summaryrefslogtreecommitdiff
path: root/arch/s390/kvm
diff options
context:
space:
mode:
Diffstat (limited to 'arch/s390/kvm')
-rw-r--r--arch/s390/kvm/Kconfig1
-rw-r--r--arch/s390/kvm/Makefile2
-rw-r--r--arch/s390/kvm/diag.c11
-rw-r--r--arch/s390/kvm/gaccess.c38
-rw-r--r--arch/s390/kvm/guestdbg.c4
-rw-r--r--arch/s390/kvm/intercept.c7
-rw-r--r--arch/s390/kvm/interrupt.c141
-rw-r--r--arch/s390/kvm/kvm-s390.c298
-rw-r--r--arch/s390/kvm/kvm-s390.h7
-rw-r--r--arch/s390/kvm/priv.c2
-rw-r--r--arch/s390/kvm/trace-s390.h6
11 files changed, 377 insertions, 140 deletions
diff --git a/arch/s390/kvm/Kconfig b/arch/s390/kvm/Kconfig
index 5fce52cf0..5ea5af3c7 100644
--- a/arch/s390/kvm/Kconfig
+++ b/arch/s390/kvm/Kconfig
@@ -29,6 +29,7 @@ config KVM
select HAVE_KVM_IRQFD
select HAVE_KVM_IRQ_ROUTING
select SRCU
+ select KVM_VFIO
---help---
Support hosting paravirtualized guest machines using the SIE
virtualization capability on the mainframe. This should work
diff --git a/arch/s390/kvm/Makefile b/arch/s390/kvm/Makefile
index b3b553469..d42fa38c2 100644
--- a/arch/s390/kvm/Makefile
+++ b/arch/s390/kvm/Makefile
@@ -7,7 +7,7 @@
# as published by the Free Software Foundation.
KVM := ../../../virt/kvm
-common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o
+common-objs = $(KVM)/kvm_main.o $(KVM)/eventfd.o $(KVM)/async_pf.o $(KVM)/irqchip.o $(KVM)/vfio.o
ccflags-y := -Ivirt/kvm -Iarch/s390/kvm
diff --git a/arch/s390/kvm/diag.c b/arch/s390/kvm/diag.c
index 5fbfb88f8..05f7de986 100644
--- a/arch/s390/kvm/diag.c
+++ b/arch/s390/kvm/diag.c
@@ -155,10 +155,8 @@ static int __diag_time_slice_end(struct kvm_vcpu *vcpu)
static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
{
- struct kvm *kvm = vcpu->kvm;
struct kvm_vcpu *tcpu;
int tid;
- int i;
tid = vcpu->run->s.regs.gprs[(vcpu->arch.sie_block->ipa & 0xf0) >> 4];
vcpu->stat.diagnose_9c++;
@@ -167,12 +165,9 @@ static int __diag_time_slice_end_directed(struct kvm_vcpu *vcpu)
if (tid == vcpu->vcpu_id)
return 0;
- kvm_for_each_vcpu(i, tcpu, kvm)
- if (tcpu->vcpu_id == tid) {
- kvm_vcpu_yield_to(tcpu);
- break;
- }
-
+ tcpu = kvm_get_vcpu_by_id(vcpu->kvm, tid);
+ if (tcpu)
+ kvm_vcpu_yield_to(tcpu);
return 0;
}
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index a7559f720..d30db4043 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -259,10 +259,14 @@ struct aste {
int ipte_lock_held(struct kvm_vcpu *vcpu)
{
- union ipte_control *ic = &vcpu->kvm->arch.sca->ipte_control;
+ if (vcpu->arch.sie_block->eca & 1) {
+ int rc;
- if (vcpu->arch.sie_block->eca & 1)
- return ic->kh != 0;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ rc = kvm_s390_get_ipte_control(vcpu->kvm)->kh != 0;
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ return rc;
+ }
return vcpu->kvm->arch.ipte_lock_count != 0;
}
@@ -274,16 +278,20 @@ static void ipte_lock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count++;
if (vcpu->kvm->arch.ipte_lock_count > 1)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.k) {
+ if (old.k) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
}
@@ -296,12 +304,14 @@ static void ipte_unlock_simple(struct kvm_vcpu *vcpu)
vcpu->kvm->arch.ipte_lock_count--;
if (vcpu->kvm->arch.ipte_lock_count)
goto out;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
wake_up(&vcpu->kvm->arch.ipte_wq);
out:
mutex_unlock(&vcpu->kvm->arch.ipte_mutex);
@@ -311,24 +321,29 @@ static void ipte_lock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+retry:
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
