/*
* s390host.c -- hosting zSeries kernel virtual machines
*
- * Copyright IBM Corp. 2008
+ * Copyright IBM Corp. 2008,2009
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License (version 2 only)
* 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>
*/
#include <linux/compiler.h>
#include <linux/err.h>
#include <linux/fs.h>
+#include <linux/hrtimer.h>
#include <linux/init.h>
#include <linux/kvm.h>
#include <linux/kvm_host.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/timer.h>
+#include <asm/asm-offsets.h>
#include <asm/lowcore.h>
#include <asm/pgtable.h>
-
+#include <asm/nmi.h>
+#include <asm/system.h>
#include "kvm-s390.h"
#include "gaccess.h"
struct kvm_stats_debugfs_item debugfs_entries[] = {
{ "userspace_handled", VCPU_STAT(exit_userspace) },
+ { "exit_null", VCPU_STAT(exit_null) },
{ "exit_validity", VCPU_STAT(exit_validity) },
{ "exit_stop_request", VCPU_STAT(exit_stop_request) },
{ "exit_external_request", VCPU_STAT(exit_external_request) },
{ "exit_instruction", VCPU_STAT(exit_instruction) },
{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
- { "instruction_lctg", VCPU_STAT(instruction_lctg) },
+ { "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
{ "deliver_emergency_signal", VCPU_STAT(deliver_emergency_signal) },
{ "deliver_service_signal", VCPU_STAT(deliver_service_signal) },
{ "deliver_restart_signal", VCPU_STAT(deliver_restart_signal) },
{ "deliver_program_interruption", VCPU_STAT(deliver_program_int) },
{ "exit_wait_state", VCPU_STAT(exit_wait_state) },
+ { "instruction_stidp", VCPU_STAT(instruction_stidp) },
+ { "instruction_spx", VCPU_STAT(instruction_spx) },
+ { "instruction_stpx", VCPU_STAT(instruction_stpx) },
+ { "instruction_stap", VCPU_STAT(instruction_stap) },
+ { "instruction_storage_key", VCPU_STAT(instruction_storage_key) },
+ { "instruction_stsch", VCPU_STAT(instruction_stsch) },
+ { "instruction_chsc", VCPU_STAT(instruction_chsc) },
+ { "instruction_stsi", VCPU_STAT(instruction_stsi) },
+ { "instruction_stfl", VCPU_STAT(instruction_stfl) },
+ { "instruction_sigp_sense", VCPU_STAT(instruction_sigp_sense) },
+ { "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+ { "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+ { "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
+ { "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
+ { "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+ { "diagnose_44", VCPU_STAT(diagnose_44) },
{ NULL }
};
+static unsigned long long *facilities;
/* Section: not file related */
-void kvm_arch_hardware_enable(void *garbage)
+int kvm_arch_hardware_enable(void *garbage)
{
/* every s390 is virtualization enabled ;-) */
+ return 0;
}
void kvm_arch_hardware_disable(void *garbage)
{
}
-void decache_vcpus_on_cpu(int cpu)
-{
-}
-
int kvm_arch_hardware_setup(void)
{
return 0;
int kvm_dev_ioctl_check_extension(long ext)
{
- return 0;
+ int r;
+
+ switch (ext) {
+ case KVM_CAP_S390_PSW:
+ r = 1;
+ break;
+ default:
+ r = 0;
+ }
+ return r;
}
/* Section: vm related */
break;
}
default:
- r = -EINVAL;
+ r = -ENOTTY;
}
return r;
debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
VM_EVENT(kvm, 3, "%s", "vm created");
- try_module_get(THIS_MODULE);
-
return kvm;
out_nodbf:
free_page((unsigned long)(kvm->arch.sca));
return ERR_PTR(rc);
}
+void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
+{
+ VCPU_EVENT(vcpu, 3, "%s", "free cpu");
+ 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();
+ free_page((unsigned long)(vcpu->arch.sie_block));
+ kvm_vcpu_uninit(vcpu);
+ kfree(vcpu);
+}
+
+static void kvm_free_vcpus(struct kvm *kvm)
