diff mbox

[v3,2/2] macvtap: restore vlan header on user read

Message ID 20120503231152.GA8602@nanobar
State Superseded, archived
Headers show

Commit Message

Basil Gor May 3, 2012, 11:11 p.m. UTC 
On Thu, May 03, 2012 at 07:22:25PM +0400, Basil Gor wrote:
> On Thu, May 03, 2012 at 05:31:10PM +0300, Michael S. Tsirkin wrote:
> > On Thu, May 03, 2012 at 06:37:46AM -0700, Eric W. Biederman wrote:
> > > "Michael S. Tsirkin" <mst@redhat.com> writes:
> > > 
> > > > On Wed, Apr 25, 2012 at 10:31:25PM -0700, Eric W. Biederman wrote:
> > > >> Basil Gor <basil.gor@gmail.com> writes:
> > > >> 
> > > >> > Vlan tag is restored during buffer transmit to a network device (bridge
> > > >> > port) in bridging code in case of tun/tap driver. In case of macvtap it
> > > >> > has to be done explicitly. Otherwise vlan_tci is ignored and user always
> > > >> > gets untagged packets.
> > > >> 
> > > >> We could quibble about efficiencies but this looks good except for
> > > >> macvtap_recvmsg which isn't setting the auxdata for the vlan header.
> > > >> 
> > > >> Eric
> > > >
> > > > Right. I'm guessing we need to support old userspace
> > > > so if there's auxdata, put vlan there but if not,
> > > > put the vlan in the packet like this patch does.
> > > 
> > > This patch isn't horrible.
> > > 
> > > Still why copy the skb when you can just split the copy to userspace
> > > into a couple of pieces?
> > > 
> > > We don't need to change the skb and changing the skb looks like
> > > it is likely to confuse things and cause bugs because we are
> > > not working with a consistent model of how vlan information
> > > is encoded.
> > > 
> > > Still something needs to happen and this works in more cases even if it
> > > isn't perfect.
> > > 
> > > Eric
> > 
> > Absolutely. And it's easier than I thought.
> > So we can do something like the below (warning: compiled only).
> > Basil - want to take a look?
> 
> Sure, I'll give it a try.
> Thanks
> 
> Basil Gor
> 
> > My only concern if we put this logic in an out of way
> > driver like macvtap will people remember to update it?
> > Maybe better to update skb_copy_datagram_const_iovec which is in core?
> > 
> > 
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> > 
> > diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
> > index 0427c65..5a1724c 100644
> > --- a/drivers/net/macvtap.c
> > +++ b/drivers/net/macvtap.c
> > @@ -1,5 +1,6 @@
> >  #include <linux/etherdevice.h>
> >  #include <linux/if_macvlan.h>
> > +#include <linux/if_vlan.h>
> >  #include <linux/interrupt.h>
> >  #include <linux/nsproxy.h>
> >  #include <linux/compat.h>
> > @@ -759,6 +760,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
> >  	struct macvlan_dev *vlan;
> >  	int ret;
> >  	int vnet_hdr_len = 0;
> > +	int vlan_offset = 0;
> >  
> >  	if (q->flags & IFF_VNET_HDR) {
> >  		struct virtio_net_hdr vnet_hdr;
> > @@ -776,8 +778,29 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
> >  
> >  	len = min_t(int, skb->len, len);
        skb->len + VLAN_HLEN if vlan tag present
> >  
> > -	ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
> > +	if (vlan_tx_tag_present(skb)) {
> > +		struct {
> > +			__be16 h_vlan_proto;
> > +			__be16 h_vlan_TCI;
> > +		} veth;
> > + 		veth.h_vlan_proto = htons(ETH_P_8021Q);
> > + 		veth.h_vlan_TCI = vlan_tx_tag_get(skb);
                htons(vlan_tx_tag_get(skb))
> > +
> > +		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
> > +		ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len,
> > +						    vlan_offset);
                do we need to count how much we copy carefully?
> > +		if (ret)
> > +			goto done;
> > +		ret = memcpy_toiovecend(iv, (unsigned char *)&veth, vlan_offset,
> > +					sizeof veth);
                offset has to be vnet_hdr_len + vlan_offset
> > +		if (ret)
> > +			goto done;
> > +		vlan_offset += sizeof veth;
                offset to use in next copy: vnet_hdr_len + vlan_offset + sizeof(veth)
> > +	}
> > +	ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, vnet_hdr_len,
> > +					    len);
> >  
> > +done:
> >  	rcu_read_lock_bh();
> >  	vlan = rcu_dereference_bh(q->vlan);
> >  	if (vlan)

Below is a bit reworked version I've tested.

---
 drivers/net/macvtap.c |   43 ++++++++++++++++++++++++++++++++++++++-----
 1 files changed, 38 insertions(+), 5 deletions(-)

Comments

Michael S. Tsirkin May 3, 2012, 11:30 p.m. UTC | #1 
On Fri, May 04, 2012 at 03:11:52AM +0400, Basil Gor wrote:
> Below is a bit reworked version I've tested.

Will review thanks.

Can you add the signature according to the rules pls?