- while (old.kg) {
+ if (old.kg) {
+ read_unlock(&vcpu->kvm->arch.sca_lock);
cond_resched();
- old = READ_ONCE(*ic);
+ goto retry;
}
new = old;
new.k = 1;
new.kh++;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
}
static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
{
union ipte_control old, new, *ic;
- ic = &vcpu->kvm->arch.sca->ipte_control;
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ ic = kvm_s390_get_ipte_control(vcpu->kvm);
do {
old = READ_ONCE(*ic);
new = old;
@@ -336,6 +351,7 @@ static void ipte_unlock_siif(struct kvm_vcpu *vcpu)
if (!new.kh)
new.k = 0;
} while (cmpxchg(&ic->val, old.val, new.val) != old.val);
+ read_unlock(&vcpu->kvm->arch.sca_lock);
if (!new.kh)
wake_up(&vcpu->kvm->arch.ipte_wq);
}
diff --git a/arch/s390/kvm/guestdbg.c b/arch/s390/kvm/guestdbg.c
index 47518a324..d697312ce 100644
--- a/arch/s390/kvm/guestdbg.c
+++ b/arch/s390/kvm/guestdbg.c
@@ -116,7 +116,7 @@ static void enable_all_hw_wp(struct kvm_vcpu *vcpu)
if (*cr9 & PER_EVENT_STORE && *cr9 & PER_CONTROL_ALTERATION) {
*cr9 &= ~PER_CONTROL_ALTERATION;
*cr10 = 0;
- *cr11 = PSW_ADDR_INSN;
+ *cr11 = -1UL;
} else {
*cr9 &= ~PER_CONTROL_ALTERATION;
*cr9 |= PER_EVENT_STORE;
@@ -159,7 +159,7 @@ void kvm_s390_patch_guest_per_regs(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->gcr[0] &= ~0x800ul;
vcpu->arch.sie_block->gcr[9] |= PER_EVENT_IFETCH;
vcpu->arch.sie_block->gcr[10] = 0;
- vcpu->arch.sie_block->gcr[11] = PSW_ADDR_INSN;
+ vcpu->arch.sie_block->gcr[11] = -1UL;
}
if (guestdbg_hw_bp_enabled(vcpu)) {
diff --git a/arch/s390/kvm/intercept.c b/arch/s390/kvm/intercept.c
index b4a5aa110..d53c10753 100644
--- a/arch/s390/kvm/intercept.c
+++ b/arch/s390/kvm/intercept.c
@@ -54,9 +54,6 @@ void kvm_s390_rewind_psw(struct kvm_vcpu *vcpu, int ilc)
static int handle_noop(struct kvm_vcpu *vcpu)
{
switch (vcpu->arch.sie_block->icptcode) {
- case 0x0:
- vcpu->stat.exit_null++;
- break;
case 0x10:
vcpu->stat.exit_external_request++;
break;
@@ -338,8 +335,10 @@ static int handle_partial_execution(struct kvm_vcpu *vcpu)
int kvm_handle_sie_intercept(struct kvm_vcpu *vcpu)
{
+ if (kvm_is_ucontrol(vcpu->kvm))
+ return -EOPNOTSUPP;
+
switch (vcpu->arch.sie_block->icptcode) {
- case 0x00:
case 0x10:
case 0x18:
return handle_noop(vcpu);
diff --git a/arch/s390/kvm/interrupt.c b/arch/s390/kvm/interrupt.c
index 6a75352f4..9ffc73221 100644
--- a/arch/s390/kvm/interrupt.c
+++ b/arch/s390/kvm/interrupt.c
@@ -34,6 +34,106 @@
#define PFAULT_DONE 0x0680
#define VIRTIO_PARAM 0x0d00
+/* handle external calls via sigp interpretation facility */
+static int sca_ext_call_pending(struct kvm_vcpu *vcpu, int *src_id)
+{
+ int c, scn;
+
+ if (!(atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND))
+ return 0;
+
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl sigp_ctrl =
+ sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+ c = sigp_ctrl.c;
+ scn = sigp_ctrl.scn;
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl sigp_ctrl =
+ sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+
+ c = sigp_ctrl.c;
+ scn = sigp_ctrl.scn;
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+
+ if (src_id)
+ *src_id = scn;
+
+ return c;
+}
+
+static int sca_inject_ext_call(struct kvm_vcpu *vcpu, int src_id)
+{
+ int expect, rc;
+
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union esca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+ new_val.scn = src_id;
+ new_val.c = 1;
+ old_val.c = 0;
+
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union bsca_sigp_ctrl new_val = {0}, old_val = *sigp_ctrl;
