ struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
+ gpa_t size;
+
+ /* 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;
+
/* 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 (mem->userspace_addr & 0xffffful)
+ if (new->userspace_addr & 0xffffful)
return -EINVAL;
- if (mem->memory_size & 0xffffful)
+ size = new->npages * PAGE_SIZE;
+ if (size & 0xffffful)
return -EINVAL;
- if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+ if ((new->base_gfn * PAGE_SIZE) + size > kvm->arch.mem_limit)
return -EINVAL;
- /* When we are protected, we should not change the memory slots */
- if (kvm_s390_pv_get_handle(kvm))
- return -EINVAL;
return 0;
}
void kvm_arch_commit_memory_region(struct kvm *kvm,
- const struct kvm_userspace_memory_region *mem,
struct kvm_memory_slot *old,
const struct kvm_memory_slot *new,
enum kvm_mr_change change)
@@ -5064,8 +5619,9 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
break;
fallthrough;
case KVM_MR_CREATE:
- rc = gmap_map_segment(kvm->arch.gmap, mem->userspace_addr,
- mem->guest_phys_addr, mem->memory_size);
+ rc = gmap_map_segment(kvm->arch.gmap, new->userspace_addr,
+ new->base_gfn * PAGE_SIZE,
+ new->npages * PAGE_SIZE);
break;
case KVM_MR_FLAGS_ONLY:
break;
@@ -5084,11 +5640,6 @@ static inline unsigned long nonhyp_mask(int i)
return 0x0000ffffffffffffUL >> (nonhyp_fai << 4);
}
-void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu)
-{
- vcpu->valid_wakeup = false;
-}
-
static int __init kvm_s390_init(void)
{
int i;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.