diff mbox series

[bpf-next,V3,1/6] bpf: Remove MTU check in __bpf_skb_max_len

Message ID 160216614239.882446.4447190431655011838.stgit@firesoul (mailing list archive)
State Changes Requested
Delegated to: BPF
Headers show
Series bpf: New approach for BPF MTU handling | expand

Commit Message

Jesper Dangaard Brouer Oct. 8, 2020, 2:09 p.m. UTC
Multiple BPF-helpers that can manipulate/increase the size of the SKB uses
__bpf_skb_max_len() as the max-length. This function limit size against
the current net_device MTU (skb->dev->mtu).

When a BPF-prog grow the packet size, then it should not be limited to the
MTU. The MTU is a transmit limitation, and software receiving this packet
should be allowed to increase the size. Further more, current MTU check in
__bpf_skb_max_len uses the MTU from ingress/current net_device, which in
case of redirects uses the wrong net_device.

Keep a sanity max limit of IP6_MAX_MTU (under CONFIG_IPV6) which is 64KiB
plus 40 bytes IPv6 header size. If compiled without IPv6 use IP_MAX_MTU.

V3: replace __bpf_skb_max_len() with define and use IPv6 max MTU size.

Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
---
 net/core/filter.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

Comments

Daniel Borkmann Oct. 9, 2020, 4:12 p.m. UTC | #1
On 10/8/20 4:09 PM, Jesper Dangaard Brouer wrote:
> Multiple BPF-helpers that can manipulate/increase the size of the SKB uses
> __bpf_skb_max_len() as the max-length. This function limit size against
> the current net_device MTU (skb->dev->mtu).
> 
> When a BPF-prog grow the packet size, then it should not be limited to the
> MTU. The MTU is a transmit limitation, and software receiving this packet
> should be allowed to increase the size. Further more, current MTU check in
> __bpf_skb_max_len uses the MTU from ingress/current net_device, which in
> case of redirects uses the wrong net_device.
> 
> Keep a sanity max limit of IP6_MAX_MTU (under CONFIG_IPV6) which is 64KiB
> plus 40 bytes IPv6 header size. If compiled without IPv6 use IP_MAX_MTU.
> 
> V3: replace __bpf_skb_max_len() with define and use IPv6 max MTU size.
> 
> Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> ---
>   net/core/filter.c |   16 ++++++++--------
>   1 file changed, 8 insertions(+), 8 deletions(-)
> 
> diff --git a/net/core/filter.c b/net/core/filter.c
> index 05df73780dd3..ddc1f9ba89d1 100644
> --- a/net/core/filter.c
> +++ b/net/core/filter.c
> @@ -3474,11 +3474,11 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
>   	return 0;
>   }
>   
> -static u32 __bpf_skb_max_len(const struct sk_buff *skb)
> -{
> -	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
> -			  SKB_MAX_ALLOC;
> -}
> +#ifdef IP6_MAX_MTU /* Depend on CONFIG_IPV6 */
> +#define BPF_SKB_MAX_LEN IP6_MAX_MTU
> +#else
> +#define BPF_SKB_MAX_LEN IP_MAX_MTU
> +#endif

Shouldn't that check on skb->protocol? The way I understand it is that a number of devices
including virtual ones use ETH_MAX_MTU as their dev->max_mtu, so the mtu must be in the range
of dev->min_mtu(=ETH_MIN_MTU), dev->max_mtu(=ETH_MAX_MTU). __dev_set_mtu() then sets the user
value to dev->mtu in the core if within this range. That means in your case skb->dev->hard_header_len
for example is left out, meaning if we go for some constant, that would need to be higher.