+
+ new_val.scn = src_id;
+ new_val.c = 1;
+ old_val.c = 0;
+
+ expect = old_val.value;
+ rc = cmpxchg(&sigp_ctrl->value, old_val.value, new_val.value);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+
+ if (rc != expect) {
+ /* another external call is pending */
+ return -EBUSY;
+ }
+ atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
+ return 0;
+}
+
+static void sca_clear_ext_call(struct kvm_vcpu *vcpu)
+{
+ struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
+ int rc, expect;
+
+ atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+ union esca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union esca_sigp_ctrl old = *sigp_ctrl;
+
+ expect = old.value;
+ rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+ union bsca_sigp_ctrl *sigp_ctrl =
+ &(sca->cpu[vcpu->vcpu_id].sigp_ctrl);
+ union bsca_sigp_ctrl old = *sigp_ctrl;
+
+ expect = old.value;
+ rc = cmpxchg(&sigp_ctrl->value, old.value, 0);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+ WARN_ON(rc != expect); /* cannot clear? */
+}
+
int psw_extint_disabled(struct kvm_vcpu *vcpu)
{
return !(vcpu->arch.sie_block->gpsw.mask & PSW_MASK_EXT);
@@ -399,9 +499,9 @@ static int __must_check __deliver_restart(struct kvm_vcpu *vcpu)
trace_kvm_s390_deliver_interrupt(vcpu->vcpu_id, KVM_S390_RESTART, 0, 0);
rc = write_guest_lc(vcpu,
- offsetof(struct _lowcore, restart_old_psw),
+ offsetof(struct lowcore, restart_old_psw),
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
- rc |= read_guest_lc(vcpu, offsetof(struct _lowcore, restart_psw),
+ rc |= read_guest_lc(vcpu, offsetof(struct lowcore, restart_psw),
&vcpu->arch.sie_block->gpsw, sizeof(psw_t));
clear_bit(IRQ_PEND_RESTART, &li->pending_irqs);
return rc ? -EFAULT : 0;
@@ -792,13 +892,11 @@ static const deliver_irq_t deliver_irq_funcs[] = {
int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
if (!sclp.has_sigpif)
return test_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs);
- return (sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_ECALL_PEND);
+ return sca_ext_call_pending(vcpu, NULL);
}
int kvm_s390_vcpu_has_irq(struct kvm_vcpu *vcpu, int exclude_stop)
@@ -868,13 +966,13 @@ no_timer:
void kvm_s390_vcpu_wakeup(struct kvm_vcpu *vcpu)
{
- if (waitqueue_active(&vcpu->wq)) {
+ if (swait_active(&vcpu->wq)) {
/*
* The vcpu gave up the cpu voluntarily, mark it as a good
* yield-candidate.
*/
vcpu->preempted = true;
- wake_up_interruptible(&vcpu->wq);
+ swake_up(&vcpu->wq);
vcpu->stat.halt_wakeup++;
}
}
@@ -909,9 +1007,7 @@ void kvm_s390_clear_local_irqs(struct kvm_vcpu *vcpu)
memset(&li->irq, 0, sizeof(li->irq));
spin_unlock(&li->lock);
- /* clear pending external calls set by sigp interpretation facility */
- atomic_andnot(CPUSTAT_ECALL_PEND, li->cpuflags);
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl = 0;
+ sca_clear_ext_call(vcpu);
}
int __must_check kvm_s390_deliver_pending_interrupts(struct kvm_vcpu *vcpu)
@@ -1003,21 +1099,6 @@ static int __inject_pfault_init(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
return 0;
}
-static int __inject_extcall_sigpif(struct kvm_vcpu *vcpu, uint16_t src_id)
-{
- unsigned char new_val, old_val;
- uint8_t *sigp_ctrl = &vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
-
- new_val = SIGP_CTRL_C | (src_id & SIGP_CTRL_SCN_MASK);
- old_val = *sigp_ctrl & ~SIGP_CTRL_C;
- if (cmpxchg(sigp_ctrl, old_val, new_val) != old_val) {
- /* another external call is pending */
- return -EBUSY;
- }
