On 08/05/2015 14:31, Joerg Roedel wrote:
> From: Joerg Roedel <[email protected]>
> 
> The allocation size of the kvm_irq_routing_table depends on
> the number of irq routing entries because they are all
> allocated with one kzalloc call.
> 
> When the irq routing table gets bigger this requires high
> order allocations which fail from time to time:
> 
>       qemu-kvm: page allocation failure: order:4, mode:0xd0
> 
> This patch fixes this issue by breaking up the allocation of
> the table and its entries into individual kzalloc calls.
> These could all be satisfied with order-0 allocations, which
> are less likely to fail.
> 
> The downside of this change is the lower performance, because
> of more calls to kzalloc. But given how often kvm_set_irq_routing
> is called in the lifetime of a guest, it doesn't really
> matter much.

It probably doesn't matter much indeed, but can you time the difference?
 kvm_set_irq_routing is not too frequent, but happens enough often that
we had to use a separate SRCU instance just to speed it up (see commit
719d93cd5f5, kvm/irqchip: Speed up KVM_SET_GSI_ROUTING, 2014-01-16).

Paolo

> Signed-off-by: Joerg Roedel <[email protected]>
> ---
>  virt/kvm/irqchip.c | 40 ++++++++++++++++++++++++++++++++--------
>  1 file changed, 32 insertions(+), 8 deletions(-)
> 
> diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
> index 1d56a90..b56168f 100644
> --- a/virt/kvm/irqchip.c
> +++ b/virt/kvm/irqchip.c
> @@ -33,7 +33,6 @@
>  
>  struct kvm_irq_routing_table {
>       int chip[KVM_NR_IRQCHIPS][KVM_IRQCHIP_NUM_PINS];
> -     struct kvm_kernel_irq_routing_entry *rt_entries;
>       u32 nr_rt_entries;
>       /*
>        * Array indexed by gsi. Each entry contains list of irq chips
> @@ -118,11 +117,31 @@ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 
> irq, int level,
>       return ret;
>  }
>  
> +static void free_irq_routing_table(struct kvm_irq_routing_table *rt)
> +{
> +     int i;
> +
> +     if (!rt)
> +             return;
> +
> +     for (i = 0; i < rt->nr_rt_entries; ++i) {
> +             struct kvm_kernel_irq_routing_entry *e;
> +             struct hlist_node *n;
> +
> +             hlist_for_each_entry_safe(e, n, &rt->map[i], link) {
> +                     hlist_del(&e->link);
> +                     kfree(e);
> +             }
> +     }
> +
> +     kfree(rt);
> +}
> +
>  void kvm_free_irq_routing(struct kvm *kvm)
>  {
>       /* Called only during vm destruction. Nobody can use the pointer
>          at this stage */
> -     kfree(kvm->irq_routing);
> +     free_irq_routing_table(kvm->irq_routing);
>  }
>  
>  static int setup_routing_entry(struct kvm_irq_routing_table *rt,
> @@ -173,25 +192,29 @@ int kvm_set_irq_routing(struct kvm *kvm,
>  
>       nr_rt_entries += 1;
>  
> -     new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct hlist_head))
> -                   + (nr * sizeof(struct kvm_kernel_irq_routing_entry)),
> +     new = kzalloc(sizeof(*new) + (nr_rt_entries * sizeof(struct 
> hlist_head)),
>                     GFP_KERNEL);
>  
>       if (!new)
>               return -ENOMEM;
>  
> -     new->rt_entries = (void *)&new->map[nr_rt_entries];
> -
>       new->nr_rt_entries = nr_rt_entries;
>       for (i = 0; i < KVM_NR_IRQCHIPS; i++)
>               for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++)
>                       new->chip[i][j] = -1;
>  
>       for (i = 0; i < nr; ++i) {
> +             struct kvm_kernel_irq_routing_entry *e;
> +
> +             r = -ENOMEM;
> +             e = kzalloc(sizeof(*e), GFP_KERNEL);
> +             if (!e)
> +                     goto out;
> +
>               r = -EINVAL;
>               if (ue->flags)
>                       goto out;
> -             r = setup_routing_entry(new, &new->rt_entries[i], ue);
> +             r = setup_routing_entry(new, e, ue);
>               if (r)
>                       goto out;
>               ++ue;
> @@ -209,6 +232,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
>       r = 0;
>  
>  out:
> -     kfree(new);
> +     free_irq_routing_table(new);
> +
>       return r;
>  }
> 
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/

Reply via email to