> ---
>  drivers/net/macvtap.c |   43 ++++++++++++++++++++++++++++++++++++++-----
>  1 files changed, 38 insertions(+), 5 deletions(-)
> 
> diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
> index 0427c65..cb8fd50 100644
> --- a/drivers/net/macvtap.c
> +++ b/drivers/net/macvtap.c
> @@ -1,5 +1,6 @@
>  #include <linux/etherdevice.h>
>  #include <linux/if_macvlan.h>
> +#include <linux/if_vlan.h>
>  #include <linux/interrupt.h>
>  #include <linux/nsproxy.h>
>  #include <linux/compat.h>
> @@ -759,6 +760,8 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
>  	struct macvlan_dev *vlan;
>  	int ret;
>  	int vnet_hdr_len = 0;
> +	int vlan_offset = 0;
> +	int copied;
>  
>  	if (q->flags & IFF_VNET_HDR) {
>  		struct virtio_net_hdr vnet_hdr;
> @@ -773,18 +776,48 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q,
>  		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
>  			return -EFAULT;
>  	}
> +	copied = vnet_hdr_len;
> +
> +	if (!vlan_tx_tag_present(skb))
> +		len = min_t(int, skb->len, len);
> +	else {
> +		int copy;
> +		struct {
> +			__be16 h_vlan_proto;
> +			__be16 h_vlan_TCI;
> +		} veth;
> +		veth.h_vlan_proto = htons(ETH_P_8021Q);
> +		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
> +
> +		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
> +		len = min_t(int, skb->len + VLAN_HLEN, len);
> +
> +		copy = min_t(int, vlan_offset, len);
> +		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
> +		len -= copy;
> +		copied += copy;
> +		if (ret || !len)
> +			goto done;
> +
> +		copy = min_t(int, sizeof(veth), len);
> +		ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
> +		len -= copy;
> +		copied += copy;
> +		if (ret || !len)
> +			goto done;
> +	}
>  
> -	len = min_t(int, skb->len, len);
> -
> -	ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
> +	ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
> +	copied += len;
>  
> +done:
>  	rcu_read_lock_bh();
>  	vlan = rcu_dereference_bh(q->vlan);
>  	if (vlan)
> -		macvlan_count_rx(vlan, len, ret == 0, 0);
> +		macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
>  	rcu_read_unlock_bh();
>  
> -	return ret ? ret : (len + vnet_hdr_len);
> +	return ret ? ret : copied;
>  }
>  
>  static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,
> -- 
> 1.7.6.5
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 0427c65..cb8fd50 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1,5 +1,6 @@ 
 #include <linux/etherdevice.h>
 #include <linux/if_macvlan.h>
+#include <linux/if_vlan.h>
 #include <linux/interrupt.h>
 #include <linux/nsproxy.h>
 #include <linux/compat.h>
@@ -759,6 +760,8 @@  static ssize_t macvtap_put_user(struct macvtap_queue *q,
 	struct macvlan_dev *vlan;
 	int ret;
 	int vnet_hdr_len = 0;
+	int vlan_offset = 0;
+	int copied;
 
 	if (q->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr vnet_hdr;
@@ -773,18 +776,48 @@  static ssize_t macvtap_put_user(struct macvtap_queue *q,
 		if (memcpy_toiovecend(iv, (void *)&vnet_hdr, 0, sizeof(vnet_hdr)))
 			return -EFAULT;
 	}
+	copied = vnet_hdr_len;
+
+	if (!vlan_tx_tag_present(skb))
+		len = min_t(int, skb->len, len);
+	else {
+		int copy;
+		struct {
+			__be16 h_vlan_proto;
+			__be16 h_vlan_TCI;
+		} veth;
+		veth.h_vlan_proto = htons(ETH_P_8021Q);
+		veth.h_vlan_TCI = htons(vlan_tx_tag_get(skb));
+
+		vlan_offset = offsetof(struct vlan_ethhdr, h_vlan_proto);
+		len = min_t(int, skb->len + VLAN_HLEN, len);
+
+		copy = min_t(int, vlan_offset, len);
+		ret = skb_copy_datagram_const_iovec(skb, 0, iv, copied, copy);
+		len -= copy;
+		copied += copy;
+		if (ret || !len)
+			goto done;
+
+		copy = min_t(int, sizeof(veth), len);
+		ret = memcpy_toiovecend(iv, (void *)&veth, copied, copy);
+		len -= copy;
+		copied += copy;
+		if (ret || !len)
+			goto done;
+	}
 
-	len = min_t(int, skb->len, len);
-
-	ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len);
+	ret = skb_copy_datagram_const_iovec(skb, vlan_offset, iv, copied, len);
+	copied += len;
 
+done:
 	rcu_read_lock_bh();
 	vlan = rcu_dereference_bh(q->vlan);
 	if (vlan)
-		macvlan_count_rx(vlan, len, ret == 0, 0);
+		macvlan_count_rx(vlan, copied - vnet_hdr_len, ret == 0, 0);
 	rcu_read_unlock_bh();
 
-	return ret ? ret : (len + vnet_hdr_len);
+	return ret ? ret : copied;
 }
 
 static ssize_t macvtap_do_read(struct macvtap_queue *q, struct kiocb *iocb,