/* * Locking order is always: * kvm->lock (mutex) * vcpu->mutex (mutex) * kvm->arch.config_lock (mutex) * its->cmd_lock (mutex) * its->its_lock (mutex) * vgic_dist->lpi_xa.xa_lock * vgic_cpu->ap_list_lock must be taken with IRQs disabled * vgic_irq->irq_lock must be taken with IRQs disabled * * As the ap_list_lock might be taken from the timer interrupt handler, * we have to disable IRQs before taking this lock and everything lower * than it. * * The config_lock has additional ordering requirements: * kvm->slots_lock * kvm->srcu * kvm->arch.config_lock * * If you need to take multiple locks, always take the upper lock first, * then the lower ones, e.g. first take the its_lock, then the irq_lock. * If you are already holding a lock and need to take a higher one, you * have to drop the lower ranking lock first and re-acquire it after having * taken the upper one. * * When taking more than one ap_list_lock at the same time, always take the * lowest numbered VCPU's ap_list_lock first, so: * vcpuX->vcpu_id < vcpuY->vcpu_id: * raw_spin_lock(vcpuX->arch.vgic_cpu.ap_list_lock); * raw_spin_lock(vcpuY->arch.vgic_cpu.ap_list_lock); * * Since the VGIC must support injecting virtual interrupts from ISRs, we have * to use the raw_spin_lock_irqsave/raw_spin_unlock_irqrestore versions of outer * spinlocks for any lock that may be taken while injecting an interrupt.
*/
/* * Index the VM's xarray of mapped LPIs and return a reference to the IRQ * structure. The caller is expected to call vgic_put_irq() later once it's * finished with the IRQ.
*/ staticstruct vgic_irq *vgic_get_lpi(struct kvm *kvm, u32 intid)
{ struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq = NULL;
rcu_read_lock();
irq = xa_load(&dist->lpi_xa, intid); if (!vgic_try_get_irq_ref(irq))
irq = NULL;
rcu_read_unlock();
return irq;
}
/* * This looks up the virtual interrupt ID to get the corresponding * struct vgic_irq. It also increases the refcount, so any caller is expected * to call vgic_put_irq() once it's finished with this IRQ.
*/ struct vgic_irq *vgic_get_irq(struct kvm *kvm, u32 intid)
{ /* SPIs */ if (intid >= VGIC_NR_PRIVATE_IRQS &&
intid < (kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) {
intid = array_index_nospec(intid, kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS); return &kvm->arch.vgic.spis[intid - VGIC_NR_PRIVATE_IRQS];
}
/* LPIs */ if (intid >= VGIC_MIN_LPI) return vgic_get_lpi(kvm, intid);
/** * vgic_target_oracle - compute the target vcpu for an irq * * @irq: The irq to route. Must be already locked. * * Based on the current state of the interrupt (enabled, pending, * active, vcpu and target_vcpu), compute the next vcpu this should be * given to. Return NULL if this shouldn't be injected at all. * * Requires the IRQ lock to be held.
*/ staticstruct kvm_vcpu *vgic_target_oracle(struct vgic_irq *irq)
{
lockdep_assert_held(&irq->irq_lock);
/* If the interrupt is active, it must stay on the current vcpu */ if (irq->active) return irq->vcpu ? : irq->target_vcpu;
/* * If the IRQ is not active but enabled and pending, we should direct * it to its configured target VCPU. * If the distributor is disabled, pending interrupts shouldn't be * forwarded.
*/ if (irq->enabled && irq_is_pending(irq)) { if (unlikely(irq->target_vcpu &&
!irq->target_vcpu->kvm->arch.vgic.enabled)) return NULL;
return irq->target_vcpu;
}
/* If neither active nor pending and enabled, then this IRQ should not * be queued to any VCPU.
*/ return NULL;
}
/* * The order of items in the ap_lists defines how we'll pack things in LRs as * well, the first items in the list being the first things populated in the * LRs. * * A hard rule is that active interrupts can never be pushed out of the LRs * (and therefore take priority) since we cannot reliably trap on deactivation * of IRQs and therefore they have to be present in the LRs. * * Otherwise things should be sorted by the priority field and the GIC * hardware support will take care of preemption of priority groups etc. * * Return negative if "a" sorts before "b", 0 to preserve order, and positive * to sort "b" before "a".
*/ staticint vgic_irq_cmp(void *priv, conststruct list_head *a, conststruct list_head *b)
{ struct vgic_irq *irqa = container_of(a, struct vgic_irq, ap_list); struct vgic_irq *irqb = container_of(b, struct vgic_irq, ap_list); bool penda, pendb; int ret;
/* * list_sort may call this function with the same element when * the list is fairly long.
