[PATCH v3 19/19] KVM: arm64: ITS: Pending table save/restore

[Andre Przywara]

Hi Eric,

just fast-forwarded to the end and noticed this one:


On 06/03/17 11:34, Eric Auger wrote:
> Save and restore the pending tables.
> 
> Pending table restore obviously requires the pendbaser to be
> already set.
> 
> Signed-off-by: Eric Auger <eric.auger at redhat.com>
> 
> ---
> 
> v1 -> v2:
> - do not care about the 1st KB which should be zeroed according to
>   the spec.
> ---
>  virt/kvm/arm/vgic/vgic-its.c | 71 ++++++++++++++++++++++++++++++++++++++++++--
>  1 file changed, 69 insertions(+), 2 deletions(-)
> 
> diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c
> index 27ebabd..24824be 100644
> --- a/virt/kvm/arm/vgic/vgic-its.c
> +++ b/virt/kvm/arm/vgic/vgic-its.c
> @@ -1736,7 +1736,48 @@ static int lookup_table(struct vgic_its *its, gpa_t base, int size, int esz,
>   */
>  static int vgic_its_flush_pending_tables(struct vgic_its *its)
>  {
> -	return -ENXIO;
> +	struct kvm *kvm = its->dev->kvm;
> +	struct vgic_dist *dist = &kvm->arch.vgic;
> +	struct vgic_irq *irq;
> +	int ret;
> +
> +	/**
> +	 * we do not take the dist->lpi_list_lock since we have a garantee
> +	 * the LPI list is not touched while the its lock is held

Can you elaborate on what gives us this guarantee? I see that we have a
locking *order*, but that doesn't mean we can avoid taking the lock. So
to me it looks like we need to take the lpi_list_lock spinlock here,
which unfortunately breaks the kvm_read_guest() calls below.

If you agree on this, you can take a look at the INVALL implementation,
where I faced the same issue. The solution we came up with is
vgic_copy_lpi_list(), which you can call under the lock to create a
(private) copy of the LPI list, which you can later iterate without
holding the lock - and thus are free to call sleeping functions.

Cheers,
Andre.

> +	 */
> +	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
> +		struct kvm_vcpu *vcpu;
> +		gpa_t pendbase, ptr;
> +		bool stored;
> +		u8 val;
> +
> +		vcpu = irq->target_vcpu;
> +		if (!vcpu)
> +			return -EINVAL;
> +
> +		pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
> +
> +		ptr = pendbase + (irq->intid / BITS_PER_BYTE);
> +
> +		ret = kvm_read_guest(kvm, (gpa_t)ptr, &val, 1);
> +		if (ret)
> +			return ret;
> +
> +		stored = val & (irq->intid % BITS_PER_BYTE);
> +		if (stored == irq->pending_latch)
> +			continue;
> +
> +		if (irq->pending_latch)
> +			val |= 1 << (irq->intid % BITS_PER_BYTE);
> +		else
> +			val &= ~(1 << (irq->intid % BITS_PER_BYTE));
> +
> +		ret = kvm_write_guest(kvm, (gpa_t)ptr, &val, 1);
> +		if (ret)
> +			return ret;
> +	}
> +
> +	return 0;
>  }
>  
>  /**
> @@ -1745,7 +1786,33 @@ static int vgic_its_flush_pending_tables(struct vgic_its *its)
>   */
>  static int vgic_its_restore_pending_tables(struct vgic_its *its)
>  {
> -	return -ENXIO;
> +	struct vgic_irq *irq;
> +	struct kvm *kvm = its->dev->kvm;
> +	struct vgic_dist *dist = &kvm->arch.vgic;
> +	int ret;
> +
> +	list_for_each_entry(irq, &dist->lpi_list_head, lpi_list) {
> +		struct kvm_vcpu *vcpu;
> +		gpa_t pendbase, ptr;
> +		u8 val;
> +
> +		vcpu = irq->target_vcpu;
> +		if (!vcpu)
> +			return -EINVAL;
> +
> +		if (!(vcpu->arch.vgic_cpu.pendbaser & GICR_PENDBASER_PTZ))
> +			return 0;
> +
> +		pendbase = PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser);
> +
> +		ptr = pendbase + (irq->intid / BITS_PER_BYTE);
> +
> +		ret = kvm_read_guest(kvm, (gpa_t)ptr, &val, 1);
> +		if (ret)
> +			return ret;
> +		irq->pending_latch = val & (1 << (irq->intid % BITS_PER_BYTE));
> +	}
> +	return 0;
>  }
>  
>  static int vgic_its_flush_ite(struct vgic_its *its, struct its_device *dev,
>