+{
+ unsigned int i;
+ struct kvm_vcpu *vcpu;
+
+ kvm_for_each_vcpu(i, vcpu, kvm)
+ kvm_arch_vcpu_destroy(vcpu);
+
+ mutex_lock(&kvm->lock);
+ for (i = 0; i < atomic_read(&kvm->online_vcpus); i++)
+ kvm->vcpus[i] = NULL;
+
+ atomic_set(&kvm->online_vcpus, 0);
+ mutex_unlock(&kvm->lock);
+}
+
+void kvm_arch_sync_events(struct kvm *kvm)
+{
+}
+
void kvm_arch_destroy_vm(struct kvm *kvm)
{
- debug_unregister(kvm->arch.dbf);
+ kvm_free_vcpus(kvm);
+ kvm_free_physmem(kvm);
free_page((unsigned long)(kvm->arch.sca));
+ debug_unregister(kvm->arch.dbf);
+ cleanup_srcu_struct(&kvm->srcu);
kfree(kvm);
- module_put(THIS_MODULE);
}
/* Section: vcpu related */
void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu)
{
- /* kvm common code refers to this, but does'nt call it */
- BUG();
+ /* Nothing todo */
}
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
vcpu->arch.guest_fpregs.fpc &= FPC_VALID_MASK;
restore_fp_regs(&vcpu->arch.guest_fpregs);
restore_access_regs(vcpu->arch.guest_acrs);
-
- if (signal_pending(current))
- atomic_set_mask(CPUSTAT_STOP_INT,
- &vcpu->arch.sie_block->cpuflags);
}
void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
int kvm_arch_vcpu_setup(struct kvm_vcpu *vcpu)
{
atomic_set(&vcpu->arch.sie_block->cpuflags, CPUSTAT_ZARCH);
- vcpu->arch.sie_block->gmslm = 0xffffffffffUL;
- vcpu->arch.sie_block->gmsor = 0x000000000000;
+ set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests);
vcpu->arch.sie_block->ecb = 2;
vcpu->arch.sie_block->eca = 0xC1002001U;
- setup_timer(&vcpu->arch.ckc_timer, kvm_s390_idle_wakeup,
- (unsigned long) vcpu);
+ vcpu->arch.sie_block->fac = (int) (long) facilities;
+ hrtimer_init(&vcpu->arch.ckc_timer, CLOCK_REALTIME, HRTIMER_MODE_ABS);
+ tasklet_init(&vcpu->arch.tasklet, kvm_s390_tasklet,
+ (unsigned long) vcpu);
+ vcpu->arch.ckc_timer.function = kvm_s390_idle_wakeup;
+ get_cpu_id(&vcpu->arch.cpu_id);
+ vcpu->arch.cpu_id.version = 0xff;
return 0;
}
if (!vcpu)
goto out_nomem;
- vcpu->arch.sie_block = (struct sie_block *) get_zeroed_page(GFP_KERNEL);
+ vcpu->arch.sie_block = (struct kvm_s390_sie_block *)
+ get_zeroed_page(GFP_KERNEL);
if (!vcpu->arch.sie_block)
goto out_free_cpu;
vcpu->arch.sie_block->icpua = id;
BUG_ON(!kvm->arch.sca);
- BUG_ON(kvm->arch.sca->cpu[id].sda);
- kvm->arch.sca->cpu[id].sda = (__u64) vcpu->arch.sie_block;
+ 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;
spin_lock_init(&vcpu->arch.local_int.lock);
INIT_LIST_HEAD(&vcpu->arch.local_int.list);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
- spin_lock_bh(&kvm->arch.float_int.lock);
+ spin_lock(&kvm->arch.float_int.lock);
kvm->arch.float_int.local_int[id] = &vcpu->arch.local_int;
init_waitqueue_head(&vcpu->arch.local_int.wq);
- spin_unlock_bh(&kvm->arch.float_int.lock);
+ vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
+ spin_unlock(&kvm->arch.float_int.lock);
rc = kvm_vcpu_init(vcpu, kvm, id);
if (rc)
- goto out_free_cpu;
+ goto out_free_sie_block;
VM_EVENT(kvm, 3, "create cpu %d at %p, sie block at %p", id, vcpu,
vcpu->arch.sie_block);
- try_module_get(THIS_MODULE);
-
return vcpu;
+out_free_sie_block:
+ free_page((unsigned long)(vcpu->arch.sie_block));
out_free_cpu:
kfree(vcpu);
out_nomem:
return ERR_PTR(rc);
}
-void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
-{
- VCPU_EVENT(vcpu, 3, "%s", "destroy cpu");
- free_page((unsigned long)(vcpu->arch.sie_block));
- kfree(vcpu);
- module_put(THIS_MODULE);
-}
-
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
/* kvm common code refers to this, but never calls it */
vcpu_load(vcpu);