- atomic_or(CPUSTAT_ECALL_PEND, &vcpu->arch.sie_block->cpuflags);
- return 0;
-}
-
static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
@@ -1034,7 +1115,7 @@ static int __inject_extcall(struct kvm_vcpu *vcpu, struct kvm_s390_irq *irq)
return -EINVAL;
if (sclp.has_sigpif)
- return __inject_extcall_sigpif(vcpu, src_id);
+ return sca_inject_ext_call(vcpu, src_id);
if (test_and_set_bit(IRQ_PEND_EXT_EXTERNAL, &li->pending_irqs))
return -EBUSY;
@@ -2203,7 +2284,7 @@ static void store_local_irq(struct kvm_s390_local_interrupt *li,
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
{
- uint8_t sigp_ctrl = vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sigp_ctrl;
+ int scn;
unsigned long sigp_emerg_pending[BITS_TO_LONGS(KVM_MAX_VCPUS)];
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
unsigned long pending_irqs;
@@ -2243,14 +2324,12 @@ int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu, __u8 __user *buf, int len)
}
}
- if ((sigp_ctrl & SIGP_CTRL_C) &&
- (atomic_read(&vcpu->arch.sie_block->cpuflags) &
- CPUSTAT_ECALL_PEND)) {
+ if (sca_ext_call_pending(vcpu, &scn)) {
if (n + sizeof(irq) > len)
return -ENOBUFS;
memset(&irq, 0, sizeof(irq));
irq.type = KVM_S390_INT_EXTERNAL_CALL;
- irq.u.extcall.code = sigp_ctrl & SIGP_CTRL_SCN_MASK;
+ irq.u.extcall.code = scn;
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index a08d0afd5..03dfe9c66 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -246,7 +246,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_NR_VCPUS:
case KVM_CAP_MAX_VCPUS:
- r = KVM_MAX_VCPUS;
+ r = sclp.has_esca ? KVM_S390_ESCA_CPU_SLOTS
+ : KVM_S390_BSCA_CPU_SLOTS;
break;
case KVM_CAP_NR_MEMSLOTS:
r = KVM_USER_MEM_SLOTS;
@@ -257,6 +258,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_VECTOR_REGISTERS:
r = MACHINE_HAS_VX;
break;
+ case KVM_CAP_S390_RI:
+ r = test_facility(64);
+ break;
default:
r = 0;
}
@@ -283,6 +287,8 @@ static void kvm_s390_sync_dirty_log(struct kvm *kvm,
}
/* Section: vm related */
+static void sca_del_vcpu(struct kvm_vcpu *vcpu);
+
/*
* Get (and clear) the dirty memory log for a memory slot.
*/
@@ -355,6 +361,20 @@ static int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
VM_EVENT(kvm, 3, "ENABLE: CAP_S390_VECTOR_REGISTERS %s",
r ? "(not available)" : "(success)");
break;
+ case KVM_CAP_S390_RI:
+ r = -EINVAL;
+ mutex_lock(&kvm->lock);
+ if (atomic_read(&kvm->online_vcpus)) {
+ r = -EBUSY;
+ } else if (test_facility(64)) {
+ set_kvm_facility(kvm->arch.model.fac->mask, 64);
+ set_kvm_facility(kvm->arch.model.fac->list, 64);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
+ VM_EVENT(kvm, 3, "ENABLE: CAP_S390_RI %s",
+ r ? "(not available)" : "(success)");
+ break;
case KVM_CAP_S390_USER_STSI:
VM_EVENT(kvm, 3, "%s", "ENABLE: CAP_S390_USER_STSI");
kvm->arch.user_stsi = 1;
@@ -375,8 +395,8 @@ static int kvm_s390_get_mem_control(struct kvm *kvm, struct kvm_device_attr *att
case KVM_S390_VM_MEM_LIMIT_SIZE:
ret = 0;
VM_EVENT(kvm, 3, "QUERY: max guest memory: %lu bytes",
- kvm->arch.gmap->asce_end);
- if (put_user(kvm->arch.gmap->asce_end, (u64 __user *)attr->addr))
+ kvm->arch.mem_limit);
+ if (put_user(kvm->arch.mem_limit, (u64 __user *)attr->addr))
ret = -EFAULT;
break;
default:
@@ -428,9 +448,17 @@ static int kvm_s390_set_mem_control(struct kvm *kvm, struct kvm_device_attr *att
if (get_user(new_limit, (u64 __user *)attr->addr))
return -EFAULT;
- if (new_limit > kvm->arch.gmap->asce_end)
+ if (kvm->arch.mem_limit != KVM_S390_NO_MEM_LIMIT &&
+ new_limit > kvm->arch.mem_limit)
return -E2BIG;
+ if (!new_limit)
