netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
To: netdev@vger.kernel.org
Cc: ast@kernel.org, daniel@iogearbox.net, sdf@google.com,
	posk@google.com, Willem de Bruijn <willemb@google.com>
Subject: [PATCH bpf-next 09/13] bpf: add bpf_skb_adjust_room encap flags
Date: Wed, 20 Mar 2019 10:49:40 -0400	[thread overview]
Message-ID: <20190320144944.147862-10-willemdebruijn.kernel@gmail.com> (raw)
In-Reply-To: <20190320144944.147862-1-willemdebruijn.kernel@gmail.com>

From: Willem de Bruijn <willemb@google.com>

When pushing tunnel headers, annotate skbs in the same way as tunnel
devices.

For GSO packets, the network stack requires certain fields set to
segment packets with tunnel headers. gro_gse_segment depends on
transport and inner mac header, for instance.

Add an option to pass this information.

Remove the restriction on len_diff to network header length, which
is too short, e.g., for GRE protocols.

Signed-off-by: Willem de Bruijn <willemb@google.com>
---
 include/uapi/linux/bpf.h | 14 +++++++++-
 net/core/filter.c        | 58 +++++++++++++++++++++++++++++++++++++---
 2 files changed, 67 insertions(+), 5 deletions(-)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0eda8f564a381..a444534cc88d7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -2595,7 +2595,19 @@ enum bpf_func_id {
 
 /* BPF_FUNC_skb_adjust_room flags. */
 #define BPF_F_ADJ_ROOM_FIXED_GSO	(1ULL << 0)
-#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO)
+
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV4	(1ULL << 1)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_IPV6	(1ULL << 2)
+#define BPF_F_ADJ_ROOM_ENCAP_L3_MASK	(BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 | \
+					 BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+
+#define BPF_F_ADJ_ROOM_ENCAP_L4_GRE	(1ULL << 3)
+#define BPF_F_ADJ_ROOM_ENCAP_L4_UDP	(1ULL << 4)
+
+#define BPF_F_ADJ_ROOM_MASK		(BPF_F_ADJ_ROOM_FIXED_GSO | \
+					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \
+					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \
+					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
 
 /* Mode for BPF_FUNC_skb_adjust_room helper. */
 enum bpf_adj_room_mode {
diff --git a/net/core/filter.c b/net/core/filter.c
index e346e48098000..6007b0b4bc0d7 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2966,6 +2966,9 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			    u64 flags)
 {
+	bool encap = flags & BPF_F_ADJ_ROOM_ENCAP_L3_MASK;
+	unsigned int gso_type = SKB_GSO_DODGY;
+	u16 mac_len, inner_net, inner_trans;
 	int ret;
 
 	if (skb_is_gso(skb) && !skb_is_gso_tcp(skb)) {
@@ -2979,10 +2982,60 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (encap) {
+		if (skb->protocol != htons(ETH_P_IP) &&
+		    skb->protocol != htons(ETH_P_IPV6))
+			return -ENOTSUPP;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV4 &&
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			return -EINVAL;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE &&
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+			return -EINVAL;
+
+		if (skb->encapsulation)
+			return -EALREADY;
+
+		mac_len = skb->network_header - skb->mac_header;
+		inner_net = skb->network_header;
+		inner_trans = skb->transport_header;
+	}
+
 	ret = bpf_skb_net_hdr_push(skb, off, len_diff);
 	if (unlikely(ret < 0))
 		return ret;
 