*/ if (unlikely(irqa == irqb)) return 0;
if (!penda || !pendb) {
ret = (int)pendb - (int)penda; goto out;
}
/* Both pending and enabled, sort by priority */
ret = irqa->priority - irqb->priority;
out:
raw_spin_unlock(&irqb->irq_lock);
raw_spin_unlock(&irqa->irq_lock); return ret;
}
/* Must be called with the ap_list_lock held */ staticvoid vgic_sort_ap_list(struct kvm_vcpu *vcpu)
{ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
/* * Only valid injection if changing level for level-triggered IRQs or for a * rising edge, and in-kernel connected IRQ lines can only be controlled by * their owner.
*/ staticbool vgic_validate_injection(struct vgic_irq *irq, bool level, void *owner)
{ if (irq->owner != owner) returnfalse;
switch (irq->config) { case VGIC_CONFIG_LEVEL: return irq->line_level != level; case VGIC_CONFIG_EDGE: return level;
}
returnfalse;
}
/* * Check whether an IRQ needs to (and can) be queued to a VCPU's ap list. * Do the queuing if necessary, taking the right locks in the right order. * Returns true when the IRQ was queued, false otherwise. * * Needs to be entered with the IRQ lock already held, but will return * with all locks dropped.
*/ bool vgic_queue_irq_unlock(struct kvm *kvm, struct vgic_irq *irq, unsignedlong flags) __releases(&irq->irq_lock)
{ struct kvm_vcpu *vcpu;
lockdep_assert_held(&irq->irq_lock);
retry:
vcpu = vgic_target_oracle(irq); if (irq->vcpu || !vcpu) { /* * If this IRQ is already on a VCPU's ap_list, then it * cannot be moved or modified and there is no more work for * us to do. * * Otherwise, if the irq is not pending and enabled, it does * not need to be inserted into an ap_list and there is also * no more work for us to do.
*/
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
/* * We have to kick the VCPU here, because we could be * queueing an edge-triggered interrupt for which we * get no EOI maintenance interrupt. In that case, * while the IRQ is already on the VCPU's AP list, the * VCPU could have EOI'ed the original interrupt and * won't see this one until it exits for some other * reason.
*/ if (vcpu) {
kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
} returnfalse;
}
/* * We must unlock the irq lock to take the ap_list_lock where * we are going to insert this new pending interrupt.
*/
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
/* someone can do stuff here, which we re-check below */
/* * Did something change behind our backs? * * There are two cases: * 1) The irq lost its pending state or was disabled behind our * backs and/or it was queued to another VCPU's ap_list. * 2) Someone changed the affinity on this irq behind our * backs and we are now holding the wrong ap_list_lock. * * In both cases, drop the locks and retry.
*/
if (unlikely(irq->vcpu || vcpu != vgic_target_oracle(irq))) {
raw_spin_unlock(&irq->irq_lock);
raw_spin_unlock_irqrestore(&vcpu->arch.vgic_cpu.ap_list_lock,
flags);
/* * Grab a reference to the irq to reflect the fact that it is * now in the ap_list. This is safe as the caller must already hold a * reference on the irq.
*/
vgic_get_irq_ref(irq);
list_add_tail(&irq->ap_list, &vcpu->arch.vgic_cpu.ap_list_head);
irq->vcpu = vcpu;
/** * kvm_vgic_inject_irq - Inject an IRQ from a device to the vgic * @kvm: The VM structure pointer * @vcpu: The CPU for PPIs or NULL for global interrupts * @intid: The INTID to inject a new state to. * @level: Edge-triggered: true: to trigger the interrupt * false: to ignore the call * Level-sensitive true: raise the input signal * false: lower the input signal * @owner: The opaque pointer to the owner of the IRQ being raised to verify * that the caller is allowed to inject this IRQ. Userspace * injections will have owner == NULL. * * The VGIC is not concerned with devices being active-LOW or active-HIGH for * level-sensitive interrupts. You can think of the level parameter as 1 * being HIGH and 0 being LOW and all devices being active-HIGH.
