diff mbox series

[bpf-next,V11,5/7] bpf: drop MTU check when doing TC-BPF redirect to ingress

Message ID 161047352593.4003084.6778762780747210369.stgit@firesoul (mailing list archive)
State Superseded
Delegated to: BPF
Headers show
Series bpf: New approach for BPF MTU handling | expand

Checks

Context Check Description
netdev/cover_letter success Link
netdev/fixes_present success Link
netdev/patch_count success Link
netdev/tree_selection success Clearly marked for bpf-next
netdev/subject_prefix success Link
netdev/cc_maintainers warning 13 maintainers not CCed: kafai@fb.com ast@kernel.org bjorn.topel@intel.com daniel@iogearbox.net jiri@mellanox.com yhs@fb.com kpsingh@kernel.org andrii@kernel.org songliubraving@fb.com edumazet@google.com ap420073@gmail.com xiyou.wangcong@gmail.com davem@davemloft.net
netdev/source_inline success Was 0 now: 0
netdev/verify_signedoff success Link
netdev/module_param success Was 0 now: 0
netdev/build_32bit success Errors and warnings before: 7182 this patch: 7182
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/verify_fixes success Link
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 101 lines checked
netdev/build_allmodconfig_warn success Errors and warnings before: 7587 this patch: 7587
netdev/header_inline success Link
netdev/stable success Stable not CCed

Commit Message

Jesper Dangaard Brouer Jan. 12, 2021, 5:45 p.m. UTC
The use-case for dropping the MTU check when TC-BPF does redirect to
ingress, is described by Eyal Birger in email[0]. The summary is the
ability to increase packet size (e.g. with IPv6 headers for NAT64) and
ingress redirect packet and let normal netstack fragment packet as needed.

[0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/

V9:
 - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect

V4:
 - Keep net_device "up" (IFF_UP) check.
 - Adjustment to handle bpf_redirect_peer() helper

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 include/linux/netdevice.h |   31 +++++++++++++++++++++++++++++--
 net/core/dev.c            |   19 ++-----------------
 net/core/filter.c         |   14 +++++++++++---
 3 files changed, 42 insertions(+), 22 deletions(-)

Comments

John Fastabend Jan. 14, 2021, 9:03 a.m. UTC | #1
Jesper Dangaard Brouer wrote:
> The use-case for dropping the MTU check when TC-BPF does redirect to
> ingress, is described by Eyal Birger in email[0]. The summary is the
> ability to increase packet size (e.g. with IPv6 headers for NAT64) and
> ingress redirect packet and let normal netstack fragment packet as needed.
> 
> [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/
> 
> V9:
>  - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect
> 
> V4:
>  - Keep net_device "up" (IFF_UP) check.
>  - Adjustment to handle bpf_redirect_peer() helper
> 
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> ---
>  include/linux/netdevice.h |   31 +++++++++++++++++++++++++++++--
>  net/core/dev.c            |   19 ++-----------------
>  net/core/filter.c         |   14 +++++++++++---
>  3 files changed, 42 insertions(+), 22 deletions(-)
> 

[...]

> diff --git a/net/core/filter.c b/net/core/filter.c
> index 3f2e593244ca..1908800b671c 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -2083,13 +2083,21 @@ static const struct bpf_func_proto bpf_csum_level_proto = {
>  
>  static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
>  {
> -	return dev_forward_skb(dev, skb);

> +	int ret = ____dev_forward_skb(dev, skb, false);
> +
> +	if (likely(!ret)) {
> +		skb->protocol = eth_type_trans(skb, dev);
> +		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
> +		ret = netif_rx(skb);
> +	}
> +
> +	return ret;

How about putting above block into a dev.c routine call it

 dev_forward_skb_nomtu(...)

or something like that. Then we keep this code next to its pair
with mtu check, dev_forward_skb().

dev_forward_skb() also uses netif_rx_internal() looks like maybe we should
just do the same here?

Thanks,
John
Jesper Dangaard Brouer Jan. 14, 2021, 4:14 p.m. UTC | #2
On Thu, 14 Jan 2021 01:03:33 -0800
John Fastabend <john.fastabend@gmail.com> wrote:

