Every time a VIF is destroyed up-to 256 pages may be leaked if packets
with more than MAX_SKB_FRAGS frags where transmitted from the guest.
Even worse, if another user of ballooned pages allocated one of these
ballooned pages it would not handle the the unexpectedly non-zero page
count (e.g., gntde
On 03/03/15 16:26, David Vrabel wrote:
Every time a VIF is destroyed up-to 256 pages may be leaked if packets
"up to" (and maybe a comma before it?)
with more than MAX_SKB_FRAGS frags where transmitted from the guest.
were
On Tue, 2015-03-03 at 16:26 +, David Vrabel wrote:
> Every time a VIF is destroyed up-to 256 pages may be leaked if packets
> with more than MAX_SKB_FRAGS frags where transmitted from the guest.
> Even worse, if another user of ballooned pages allocated one of these
> ballooned pages it would n
On 04/03/15 09:48, Ian Campbell wrote:
> On Tue, 2015-03-03 at 16:26 +, David Vrabel wrote:
>> Every time a VIF is destroyed up-to 256 pages may be leaked if packets
>> with more than MAX_SKB_FRAGS frags where transmitted from the guest.
>> Even worse, if another user of ballooned pages allocat
On Wed, 2015-03-04 at 09:56 +, David Vrabel wrote:
> On 04/03/15 09:48, Ian Campbell wrote:
> > On Tue, 2015-03-03 at 16:26 +, David Vrabel wrote:
> >> Every time a VIF is destroyed up-to 256 pages may be leaked if packets
> >> with more than MAX_SKB_FRAGS frags where transmitted from the g