*/ int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, unsignedint intid, bool level, void *owner)
{ struct vgic_irq *irq; unsignedlong flags; int ret;
ret = vgic_lazy_init(kvm); if (ret) return ret;
if (!vcpu && intid < VGIC_NR_PRIVATE_IRQS) return -EINVAL;
/* @irq->irq_lock must be held */ staticint kvm_vgic_map_irq(struct kvm_vcpu *vcpu, struct vgic_irq *irq, unsignedint host_irq, struct irq_ops *ops)
{ struct irq_desc *desc; struct irq_data *data;
/* * Find the physical IRQ number corresponding to @host_irq
*/
desc = irq_to_desc(host_irq); if (!desc) {
kvm_err("%s: no interrupt descriptor\n", __func__); return -EINVAL;
}
data = irq_desc_get_irq_data(desc); while (data->parent_data)
data = data->parent_data;
/** * kvm_vgic_reset_mapped_irq - Reset a mapped IRQ * @vcpu: The VCPU pointer * @vintid: The INTID of the interrupt * * Reset the active and pending states of a mapped interrupt. Kernel * subsystems injecting mapped interrupts should reset their interrupt lines * when we are doing a reset of the VM.
*/ void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid)
{ struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsignedlong flags;
int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsignedint vintid)
{ struct vgic_irq *irq = vgic_get_vcpu_irq(vcpu, vintid); unsignedlong flags; int ret = -1;
raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw)
ret = irq->hwintid;
raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
vgic_put_irq(vcpu->kvm, irq); return ret;
}
/** * kvm_vgic_set_owner - Set the owner of an interrupt for a VM * * @vcpu: Pointer to the VCPU (used for PPIs) * @intid: The virtual INTID identifying the interrupt (PPI or SPI) * @owner: Opaque pointer to the owner * * Returns 0 if intid is not already used by another in-kernel device and the * owner is set, otherwise returns an error code.
*/ int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsignedint intid, void *owner)
{ struct vgic_irq *irq; unsignedlong flags; int ret = 0;
if (!vgic_initialized(vcpu->kvm)) return -EAGAIN;
/* SGIs and LPIs cannot be wired up to any device */ if (!irq_is_ppi(intid) && !vgic_valid_spi(vcpu->kvm, intid)) return -EINVAL;
/** * vgic_prune_ap_list - Remove non-relevant interrupts from the list * * @vcpu: The VCPU pointer * * Go over the list of "interesting" interrupts, and prune those that we * won't have to consider in the near future.
*/ staticvoid vgic_prune_ap_list(struct kvm_vcpu *vcpu)
{ struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_irq *irq, *tmp; bool deleted_lpis = false;
if (!target_vcpu) { /* * We don't need to process this interrupt any * further, move it off the list.
*/
list_del(&irq->ap_list);
irq->vcpu = NULL;
raw_spin_unlock(&irq->irq_lock);
/* * This vgic_put_irq call matches the * vgic_get_irq_ref in vgic_queue_irq_unlock, * where we added the LPI to the ap_list. As * we remove the irq from the list, we drop * also drop the refcount.
*/
deleted_lpis |= vgic_put_irq_norelease(vcpu->kvm, irq); continue;
}
if (target_vcpu == vcpu) { /* We're on the right CPU */
raw_spin_unlock(&irq->irq_lock); continue;
}
/* This interrupt looks like it has to be migrated. */
/* * If the affinity has been preserved, move the * interrupt around. Otherwise, it means things have * changed while the interrupt was unlocked, and we * need to replay this. * * In all cases, we cannot trust the list not to have * changed, so we restart from the beginning.
*/ if (target_vcpu == vgic_target_oracle(irq)) { struct vgic_cpu *new_cpu = &target_vcpu->arch.vgic_cpu;
/* Requires the irq_lock to be held. */ staticinlinevoid vgic_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr)
{
lockdep_assert_held(&irq->irq_lock);
/* * If we have multi-SGIs in the pipeline, we need to * guarantee that they are all seen before any IRQ of * lower priority. In that case, we need to filter out * these interrupts by exiting early. This is easy as * the AP list has been sorted already.
*/ if (multi_sgi && irq->priority > prio) {
raw_spin_unlock(&irq->irq_lock); break;
}
if (likely(vgic_target_oracle(irq) == vcpu)) {
vgic_populate_lr(vcpu, irq, count++);
if (irq->source)
prio = irq->priority;
}
raw_spin_unlock(&irq->irq_lock);
if (count == kvm_vgic_global_state.nr_lr) { if (!list_is_last(&irq->ap_list,
&vgic_cpu->ap_list_head))
vgic_set_underflow(vcpu); break;
}
}
/* Nuke remaining LRs */ for (i = count ; i < kvm_vgic_global_state.nr_lr; i++)
vgic_clear_lr(vcpu, i);
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vcpu->arch.vgic_cpu.vgic_v2.used_lrs = count; else
vcpu->arch.vgic_cpu.vgic_v3.used_lrs = count;
}
staticinlinebool can_access_vgic_from_kernel(void)
{ /* * GICv2 can always be accessed from the kernel because it is * memory-mapped, and VHE systems can access GICv3 EL2 system * registers.