+ return -EINVAL;
+
+ /* gmap_alloc takes last usable address */
+ if (new_limit != KVM_S390_NO_MEM_LIMIT)
+ new_limit -= 1;
+
ret = -EBUSY;
mutex_lock(&kvm->lock);
if (atomic_read(&kvm->online_vcpus) == 0) {
@@ -447,7 +475,9 @@ 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 memory: %lu bytes", new_limit);
+ VM_EVENT(kvm, 3, "SET: max guest address: %lu", new_limit);
+ VM_EVENT(kvm, 3, "New guest asce: 0x%pK",
+ (void *) kvm->arch.gmap->asce);
break;
}
default:
@@ -1024,7 +1054,7 @@ static int kvm_s390_apxa_installed(void)
u8 config[128];
int cc;
- if (test_facility(2) && test_facility(12)) {
+ if (test_facility(12)) {
cc = kvm_s390_query_ap_config(config);
if (cc)
@@ -1075,6 +1105,15 @@ static int kvm_s390_crypto_init(struct kvm *kvm)
return 0;
}
+static void sca_dispose(struct kvm *kvm)
+{
+ if (kvm->arch.use_esca)
+ free_pages_exact(kvm->arch.sca, sizeof(struct esca_block));
+ else
+ free_page((unsigned long)(kvm->arch.sca));
+ kvm->arch.sca = NULL;
+}
+
int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
{
int i, rc;
@@ -1098,14 +1137,17 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
rc = -ENOMEM;
- kvm->arch.sca = (struct sca_block *) get_zeroed_page(GFP_KERNEL);
+ kvm->arch.use_esca = 0; /* start with basic SCA */
+ rwlock_init(&kvm->arch.sca_lock);
+ kvm->arch.sca = (struct bsca_block *) get_zeroed_page(GFP_KERNEL);
if (!kvm->arch.sca)
goto out_err;
spin_lock(&kvm_lock);
sca_offset += 16;
- if (sca_offset + sizeof(struct sca_block) > PAGE_SIZE)
+ if (sca_offset + sizeof(struct bsca_block) > PAGE_SIZE)
sca_offset = 0;
- kvm->arch.sca = (struct sca_block *) ((char *) kvm->arch.sca + sca_offset);
+ kvm->arch.sca = (struct bsca_block *)
+ ((char *) kvm->arch.sca + sca_offset);
spin_unlock(&kvm_lock);
sprintf(debug_name, "kvm-%u", current->pid);
@@ -1157,8 +1199,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
if (type & KVM_VM_S390_UCONTROL) {
kvm->arch.gmap = NULL;
+ kvm->arch.mem_limit = KVM_S390_NO_MEM_LIMIT;
} else {
- kvm->arch.gmap = gmap_alloc(current->mm, (1UL << 44) - 1);
+ if (sclp.hamax == U64_MAX)
+ kvm->arch.mem_limit = TASK_MAX_SIZE;
+ else
+ kvm->arch.mem_limit = min_t(unsigned long, TASK_MAX_SIZE,
+ sclp.hamax + 1);
+ kvm->arch.gmap = gmap_alloc(current->mm, kvm->arch.mem_limit - 1);
if (!kvm->arch.gmap)
goto out_err;
kvm->arch.gmap->private = kvm;
@@ -1170,14 +1218,14 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
kvm->arch.epoch = 0;
spin_lock_init(&kvm->arch.start_stop_lock);
- KVM_EVENT(3, "vm 0x%p created by pid %u", kvm, current->pid);
+ KVM_EVENT(3, "vm 0x%pK created by pid %u", kvm, current->pid);
return 0;
out_err:
kfree(kvm->arch.crypto.crycb);
free_page((unsigned long)kvm->arch.model.fac);
debug_unregister(kvm->arch.dbf);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
KVM_EVENT(3, "creation of vm failed: %d", rc);
return rc;
}
@@ -1188,14 +1236,8 @@ void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
trace_kvm_s390_destroy_vcpu(vcpu->vcpu_id);
kvm_s390_clear_local_irqs(vcpu);
kvm_clear_async_pf_completion_queue(vcpu);
- if (!kvm_is_ucontrol(vcpu->kvm)) {
- clear_bit(63 - vcpu->vcpu_id,
- (unsigned long *) &vcpu->kvm->arch.sca->mcn);
- if (vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda ==
- (__u64) vcpu->arch.sie_block)
- vcpu->kvm->arch.sca->cpu[vcpu->vcpu_id].sda = 0;
- }
- smp_mb();
+ if (!kvm_is_ucontrol(vcpu->kvm))
+ sca_del_vcpu(vcpu);
if (kvm_is_ucontrol(vcpu->kvm))
gmap_free(vcpu->arch.gmap);
@@ -1228,14 +1270,14 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
