KVM: s390: migrate vcpu interrupt state

This patch adds support to migrate vcpu interrupts. Two new vcpu ioctls
are added which get/set the complete status of pending interrupts in one
go. The ioctls are marked as available with the new capability
KVM_CAP_S390_IRQ_STATE.

We can not use a ONEREG, as the number of pending local interrupts is not
constant and depends on the number of CPUs.

To retrieve the interrupt state we add an ioctl KVM_S390_GET_IRQ_STATE.
Its input parameter is a pointer to a struct kvm_s390_irq_state which
has a buffer and length.  For all currently pending interrupts, we copy
a struct kvm_s390_irq into the buffer and pass it to userspace.

To store interrupt state into a buffer provided by userspace, we add an
ioctl KVM_S390_SET_IRQ_STATE. It passes a struct kvm_s390_irq_state into
the kernel and injects all interrupts contained in the buffer.

Signed-off-by: Jens Freimann <jfrei@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Cornelia Huck <cornelia.huck@de.ibm.com>
This commit is contained in:
Jens Freimann 2014-11-24 17:13:46 +01:00 committed by Christian Borntraeger
parent 79e87a103d
commit 816c7667ea
5 changed files with 252 additions and 0 deletions

View File

@ -2875,6 +2875,67 @@ KVM_S390_MCHK - machine check interrupt; parameters in .mchk
Note that the vcpu ioctl is asynchronous to vcpu execution.
4.94 KVM_S390_GET_IRQ_STATE
Capability: KVM_CAP_S390_IRQ_STATE
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_irq_state (out)
Returns: >= number of bytes copied into buffer,
-EINVAL if buffer size is 0,
-ENOBUFS if buffer size is too small to fit all pending interrupts,
-EFAULT if the buffer address was invalid
This ioctl allows userspace to retrieve the complete state of all currently
pending interrupts in a single buffer. Use cases include migration
and introspection. The parameter structure contains the address of a
userspace buffer and its length:
struct kvm_s390_irq_state {
__u64 buf;
__u32 flags;
__u32 len;
__u32 reserved[4];
};
Userspace passes in the above struct and for each pending interrupt a
struct kvm_s390_irq is copied to the provided buffer.
If -ENOBUFS is returned the buffer provided was too small and userspace
may retry with a bigger buffer.
4.95 KVM_S390_SET_IRQ_STATE
Capability: KVM_CAP_S390_IRQ_STATE
Architectures: s390
Type: vcpu ioctl
Parameters: struct kvm_s390_irq_state (in)
Returns: 0 on success,
-EFAULT if the buffer address was invalid,
-EINVAL for an invalid buffer length (see below),
-EBUSY if there were already interrupts pending,
errors occurring when actually injecting the
interrupt. See KVM_S390_IRQ.
This ioctl allows userspace to set the complete state of all cpu-local
interrupts currently pending for the vcpu. It is intended for restoring
interrupt state after a migration. The input parameter is a userspace buffer
containing a struct kvm_s390_irq_state:
struct kvm_s390_irq_state {
__u64 buf;
__u32 len;
__u32 pad;
};
The userspace memory referenced by buf contains a struct kvm_s390_irq
for each interrupt to be injected into the guest.
If one of the interrupts could not be injected for some reason the
ioctl aborts.
len must be a multiple of sizeof(struct kvm_s390_irq). It must be > 0
and it must not exceed (max_vcpus + 32) * sizeof(struct kvm_s390_irq),
which is the maximum number of possibly pending cpu-local interrupts.
5. The kvm_run structure
------------------------