if (atomic_read(&vcpu->arch.sie_block->cpuflags) & CPUSTAT_RUNNING)
rc = -EBUSY;
- else
- vcpu->arch.sie_block->gpsw = psw;
+ else {
+ vcpu->run->psw_mask = psw.mask;
+ vcpu->run->psw_addr = psw.addr;
+ }
vcpu_put(vcpu);
return rc;
}
return -EINVAL; /* not implemented yet */
}
-int kvm_arch_vcpu_ioctl_debug_guest(struct kvm_vcpu *vcpu,
- struct kvm_debug_guest *dbg)
+int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
+ struct kvm_guest_debug *dbg)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_get_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
+{
+ return -EINVAL; /* not implemented yet */
+}
+
+int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
+ struct kvm_mp_state *mp_state)
{
return -EINVAL; /* not implemented yet */
}
if (need_resched())
schedule();
+ if (test_thread_flag(TIF_MCCK_PENDING))
+ s390_handle_mcck();
+
+ kvm_s390_deliver_pending_interrupts(vcpu);
+
vcpu->arch.sie_block->icptcode = 0;
local_irq_disable();
kvm_guest_enter();
local_irq_enable();
VCPU_EVENT(vcpu, 6, "entering sie flags %x",
atomic_read(&vcpu->arch.sie_block->cpuflags));
- sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs);
+ if (sie64a(vcpu->arch.sie_block, vcpu->arch.guest_gprs)) {
+ VCPU_EVENT(vcpu, 3, "%s", "fault in sie instruction");
+ kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
+ }
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
local_irq_disable();
vcpu_load(vcpu);
+rerun_vcpu:
+ if (vcpu->requests)
+ if (test_and_clear_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+ kvm_s390_vcpu_set_mem(vcpu);
+
+ /* verify, that memory has been registered */
+ if (!vcpu->arch.sie_block->gmslm) {
+ vcpu_put(vcpu);
+ VCPU_EVENT(vcpu, 3, "%s", "no memory registered to run vcpu");
+ return -EINVAL;
+ }
+
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &vcpu->sigset, &sigsaved);
switch (kvm_run->exit_reason) {
case KVM_EXIT_S390_SIEIC:
- vcpu->arch.sie_block->gpsw.mask = kvm_run->s390_sieic.mask;
- vcpu->arch.sie_block->gpsw.addr = kvm_run->s390_sieic.addr;
- break;
case KVM_EXIT_UNKNOWN:
+ case KVM_EXIT_INTR:
case KVM_EXIT_S390_RESET:
break;
default:
BUG();
}
- might_sleep();
+ vcpu->arch.sie_block->gpsw.mask = kvm_run->psw_mask;
+ vcpu->arch.sie_block->gpsw.addr = kvm_run->psw_addr;
+
+ might_fault();
do {
- kvm_s390_deliver_pending_interrupts(vcpu);
__vcpu_run(vcpu);
rc = kvm_handle_sie_intercept(vcpu);
} while (!signal_pending(current) && !rc);
- if (signal_pending(current) && !rc)
+ if (rc == SIE_INTERCEPT_RERUNVCPU)
+ goto rerun_vcpu;
+
+ if (signal_pending(current) && !rc) {
+ kvm_run->exit_reason = KVM_EXIT_INTR;
rc = -EINTR;
+ }
- if (rc == -ENOTSUPP) {
+ 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.mask = vcpu->arch.sie_block->gpsw.mask;
- kvm_run->s390_sieic.addr = vcpu->arch.sie_block->gpsw.addr;
kvm_run->s390_sieic.ipa = vcpu->arch.sie_block->ipa;
kvm_run->s390_sieic.ipb = vcpu->arch.sie_block->ipb;
rc = 0;
rc = 0;
}
+ kvm_run->psw_mask = vcpu->arch.sie_block->gpsw.mask;
+ kvm_run->psw_addr = vcpu->arch.sie_block->gpsw.addr;
+
if (vcpu->sigset_active)
sigprocmask(SIG_SETMASK, &sigsaved, NULL);
vcpu_put(vcpu);
vcpu->stat.exit_userspace++;
- return 0;
+ return rc;
}
static int __guestcopy(struct kvm_vcpu *vcpu, u64 guestdest, const void *from,
} else
prefix = 0;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, fp_regs),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, fp_regs),
vcpu->arch.guest_fpregs.fprs, 128, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, gp_regs),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, gp_regs),