*/ return !static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) || has_vhe();
}
/* Flush our emulation state into the GIC hardware before entering the guest. */ void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu)
{ /* * If in a nested state, we must return early. Two possibilities: * * - If we have any pending IRQ for the guest and the guest * expects IRQs to be handled in its virtual EL2 mode (the * virtual IMO bit is set) and it is not already running in * virtual EL2 mode, then we have to emulate an IRQ * exception to virtual EL2. * * We do that by placing a request to ourselves which will * abort the entry procedure and inject the exception at the * beginning of the run loop. * * - Otherwise, do exactly *NOTHING*. The guest state is * already loaded, and we can carry on with running it. * * If we have NV, but are not in a nested state, compute the * maintenance interrupt state, as it may fire.
*/ if (vgic_state_is_nested(vcpu)) { if (kvm_vgic_vcpu_pending_irq(vcpu))
kvm_make_request(KVM_REQ_GUEST_HYP_IRQ_PENDING, vcpu);
return;
}
if (vcpu_has_nv(vcpu))
vgic_v3_nested_update_mi(vcpu);
/* * If there are no virtual interrupts active or pending for this * VCPU, then there is no work to do and we can bail out without * taking any lock. There is a potential race with someone injecting * interrupts to the VCPU, but it is a benign race as the VCPU will * either observe the new interrupt before or after doing this check, * and introducing additional synchronization mechanism doesn't change * this. * * Note that we still need to go through the whole thing if anything * can be directly injected (GICv4).
*/ if (list_empty(&vcpu->arch.vgic_cpu.ap_list_head) &&
!vgic_supports_direct_irqs(vcpu->kvm)) return;
DEBUG_SPINLOCK_BUG_ON(!irqs_disabled());
if (!list_empty(&vcpu->arch.vgic_cpu.ap_list_head)) {
raw_spin_lock(&vcpu->arch.vgic_cpu.ap_list_lock);
vgic_flush_lr_state(vcpu);
raw_spin_unlock(&vcpu->arch.vgic_cpu.ap_list_lock);
}
if (can_access_vgic_from_kernel())
vgic_restore_state(vcpu);
if (vgic_supports_direct_irqs(vcpu->kvm))
vgic_v4_commit(vcpu);
}
void kvm_vgic_load(struct kvm_vcpu *vcpu)
{ if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
__vgic_v3_activate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return;
}
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_load(vcpu); else
vgic_v3_load(vcpu);
}
void kvm_vgic_put(struct kvm_vcpu *vcpu)
{ if (unlikely(!irqchip_in_kernel(vcpu->kvm) || !vgic_initialized(vcpu->kvm))) { if (has_vhe() && static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
__vgic_v3_deactivate_traps(&vcpu->arch.vgic_cpu.vgic_v3); return;
}
if (!static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif))
vgic_v2_put(vcpu); else
vgic_v3_put(vcpu);
}
/* * We've injected an interrupt, time to find out who deserves * a good kick...
*/
kvm_for_each_vcpu(c, vcpu, kvm) { if (kvm_vgic_vcpu_pending_irq(vcpu)) {
kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
kvm_vcpu_kick(vcpu);
}
}
}
/* * Level-triggered mapped IRQs are special because we only observe rising * edges as input to the VGIC. * * If the guest never acked the interrupt we have to sample the physical * line and set the line level, because the device state could have changed * or we simply need to process the still pending interrupt later. * * We could also have entered the guest with the interrupt active+pending. * On the next exit, we need to re-evaluate the pending state, as it could * otherwise result in a spurious interrupt by injecting a now potentially * stale pending state. * * If this causes us to lower the level, we have to also clear the physical * active state, since we will otherwise never be told when the interrupt * becomes asserted again. * * Another case is when the interrupt requires a helping hand on * deactivation (no HW deactivation, for example).
*/ void vgic_irq_handle_resampling(struct vgic_irq *irq, bool lr_deactivated, bool lr_pending)
{ if (vgic_irq_is_mapped_level(irq)) { bool resample = false;
Die Informationen auf dieser Webseite wurden
nach bestem Wissen sorgfältig zusammengestellt. Es wird jedoch weder Vollständigkeit, noch Richtigkeit,
noch Qualität der bereit gestellten Informationen zugesichert.
Bemerkung:
Die farbliche Syntaxdarstellung und die Messung sind noch experimentell.