>   BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
>   	   u32, mode, u64, flags)
> @@ -3527,7 +3527,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
>   {
>   	u32 len_cur, len_diff_abs = abs(len_diff);
>   	u32 len_min = bpf_skb_net_base_len(skb);
> -	u32 len_max = __bpf_skb_max_len(skb);
> +	u32 len_max = BPF_SKB_MAX_LEN;
>   	__be16 proto = skb->protocol;
>   	bool shrink = len_diff < 0;
>   	u32 off;
> @@ -3610,7 +3610,7 @@ static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
>   static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
>   					u64 flags)
>   {
> -	u32 max_len = __bpf_skb_max_len(skb);
> +	u32 max_len = BPF_SKB_MAX_LEN;
>   	u32 min_len = __bpf_skb_min_len(skb);
>   	int ret;
>   
> @@ -3686,7 +3686,7 @@ static const struct bpf_func_proto sk_skb_change_tail_proto = {
>   static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
>   					u64 flags)
>   {
> -	u32 max_len = __bpf_skb_max_len(skb);
> +	u32 max_len = BPF_SKB_MAX_LEN;
>   	u32 new_len = skb->len + head_room;
>   	int ret;
>   
> 
>
Maciej Żenczykowski Oct. 9, 2020, 6:26 p.m. UTC | #2
> > Multiple BPF-helpers that can manipulate/increase the size of the SKB uses
> > __bpf_skb_max_len() as the max-length. This function limit size against
> > the current net_device MTU (skb->dev->mtu).
> >
> > When a BPF-prog grow the packet size, then it should not be limited to the
> > MTU. The MTU is a transmit limitation, and software receiving this packet
> > should be allowed to increase the size. Further more, current MTU check in
> > __bpf_skb_max_len uses the MTU from ingress/current net_device, which in
> > case of redirects uses the wrong net_device.
> >
> > Keep a sanity max limit of IP6_MAX_MTU (under CONFIG_IPV6) which is 64KiB
> > plus 40 bytes IPv6 header size. If compiled without IPv6 use IP_MAX_MTU.
> >
> > V3: replace __bpf_skb_max_len() with define and use IPv6 max MTU size.
> >
> > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> > ---
> >   net/core/filter.c |   16 ++++++++--------
> >   1 file changed, 8 insertions(+), 8 deletions(-)
> >
> > diff --git a/net/core/filter.c b/net/core/filter.c
> > index 05df73780dd3..ddc1f9ba89d1 100644
> > --- a/net/core/filter.c
> > +++ b/net/core/filter.c
> > @@ -3474,11 +3474,11 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
> >       return 0;
> >   }
> >
> > -static u32 __bpf_skb_max_len(const struct sk_buff *skb)
> > -{
> > -     return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
> > -                       SKB_MAX_ALLOC;
> > -}
> > +#ifdef IP6_MAX_MTU /* Depend on CONFIG_IPV6 */
> > +#define BPF_SKB_MAX_LEN IP6_MAX_MTU
> > +#else
> > +#define BPF_SKB_MAX_LEN IP_MAX_MTU
> > +#endif
>
> Shouldn't that check on skb->protocol? The way I understand it is that a number of devices
> including virtual ones use ETH_MAX_MTU as their dev->max_mtu, so the mtu must be in the range
> of dev->min_mtu(=ETH_MIN_MTU), dev->max_mtu(=ETH_MAX_MTU). __dev_set_mtu() then sets the user
> value to dev->mtu in the core if within this range. That means in your case skb->dev->hard_header_len
> for example is left out, meaning if we go for some constant, that would need to be higher.

I think in the past skb->protocol was not guaranteed to be correct -
could be zero...
(with [misconfigured] raw sockets - maybe that's fixed now?)
Jesper Dangaard Brouer Oct. 10, 2020, 10:25 a.m. UTC | #3
On Fri, 9 Oct 2020 18:12:20 +0200
Daniel Borkmann <daniel@iogearbox.net> wrote:

> On 10/8/20 4:09 PM, Jesper Dangaard Brouer wrote:
> > Multiple BPF-helpers that can manipulate/increase the size of the SKB uses
> > __bpf_skb_max_len() as the max-length. This function limit size against
> > the current net_device MTU (skb->dev->mtu).
> > 
> > When a BPF-prog grow the packet size, then it should not be limited to the
> > MTU. The MTU is a transmit limitation, and software receiving this packet
> > should be allowed to increase the size. Further more, current MTU check in
> > __bpf_skb_max_len uses the MTU from ingress/current net_device, which in
> > case of redirects uses the wrong net_device.
> > 
> > Keep a sanity max limit of IP6_MAX_MTU (under CONFIG_IPV6) which is 64KiB
> > plus 40 bytes IPv6 header size. If compiled without IPv6 use IP_MAX_MTU.
> > 
> > V3: replace __bpf_skb_max_len() with define and use IPv6 max MTU size.
> > 
> > Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
> > ---
> >   net/core/filter.c |   16 ++++++++--------
> >   1 file changed, 8 insertions(+), 8 deletions(-)
> > 
> > diff --git a/net/core/filter.c b/net/core/filter.c
> > index 05df73780dd3..ddc1f9ba89d1 100644
> > --- a/net/core/filter.c
> > +++ b/net/core/filter.c
> > @@ -3474,11 +3474,11 @@ static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
> >   	return 0;
> >   }
> >   
> > -static u32 __bpf_skb_max_len(const struct sk_buff *skb)
> > -{
> > -	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
> > -			  SKB_MAX_ALLOC;
> > -}
> > +#ifdef IP6_MAX_MTU /* Depend on CONFIG_IPV6 */
> > +#define BPF_SKB_MAX_LEN IP6_MAX_MTU
> > +#else
> > +#define BPF_SKB_MAX_LEN IP_MAX_MTU
> > +#endif  
> 
> Shouldn't that check on skb->protocol? The way I understand it is
> that a number of devices including virtual ones use ETH_MAX_MTU as
> their dev->max_mtu, so the mtu must be in the range of
> dev->min_mtu(=ETH_MIN_MTU), dev->max_mtu(=ETH_MAX_MTU).
> __dev_set_mtu() then sets the user value to dev->mtu in the core if
> within this range. That means in your case skb->dev->hard_header_len
> for example is left out, meaning if we go for some constant, that
> would need to be higher.

Sorry, but I think you have missed the point.  This BPF_SKB_MAX_LEN is
just a sanity max limit.  We are removing the limit for BPF-progs to
change the size of the packet (regardless of MTU).

This will allow BPF-ingress to increase packet size (up-to this sanity
limit) and then BPF-egress can decrease packet size again, before
sending it to the actual dev.  It is up to the BPF-programmer that to
use this for, but I think this adds good flexibility, instead of being
limited to the *transmit* size (MTU) of the dev.  This is software why
have this MTU limit.
diff mbox series

Patch

diff --git a/net/core/filter.c b/net/core/filter.c
index 05df73780dd3..ddc1f9ba89d1 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3474,11 +3474,11 @@  static int bpf_skb_net_shrink(struct sk_buff *skb, u32 off, u32 len_diff,
 	return 0;
 }
 
-static u32 __bpf_skb_max_len(const struct sk_buff *skb)
-{
-	return skb->dev ? skb->dev->mtu + skb->dev->hard_header_len :
-			  SKB_MAX_ALLOC;
-}
+#ifdef IP6_MAX_MTU /* Depend on CONFIG_IPV6 */
+#define BPF_SKB_MAX_LEN IP6_MAX_MTU
+#else
+#define BPF_SKB_MAX_LEN IP_MAX_MTU
+#endif
 
 BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
@@ -3527,7 +3527,7 @@  BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 {
 	u32 len_cur, len_diff_abs = abs(len_diff);
 	u32 len_min = bpf_skb_net_base_len(skb);
-	u32 len_max = __bpf_skb_max_len(skb);
+	u32 len_max = BPF_SKB_MAX_LEN;
 	__be16 proto = skb->protocol;
 	bool shrink = len_diff < 0;
 	u32 off;
@@ -3610,7 +3610,7 @@  static int bpf_skb_trim_rcsum(struct sk_buff *skb, unsigned int new_len)
 static inline int __bpf_skb_change_tail(struct sk_buff *skb, u32 new_len,
 					u64 flags)
 {
-	u32 max_len = __bpf_skb_max_len(skb);
+	u32 max_len = BPF_SKB_MAX_LEN;
 	u32 min_len = __bpf_skb_min_len(skb);
 	int ret;
 
@@ -3686,7 +3686,7 @@  static const struct bpf_func_proto sk_skb_change_tail_proto = {
 static inline int __bpf_skb_change_head(struct sk_buff *skb, u32 head_room,
 					u64 flags)
 {
-	u32 max_len = __bpf_skb_max_len(skb);
+	u32 max_len = BPF_SKB_MAX_LEN;
 	u32 new_len = skb->len + head_room;
 	int ret;