From: Alexander Duyck
> Sent: 01 February 2016 18:18
> >> 1) Unaligned accesses
> >
> > Remember the even if you do a 'realignment copy' of the IP header,
> > at some point the 'userdata' of the packet has to be accessed.
> > Mostly this will be with memcpy() and you want that copy to be aligned.
From: David Miller
> Sent: 31 January 2016 03:45
> To: alexander.du...@gmail.com
...
> > I would really prefer to keep the pages DMA aligned, and the skb->data
> > IP aligned. If nothing else it has the advantage of actually having
> > the proper alignment on all the headers if I only pull the
On Mon, Feb 1, 2016 at 8:50 AM, David Laight wrote:
> From: David Miller
>> Sent: 31 January 2016 03:45
>> To: alexander.du...@gmail.com
> ...
>> > I would really prefer to keep the pages DMA aligned, and the skb->data
>> > IP aligned. If nothing else it has the
From: Alexander Duyck
Date: Sun, 31 Jan 2016 01:12:03 -0800
> If nothing else we can discuss this further in Seville as I am just
> not convinced changing the drivers is the right way to go about fixing
> this, and I won't have the time to really get around to doing
On (01/31/16 11:17), David Miller wrote:
>
> > If nothing else we can discuss this further in Seville as I am just
> > not convinced changing the drivers is the right way to go about fixing
> > this, and I won't have the time to really get around to doing any of
> > it until I have come back from
On Sat, Jan 30, 2016 at 7:45 PM, David Miller wrote:
> From: Alexander Duyck
> Date: Sat, 30 Jan 2016 17:13:35 -0800
>
>> The NIC hardware only allows us to set receive buffer sizes in 1K
>> increments. I think fm10k may be an exception in that it
On Sat, 2016-01-30 at 10:36 -0800, Alexander Duyck wrote:
> As far as the NET_IP_ALIGN on the page offset I think it is a horrible
> idea. Basically it means we have to allocate at least 1K more space
> than we need since page sizes are powers of 2, and buffer sizes in
> hardware are measured in
On Sat, Jan 30, 2016 at 8:17 AM, Sowmini Varadhan
wrote:
> On (01/29/16 19:23), Eric Dumazet wrote:
>> BTW, even a memcpy(_addrs->v4addrs, >saddr, 8) could crash, as
>> the compiler can certainly assume src and dst are 4 bytes aligned, and
>> could use word accesses
On Sat, Jan 30, 2016 at 8:17 AM, Sowmini Varadhan
wrote:
> On (01/29/16 19:23), Eric Dumazet wrote:
>> BTW, even a memcpy(_addrs->v4addrs, >saddr, 8) could crash, as
>> the compiler can certainly assume src and dst are 4 bytes aligned, and
>> could use word accesses
On (01/30/16 09:43), Tom Herbert wrote:
> That is not the only case, If a GRE TEB packet is ever received and
> flow dissector is called for any reason (like skb_get_hash) there's
> going to be problems-- and this doesn't require GRE to even be
> configured on the host.
>
> I have a patch that
On (01/29/16 19:23), Eric Dumazet wrote:
> BTW, even a memcpy(_addrs->v4addrs, >saddr, 8) could crash, as
> the compiler can certainly assume src and dst are 4 bytes aligned, and
> could use word accesses when inlining memcpy() even on Sparc.
>
> Apparently the compiler used by Sowmini is gentle.
On Sat, Jan 30, 2016 at 11:26 AM, Eric Dumazet wrote:
> On Sat, 2016-01-30 at 10:36 -0800, Alexander Duyck wrote:
>
>> As far as the NET_IP_ALIGN on the page offset I think it is a horrible
>> idea. Basically it means we have to allocate at least 1K more space
>> than we
From: Alexander Duyck
Date: Sat, 30 Jan 2016 17:13:35 -0800
> The NIC hardware only allows us to set receive buffer sizes in 1K
> increments. I think fm10k may be an exception in that it may be able
> to support 512 byte, but otherwise igb and ixgbe are strictly set
From: Eric Dumazet
Date: Fri, 29 Jan 2016 19:23:54 -0800
> On Fri, 2016-01-29 at 18:49 -0800, Alexander Duyck wrote:
>> This patch fixes an issue with unaligned accesses when using
>> eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
>> The fact
On Fri, 2016-01-29 at 18:49 -0800, Alexander Duyck wrote:
> This patch fixes an issue with unaligned accesses when using
> eth_get_headlen on a page that was DMA aligned instead of being IP aligned.
> The fact is when trying to check the length we don't need to be looking at
> the flow label so we
On Fri, Jan 29, 2016 at 7:35 PM, David Miller wrote:
> From: Eric Dumazet
> Date: Fri, 29 Jan 2016 19:23:54 -0800
>
>> On Fri, 2016-01-29 at 18:49 -0800, Alexander Duyck wrote:
>>> This patch fixes an issue with unaligned accesses when using
>>>
16 matches
Mail list logo