> Jesper Dangaard Brouer wrote:
> > The use-case for dropping the MTU check when TC-BPF does redirect to
> > ingress, is described by Eyal Birger in email[0]. The summary is the
> > ability to increase packet size (e.g. with IPv6 headers for NAT64) and
> > ingress redirect packet and let normal netstack fragment packet as needed.
> > 
> > [0] https://lore.kernel.org/netdev/CAHsH6Gug-hsLGHQ6N0wtixdOa85LDZ3HNRHVd0opR=19Qo4W4Q@mail.gmail.com/
> > 
> > V9:
> >  - Make net_device "up" (IFF_UP) check explicit in skb_do_redirect
> > 
> > V4:
> >  - Keep net_device "up" (IFF_UP) check.
> >  - Adjustment to handle bpf_redirect_peer() helper
> > 
> > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> > ---
> >  include/linux/netdevice.h |   31 +++++++++++++++++++++++++++++--
> >  net/core/dev.c            |   19 ++-----------------
> >  net/core/filter.c         |   14 +++++++++++---
> >  3 files changed, 42 insertions(+), 22 deletions(-)
> >   
> 
> [...]
> 
> > diff --git a/net/core/filter.c b/net/core/filter.c
> > index 3f2e593244ca..1908800b671c 100644
> > --- a/net/core/filter.c
> > +++ b/net/core/filter.c
> > @@ -2083,13 +2083,21 @@ static const struct bpf_func_proto bpf_csum_level_proto = {
> >  
> >  static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
> >  {
> > -	return dev_forward_skb(dev, skb);  
> 
> > +	int ret = ____dev_forward_skb(dev, skb, false);
> > +
> > +	if (likely(!ret)) {
> > +		skb->protocol = eth_type_trans(skb, dev);
> > +		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
> > +		ret = netif_rx(skb);
> > +	}
> > +
> > +	return ret;  
> 
> How about putting above block into a dev.c routine call it
> 
>  dev_forward_skb_nomtu(...)
> 
> or something like that. Then we keep this code next to its pair
> with mtu check, dev_forward_skb().
> 
> dev_forward_skb() also uses netif_rx_internal() looks like maybe we should
> just do the same here?

I love the idea.  I'm coding it up and it looks much nicer.  And yes we
obviously can use netif_rx_internal() once the code in core/dev.c
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1ec3ac5d5bbf..438943f98a9c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3930,11 +3930,38 @@  int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 bool is_skb_forwardable(const struct net_device *dev,
 			const struct sk_buff *skb);
 
+static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
+						 const struct sk_buff *skb,
+						 const bool check_mtu)
+{
+	const u32 vlan_hdr_len = 4; /* VLAN_HLEN */
+	unsigned int len;
+
+	if (!(dev->flags & IFF_UP))
+		return false;
+
+	if (!check_mtu)
+		return true;
+
+	len = dev->mtu + dev->hard_header_len + vlan_hdr_len;
+	if (skb->len <= len)
+		return true;
+
+	/* if TSO is enabled, we don't care about the length as the packet
+	 * could be forwarded without being segmented before
+	 */
+	if (skb_is_gso(skb))
+		return true;
+
+	return false;
+}
+
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
-					       struct sk_buff *skb)
+					       struct sk_buff *skb,
+					       const bool check_mtu)
 {
 	if (skb_orphan_frags(skb, GFP_ATOMIC) ||
-	    unlikely(!is_skb_forwardable(dev, skb))) {
+	    unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) {
 		atomic_long_inc(&dev->rx_dropped);
 		kfree_skb(skb);
 		return NET_RX_DROP;
diff --git a/net/core/dev.c b/net/core/dev.c
index 55499b017a42..51bc7f079958 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2194,28 +2194,13 @@  static inline void net_timestamp_set(struct sk_buff *skb)
 
 bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb)
 {
-	unsigned int len;
-
-	if (!(dev->flags & IFF_UP))
-		return false;
-
-	len = dev->mtu + dev->hard_header_len + VLAN_HLEN;
-	if (skb->len <= len)
-		return true;
-
-	/* if TSO is enabled, we don't care about the length as the packet
-	 * could be forwarded without being segmented before
-	 */
-	if (skb_is_gso(skb))
-		return true;
-
-	return false;
+	return __is_skb_forwardable(dev, skb, true);
 }
 EXPORT_SYMBOL_GPL(is_skb_forwardable);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, true);
 
 	if (likely(!ret)) {
 		skb->protocol = eth_type_trans(skb, dev);
diff --git a/net/core/filter.c b/net/core/filter.c
index 3f2e593244ca..1908800b671c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2083,13 +2083,21 @@  static const struct bpf_func_proto bpf_csum_level_proto = {
 
 static inline int __bpf_rx_skb(struct net_device *dev, struct sk_buff *skb)
 {
-	return dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
+
+	if (likely(!ret)) {
+		skb->protocol = eth_type_trans(skb, dev);
+		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
+		ret = netif_rx(skb);
+	}
+
+	return ret;
 }
 
 static inline int __bpf_rx_skb_no_mac(struct net_device *dev,
 				      struct sk_buff *skb)
 {
-	int ret = ____dev_forward_skb(dev, skb);
+	int ret = ____dev_forward_skb(dev, skb, false);
 
 	if (likely(!ret)) {
 		skb->dev = dev;
@@ -2480,7 +2488,7 @@  int skb_do_redirect(struct sk_buff *skb)
 			goto out_drop;
 		dev = ops->ndo_get_peer_dev(dev);
 		if (unlikely(!dev ||
-			     !is_skb_forwardable(dev, skb) ||
+			     !(dev->flags & IFF_UP) ||
 			     net_eq(net, dev_net(dev))))
 			goto out_drop;
 		skb->dev = dev;