{
kvm_free_vcpus(kvm);
free_page((unsigned long)kvm->arch.model.fac);
- free_page((unsigned long)(kvm->arch.sca));
+ sca_dispose(kvm);
debug_unregister(kvm->arch.dbf);
kfree(kvm->arch.crypto.crycb);
if (!kvm_is_ucontrol(kvm))
gmap_free(kvm->arch.gmap);
kvm_s390_destroy_adapters(kvm);
kvm_s390_clear_float_irqs(kvm);
- KVM_EVENT(3, "vm 0x%p destroyed", kvm);
+ KVM_EVENT(3, "vm 0x%pK destroyed", kvm);
}
/* Section: vcpu related */
@@ -1249,6 +1291,117 @@ static int __kvm_ucontrol_vcpu_init(struct kvm_vcpu *vcpu)
return 0;
}
+static void sca_del_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.sca;
+
+ clear_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ sca->cpu[vcpu->vcpu_id].sda = 0;
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+static void sca_add_vcpu(struct kvm_vcpu *vcpu)
+{
+ read_lock(&vcpu->kvm->arch.sca_lock);
+ if (vcpu->kvm->arch.use_esca) {
+ struct esca_block *sca = vcpu->kvm->arch.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;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) sca->mcn);
+ } else {
+ struct bsca_block *sca = vcpu->kvm->arch.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;
+ set_bit_inv(vcpu->vcpu_id, (unsigned long *) &sca->mcn);
+ }
+ read_unlock(&vcpu->kvm->arch.sca_lock);
+}
+
+/* Basic SCA to Extended SCA data copy routines */
+static inline void sca_copy_entry(struct esca_entry *d, struct bsca_entry *s)
+{
+ d->sda = s->sda;
+ d->sigp_ctrl.c = s->sigp_ctrl.c;
+ d->sigp_ctrl.scn = s->sigp_ctrl.scn;
+}
+
+static void sca_copy_b_to_e(struct esca_block *d, struct bsca_block *s)
+{
+ int i;
+
+ d->ipte_control = s->ipte_control;
+ d->mcn[0] = s->mcn;
+ for (i = 0; i < KVM_S390_BSCA_CPU_SLOTS; i++)
+ sca_copy_entry(&d->cpu[i], &s->cpu[i]);
+}
+
+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;
+ u32 scaol, scaoh;
+
+ new_sca = alloc_pages_exact(sizeof(*new_sca), GFP_KERNEL|__GFP_ZERO);
+ if (!new_sca)
+ return -ENOMEM;
+
+ scaoh = (u32)((u64)(new_sca) >> 32);
+ scaol = (u32)(u64)(new_sca) & ~0x3fU;
+
+ kvm_s390_vcpu_block_all(kvm);
+ write_lock(&kvm->arch.sca_lock);
+
+ sca_copy_b_to_e(new_sca, old_sca);
+
+ kvm_for_each_vcpu(vcpu_idx, vcpu, kvm) {
+ vcpu->arch.sie_block->scaoh = scaoh;
+ vcpu->arch.sie_block->scaol = scaol;
+ vcpu->arch.sie_block->ecb2 |= 0x04U;
+ }
+ kvm->arch.sca = new_sca;
+ kvm->arch.use_esca = 1;
+
+ write_unlock(&kvm->arch.sca_lock);
+ kvm_s390_vcpu_unblock_all(kvm);
+
+ free_page((unsigned long)old_sca);
+
+ VM_EVENT(kvm, 2, "Switched to ESCA (0x%pK -> 0x%pK)",
+ old_sca, kvm->arch.sca);
+ return 0;
+}
+
+static int sca_can_add_vcpu(struct kvm *kvm, unsigned int id)
+{
+ int rc;
+
+ if (id < KVM_S390_BSCA_CPU_SLOTS)
+ return true;
+ if (!sclp.has_esca)
+ 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;
+}
+
int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
{
vcpu->arch.pfault_token = KVM_S390_PFAULT_TOKEN_INVALID;
@@ -1259,6 +1412,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
KVM_SYNC_CRS |
KVM_SYNC_ARCH0 |
KVM_SYNC_PFAULT;
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->run->kvm_valid_regs |= KVM_SYNC_RICCB;
if (test_kvm_facility(vcpu->kvm, 129))
vcpu->run->kvm_valid_regs |= KVM_SYNC_VRS;
@@ -1338,8 +1493,11 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->epoch = vcpu->kvm->arch.epoch;
preempt_enable();
mutex_unlock(&vcpu->kvm->lock);
- if (!kvm_is_ucontrol(vcpu->kvm))
+ if (!kvm_is_ucontrol(vcpu->kvm)) {
vcpu->arch.gmap = vcpu->kvm->arch.gmap;
+ sca_add_vcpu(vcpu);
+ }
+
}