View File

@ -2123,3 +2123,143 @@ int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
{
return -EINVAL;
}
int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu, void __user *irqstate, int len)
{
struct kvm_s390_local_interrupt *li = &vcpu->arch.local_int;
struct kvm_s390_irq *buf;
int r = 0;
int n;
buf = vmalloc(len);
if (!buf)
return -ENOMEM;
if (copy_from_user((void *) buf, irqstate, len)) {
r = -EFAULT;
goto out_free;
}
/*
* Don't allow setting the interrupt state
* when there are already interrupts pending
*/
spin_lock(&li->lock);
if (li->pending_irqs) {
r = -EBUSY;
goto out_unlock;
}
for (n = 0; n < len / sizeof(*buf); n++) {
r = do_inject_vcpu(vcpu, &buf[n]);
if (r)
break;
}
out_unlock:
spin_unlock(&li->lock);
out_free:
vfree(buf);
return r;
}
static void store_local_irq(struct kvm_s390_local_interrupt *li,
struct kvm_s390_irq *irq,
unsigned long irq_type)
{
switch (irq_type) {
case IRQ_PEND_MCHK_EX:
case IRQ_PEND_MCHK_REP:
irq->type = KVM_S390_MCHK;
irq->u.mchk = li->irq.mchk;
break;
case IRQ_PEND_PROG:
irq->type = KVM_S390_PROGRAM_INT;
irq->u.pgm = li->irq.pgm;
break;
case IRQ_PEND_PFAULT_INIT:
irq->type = KVM_S390_INT_PFAULT_INIT;
irq->u.ext = li->irq.ext;
break;
case IRQ_PEND_EXT_EXTERNAL:
irq->type = KVM_S390_INT_EXTERNAL_CALL;
irq->u.extcall = li->irq.extcall;
break;
case IRQ_PEND_EXT_CLOCK_COMP:
irq->type = KVM_S390_INT_CLOCK_COMP;
break;
case IRQ_PEND_EXT_CPU_TIMER:
irq->type = KVM_S390_INT_CPU_TIMER;
break;
case IRQ_PEND_SIGP_STOP:
irq->type = KVM_S390_SIGP_STOP;
irq->u.stop = li->irq.stop;
break;
case IRQ_PEND_RESTART:
irq->type = KVM_S390_RESTART;
break;
case IRQ_PEND_SET_PREFIX:
irq->type = KVM_S390_SIGP_SET_PREFIX;
irq->u.prefix = li->irq.prefix;
break;
}
}
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;
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;
struct kvm_s390_irq irq;
unsigned long irq_type;
int cpuaddr;
int n = 0;
spin_lock(&li->lock);
pending_irqs = li->pending_irqs;
memcpy(&sigp_emerg_pending, &li->sigp_emerg_pending,
sizeof(sigp_emerg_pending));
spin_unlock(&li->lock);
for_each_set_bit(irq_type, &pending_irqs, IRQ_PEND_COUNT) {
memset(&irq, 0, sizeof(irq));
if (irq_type == IRQ_PEND_EXT_EMERGENCY)
continue;
if (n + sizeof(irq) > len)
return -ENOBUFS;
store_local_irq(&vcpu->arch.local_int, &irq, irq_type);
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
}
if (test_bit(IRQ_PEND_EXT_EMERGENCY, &pending_irqs)) {
for_each_set_bit(cpuaddr, sigp_emerg_pending, KVM_MAX_VCPUS) {
memset(&irq, 0, sizeof(irq));
if (n + sizeof(irq) > len)
return -ENOBUFS;
irq.type = KVM_S390_INT_EMERGENCY;
irq.u.emerg.code = cpuaddr;
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
}
}
if ((sigp_ctrl & SIGP_CTRL_C) &&
(atomic_read(&vcpu->arch.sie_block->cpuflags) &
CPUSTAT_ECALL_PEND)) {
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;
if (copy_to_user(&buf[n], &irq, sizeof(irq)))
return -EFAULT;
n += sizeof(irq);
}
return n;
}