+	if (encap) {
+		/* inner mac == inner_net on l3 encap */
+		skb->inner_mac_header = inner_net;
+		skb->inner_network_header = inner_net;
+		skb->inner_transport_header = inner_trans;
+		skb_set_inner_protocol(skb, skb->protocol);
+
+		skb->encapsulation = 1;
+		skb_set_network_header(skb, mac_len);
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)
+			gso_type |= SKB_GSO_UDP_TUNNEL;
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE)
+			gso_type |= SKB_GSO_GRE;
+		else if (flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6)
+			gso_type |= SKB_GSO_IPXIP6;
+		else
+			gso_type |= SKB_GSO_IPXIP4;
+
+		if (flags & BPF_F_ADJ_ROOM_ENCAP_L4_GRE ||
+		    flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP) {
+			int nh_len = flags & BPF_F_ADJ_ROOM_ENCAP_L3_IPV6 ?
+					sizeof(struct ipv6hdr) :
+					sizeof(struct iphdr);
+
+			skb_set_transport_header(skb, mac_len + nh_len);
+		}
+	}
+
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
@@ -2991,7 +3044,7 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			skb_decrease_gso_size(shinfo, len_diff);
 
 		/* Header must be checked, and gso_segs recomputed. */
-		shinfo->gso_type |= SKB_GSO_DODGY;
+		shinfo->gso_type |= gso_type;
 		shinfo->gso_segs = 0;
 	}
 
@@ -3042,7 +3095,6 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb)
 BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	   u32, mode, u64, flags)
 {
-	bool trans_same = skb->transport_header == skb->network_header;
 	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);
@@ -3071,8 +3123,6 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 	}
 
 	len_cur = skb->len - skb_network_offset(skb);
-	if (skb_transport_header_was_set(skb) && !trans_same)
-		len_cur = skb_network_header_len(skb);
 	if ((shrink && (len_diff_abs >= len_cur ||
 			len_cur - len_diff_abs < len_min)) ||
 	    (!shrink && (skb->len + len_diff_abs > len_max &&
-- 
2.21.0.225.g810b269d1ac-goog


  parent reply	other threads:[~2019-03-20 14:50 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-20 14:49 [PATCH bpf-next 00/13] bpf tc tunneling Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 01/13] bpf: in bpf_skb_adjust_room avoid copy in tx fast path Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 02/13] selftests/bpf: bpf tunnel encap test Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 03/13] selftests/bpf: expand bpf tunnel test with decap Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 04/13] selftests/bpf: expand bpf tunnel test to ipv6 Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 05/13] selftests/bpf: extend bpf tunnel test with gre Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 06/13] selftests/bpf: extend bpf tunnel test with tso Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 07/13] bpf: add bpf_skb_adjust_room mode BPF_ADJ_ROOM_MAC Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 08/13] bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_FIXED_GSO Willem de Bruijn
2019-03-21 13:42   ` Alan Maguire
2019-03-21 14:00     ` Willem de Bruijn
2019-03-20 14:49 ` Willem de Bruijn [this message]
2019-03-20 15:51   ` [PATCH bpf-next 09/13] bpf: add bpf_skb_adjust_room encap flags Alan Maguire
2019-03-20 18:10     ` Willem de Bruijn
2019-03-21  3:13   ` Alexei Starovoitov
2019-03-21 13:25     ` Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 10/13] bpf: Sync bpf.h to tools Willem de Bruijn
2019-03-20 14:56   ` Soheil Hassas Yeganeh
2019-03-20 14:49 ` [PATCH bpf-next 11/13] selftests/bpf: convert bpf tunnel test to BPF_ADJ_ROOM_MAC Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 12/13] selftests/bpf: convert bpf tunnel test to BPF_F_ADJ_ROOM_FIXED_GSO Willem de Bruijn
2019-03-20 14:49 ` [PATCH bpf-next 13/13] selftests/bpf: convert bpf tunnel test to encap modes Willem de Bruijn

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190320144944.147862-10-willemdebruijn.kernel@gmail.com \
    --to=willemdebruijn.kernel@gmail.com \
    --cc=ast@kernel.org \
    --cc=daniel@iogearbox.net \
    --cc=netdev@vger.kernel.org \
    --cc=posk@google.com \
    --cc=sdf@google.com \
    --cc=willemb@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).