static void kvm_s390_vcpu_crypto_setup(struct kvm_vcpu *vcpu)
@@ -1408,10 +1566,13 @@ int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
vcpu->arch.sie_block->eca |= 1;
if (sclp.has_sigpif)
vcpu->arch.sie_block->eca |= 0x10000000U;
+ if (test_kvm_facility(vcpu->kvm, 64))
+ vcpu->arch.sie_block->ecb3 |= 0x01;
if (test_kvm_facility(vcpu->kvm, 129)) {
vcpu->arch.sie_block->eca |= 0x00020000;
vcpu->arch.sie_block->ecd |= 0x20000000;
}
+ vcpu->arch.sie_block->riccbd = (unsigned long) &vcpu->run->s.regs.riccb;
vcpu->arch.sie_block->ictl |= ICTL_ISKE | ICTL_SSKE | ICTL_RRBE;
if (vcpu->kvm->arch.use_cmma) {
@@ -1434,7 +1595,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
struct sie_page *sie_page;
int rc = -EINVAL;
- if (id >= KVM_MAX_VCPUS)
+ if (!kvm_is_ucontrol(kvm) && !sca_can_add_vcpu(kvm, id))
goto out;
rc = -ENOMEM;
@@ -1451,20 +1612,6 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
vcpu->arch.sie_block->itdba = (unsigned long) &sie_page->itdb;
vcpu->arch.sie_block->icpua = id;
- if (!kvm_is_ucontrol(kvm)) {
- if (!kvm->arch.sca) {
- WARN_ON_ONCE(1);
- goto out_free_cpu;
- }
- if (!kvm->arch.sca->cpu[id].sda)
- kvm->arch.sca->cpu[id].sda =
- (__u64) vcpu->arch.sie_block;
- vcpu->arch.sie_block->scaoh =
- (__u32)(((__u64)kvm->arch.sca) >> 32);
- vcpu->arch.sie_block->scaol = (__u32)(__u64)kvm->arch.sca;
- set_bit(63 - id, (unsigned long *) &kvm->arch.sca->mcn);
- }
-
spin_lock_init(&vcpu->arch.local_int.lock);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
vcpu->arch.local_int.wq = &vcpu->wq;
@@ -1473,7 +1620,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
goto out_free_sie_block;
- VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
+ VM_EVENT(kvm, 3, "create cpu %d at 0x%pK, sie block at 0x%pK", id, vcpu,
vcpu->arch.sie_block);
trace_kvm_s390_create_vcpu(id, vcpu, vcpu->arch.sie_block);
@@ -1977,7 +2124,8 @@ static int vcpu_pre_run(struct kvm_vcpu *vcpu)
*/
kvm_check_async_pf_completion(vcpu);
- memcpy(&vcpu->arch.sie_block->gg14, &vcpu->run->s.regs.gprs[14], 16);
+ vcpu->arch.sie_block->gg14 = vcpu->run->s.regs.gprs[14];
+ vcpu->arch.sie_block->gg15 = vcpu->run->s.regs.gprs[15];
if (need_resched())
schedule();
@@ -2035,8 +2183,6 @@ static int vcpu_post_run_fault_in_sie(struct kvm_vcpu *vcpu)
static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
{
- int rc = -1;
-
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
@@ -2044,40 +2190,36 @@ static int vcpu_post_run(struct kvm_vcpu *vcpu, int exit_reason)
if (guestdbg_enabled(vcpu))
kvm_s390_restore_guest_per_regs(vcpu);
- if (exit_reason >= 0) {
- rc = 0;
+ vcpu->run->s.regs.gprs[14] = vcpu->arch.sie_block->gg14;
+ vcpu->run->s.regs.gprs[15] = vcpu->arch.sie_block->gg15;
+
+ if (vcpu->arch.sie_block->icptcode > 0) {
+ int rc = kvm_handle_sie_intercept(vcpu);
+
+ if (rc != -EOPNOTSUPP)
+ return rc;
+ vcpu->run->exit_reason = KVM_EXIT_S390_SIEIC;
+ vcpu->run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
+ 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;
- rc = -EREMOTE;
-
+ 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)) {
- rc = 0;
- } else {
- gpa_t gpa = current->thread.gmap_addr;
- rc = kvm_arch_fault_in_page(vcpu, gpa, 1);
- }
- }
-
- if (rc == -1)
- rc = vcpu_post_run_fault_in_sie(vcpu);
-
- memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
-
- if (rc == 0) {
- if (kvm_is_ucontrol(vcpu->kvm))
- /* Don't exit for host interrupts. */
- rc = vcpu->arch.sie_block->icptcode ? -EOPNOTSUPP : 0;
- else
- rc = kvm_handle_sie_intercept(vcpu);