vcpu->arch.guest_gprs, 128, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, psw),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, psw),
&vcpu->arch.sie_block->gpsw, 16, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, pref_reg),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, pref_reg),
&vcpu->arch.sie_block->prefix, 4, prefix))
return -EFAULT;
if (__guestcopy(vcpu,
- addr + offsetof(struct save_area_s390x, fp_ctrl_reg),
+ addr + offsetof(struct save_area, fp_ctrl_reg),
&vcpu->arch.guest_fpregs.fpc, 4, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, tod_reg),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, tod_reg),
&vcpu->arch.sie_block->todpr, 4, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, timer),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, timer),
&vcpu->arch.sie_block->cputm, 8, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, clk_cmp),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, clk_cmp),
&vcpu->arch.sie_block->ckc, 8, prefix))
return -EFAULT;
- if (__guestcopy(vcpu, addr + offsetof(struct save_area_s390x, acc_regs),
+ if (__guestcopy(vcpu, addr + offsetof(struct save_area, acc_regs),
&vcpu->arch.guest_acrs, 64, prefix))
return -EFAULT;
if (__guestcopy(vcpu,
- addr + offsetof(struct save_area_s390x, ctrl_regs),
+ addr + offsetof(struct save_area, ctrl_regs),
&vcpu->arch.sie_block->gcr, 128, prefix))
return -EFAULT;
return 0;
}
/* Section: memory related */
-int kvm_arch_set_memory_region(struct kvm *kvm,
- struct kvm_userspace_memory_region *mem,
- struct kvm_memory_slot old,
- int user_alloc)
+int kvm_arch_prepare_memory_region(struct kvm *kvm,
+ struct kvm_memory_slot *memslot,
+ struct kvm_memory_slot old,
+ struct kvm_userspace_memory_region *mem,
+ int user_alloc)
{
/* A few sanity checks. We can have exactly one memory slot which has
to start at guest virtual zero and which has to be located at a
if (mem->memory_size & (PAGE_SIZE - 1))
return -EINVAL;
- kvm->arch.guest_origin = mem->userspace_addr;
- kvm->arch.guest_memsize = mem->memory_size;
-
- /* FIXME: we do want to interrupt running CPUs and update their memory
- configuration now to avoid race conditions. But hey, changing the
- memory layout while virtual CPUs are running is usually bad
- programming practice. */
+ if (!user_alloc)
+ return -EINVAL;
return 0;
}
+void kvm_arch_commit_memory_region(struct kvm *kvm,
+ struct kvm_userspace_memory_region *mem,
+ struct kvm_memory_slot old,
+ int user_alloc)
+{
+ int i;
+ struct kvm_vcpu *vcpu;
+
+ /* request update of sie control block for all available vcpus */
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (test_and_set_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests))
+ continue;
+ kvm_s390_inject_sigp_stop(vcpu, ACTION_RELOADVCPU_ON_STOP);
+ }
+}
+
+void kvm_arch_flush_shadow(struct kvm *kvm)
+{
+}
+
gfn_t unalias_gfn(struct kvm *kvm, gfn_t gfn)
{
return gfn;
static int __init kvm_s390_init(void)
{
- return kvm_init(NULL, sizeof(struct kvm_vcpu), THIS_MODULE);
+ int ret;
+ ret = kvm_init(NULL, sizeof(struct kvm_vcpu), 0, THIS_MODULE);
+ if (ret)
+ return ret;
+
+ /*
+ * guests can ask for up to 255+1 double words, we need a full page
+ * to hold the maximum amount of facilites. On the other hand, we
+ * only set facilities that are known to work in KVM.
+ */
+ facilities = (unsigned long long *) get_zeroed_page(GFP_KERNEL|GFP_DMA);
+ if (!facilities) {
+ kvm_exit();
+ return -ENOMEM;
+ }
+ stfle(facilities, 1);
+ facilities[0] &= 0xff00fff3f0700000ULL;
+ return 0;
}
static void __exit kvm_s390_exit(void)
{
+ free_page((unsigned long) facilities);
kvm_exit();
}