View File

@ -41,6 +41,9 @@
#include "trace-s390.h"
#define MEM_OP_MAX_SIZE 65536 /* Maximum transfer size for KVM_S390_MEM_OP */
#define LOCAL_IRQS 32
#define VCPU_IRQS_MAX_BUF (sizeof(struct kvm_s390_irq) * \
(KVM_MAX_VCPUS + LOCAL_IRQS))
#define VCPU_STAT(x) offsetof(struct kvm_vcpu, stat.x), KVM_STAT_VCPU
@ -181,6 +184,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_S390_USER_SIGP:
case KVM_CAP_S390_USER_STSI:
case KVM_CAP_S390_SKEYS:
case KVM_CAP_S390_IRQ_STATE:
r = 1;
break;
case KVM_CAP_S390_MEM_OP:
@ -2500,6 +2504,38 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
r = -EFAULT;
break;
}
case KVM_S390_SET_IRQ_STATE: {
struct kvm_s390_irq_state irq_state;
r = -EFAULT;
if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
break;
if (irq_state.len > VCPU_IRQS_MAX_BUF ||
irq_state.len == 0 ||
irq_state.len % sizeof(struct kvm_s390_irq) > 0) {
r = -EINVAL;
break;
}
r = kvm_s390_set_irq_state(vcpu,
(void __user *) irq_state.buf,
irq_state.len);
break;
}
case KVM_S390_GET_IRQ_STATE: {
struct kvm_s390_irq_state irq_state;
r = -EFAULT;
if (copy_from_user(&irq_state, argp, sizeof(irq_state)))
break;
if (irq_state.len == 0) {
r = -EINVAL;
break;
}
r = kvm_s390_get_irq_state(vcpu,
(__u8 __user *) irq_state.buf,
irq_state.len);
break;
}
default:
r = -ENOTTY;
}

View File

@ -272,6 +272,10 @@ int kvm_s390_ext_call_pending(struct kvm_vcpu *vcpu);
extern struct kvm_device_ops kvm_flic_ops;
int kvm_s390_is_stop_irq_pending(struct kvm_vcpu *vcpu);
void kvm_s390_clear_stop_irq(struct kvm_vcpu *vcpu);
int kvm_s390_set_irq_state(struct kvm_vcpu *vcpu,
void __user *buf, int len);
int kvm_s390_get_irq_state(struct kvm_vcpu *vcpu,
__u8 __user *buf, int len);
/* implemented in guestdbg.c */
void kvm_s390_backup_guest_per_regs(struct kvm_vcpu *vcpu);

View File

@ -558,6 +558,13 @@ struct kvm_s390_irq {
} u;
};
struct kvm_s390_irq_state {
__u64 buf;
__u32 flags;
__u32 len;
__u32 reserved[4];
};
/* for KVM_SET_GUEST_DEBUG */
#define KVM_GUESTDBG_ENABLE 0x00000001
@ -803,6 +810,7 @@ struct kvm_ppc_smmu_info {
#define KVM_CAP_S390_USER_STSI 109
#define KVM_CAP_S390_SKEYS 110
#define KVM_CAP_S390_INJECT_IRQ 113
#define KVM_CAP_S390_IRQ_STATE 114
#ifdef KVM_CAP_IRQ_ROUTING
@ -1185,6 +1193,9 @@ struct kvm_s390_ucas_mapping {
#define KVM_S390_SET_SKEYS _IOW(KVMIO, 0xb3, struct kvm_s390_skeys)
/* Available with KVM_CAP_S390_INJECT_IRQ */
#define KVM_S390_IRQ _IOW(KVMIO, 0xb4, struct kvm_s390_irq)
/* Available with KVM_CAP_S390_IRQ_STATE */
#define KVM_S390_SET_IRQ_STATE _IOW(KVMIO, 0xb5, struct kvm_s390_irq_state)
#define KVM_S390_GET_IRQ_STATE _IOW(KVMIO, 0xb6, struct kvm_s390_irq_state)
#define KVM_DEV_ASSIGN_ENABLE_IOMMU (1 << 0)
#define KVM_DEV_ASSIGN_PCI_2_3 (1 << 1)