+ if (kvm_arch_setup_async_pf(vcpu))
+ return 0;
+ return kvm_arch_fault_in_page(vcpu, current->thread.gmap_addr, 1);
}
-
- return rc;
+ return vcpu_post_run_fault_in_sie(vcpu);
}
static int __vcpu_run(struct kvm_vcpu *vcpu)
@@ -2197,18 +2339,8 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu, struct kvm_run *kvm_run)
rc = 0;
}
- if (rc == -EOPNOTSUPP) {
- /* intercept cannot be handled in-kernel, prepare kvm-run */
- kvm_run->exit_reason = KVM_EXIT_S390_SIEIC;
- kvm_run->s390_sieic.icptcode = vcpu->arch.sie_block->icptcode;
- kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
- kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
- rc = 0;
- }
-
if (rc == -EREMOTE) {
- /* intercept was handled, but userspace support is needed
- * kvm_run has been prepared by the handler */
+ /* userspace support is needed, kvm_run has been prepared */
rc = 0;
}
@@ -2249,7 +2381,7 @@ int kvm_s390_store_status_unloaded(struct kvm_vcpu *vcpu, unsigned long gpa)
/* manually convert vector registers if necessary */
if (MACHINE_HAS_VX) {
- convert_vx_to_fp(fprs, current->thread.fpu.vxrs);
+ convert_vx_to_fp(fprs, (__vector128 *) vcpu->run->s.regs.vrs);
rc = write_guest_abs(vcpu, gpa + __LC_FPREGS_SAVE_AREA,
fprs, 128);
} else {
@@ -2697,6 +2829,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
if (mem->memory_size & 0xffffful)
return -EINVAL;
+ if (mem->guest_phys_addr + mem->memory_size > kvm->arch.mem_limit)
+ return -EINVAL;
+
return 0;
}
@@ -2728,6 +2863,11 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
static int __init kvm_s390_init(void)
{
+ if (!sclp.has_sief2) {
+ pr_info("SIE not available\n");
+ return -ENODEV;
+ }
+
return kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
}
diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
index 1e70e00d3..df1abada1 100644
--- a/arch/s390/kvm/kvm-s390.h
+++ b/arch/s390/kvm/kvm-s390.h
@@ -340,4 +340,11 @@ void kvm_s390_clear_bp_data(struct kvm_vcpu *vcpu);
void kvm_s390_prepare_debug_exit(struct kvm_vcpu *vcpu);
void kvm_s390_handle_per_event(struct kvm_vcpu *vcpu);
+/* support for Basic/Extended SCA handling */
+static inline union ipte_control *kvm_s390_get_ipte_control(struct kvm *kvm)
+{
+ struct bsca_block *sca = kvm->arch.sca; /* SCA version doesn't matter */
+
+ return &sca->ipte_control;
+}
#endif
diff --git a/arch/s390/kvm/priv.c b/arch/s390/kvm/priv.c
index d76b51cb4..ed74e86d9 100644
--- a/arch/s390/kvm/priv.c
+++ b/arch/s390/kvm/priv.c
@@ -355,7 +355,7 @@ static int handle_stfl(struct kvm_vcpu *vcpu)
* into a u32 memory representation. They will remain bits 0-31.
*/
fac = *vcpu->kvm->arch.model.fac->list >> 32;
- rc = write_guest_lc(vcpu, offsetof(struct _lowcore, stfl_fac_list),
+ rc = write_guest_lc(vcpu, offsetof(struct lowcore, stfl_fac_list),
&fac, sizeof(fac));
if (rc)
return rc;
diff --git a/arch/s390/kvm/trace-s390.h b/arch/s390/kvm/trace-s390.h
index cc1d6c683..396485bca 100644
--- a/arch/s390/kvm/trace-s390.h
+++ b/arch/s390/kvm/trace-s390.h
@@ -55,8 +55,8 @@ TRACE_EVENT(kvm_s390_create_vcpu,
__entry->sie_block = sie_block;
),
- TP_printk("create cpu %d at %p, sie block at %p", __entry->id,
- __entry->vcpu, __entry->sie_block)
+ TP_printk("create cpu %d at 0x%pK, sie block at 0x%pK",
+ __entry->id, __entry->vcpu, __entry->sie_block)
);
TRACE_EVENT(kvm_s390_destroy_vcpu,
@@ -254,7 +254,7 @@ TRACE_EVENT(kvm_s390_enable_css,
__entry->kvm = kvm;
),
- TP_printk("enabling channel I/O support (kvm @ %p)\n",
+ TP_printk("enabling channel I/O support (kvm @ %pK)\n",
__entry->kvm)
);