Since commit 8a29111c7 ("net: gro: allow to build full sized skb")
gro may build buffers with a frag_list. This can hurt forwarding
because most NICs can't offload such packets, they need to be
segmented in software. This patch splits buffers with a frag_list
at the frag_list pointer into buffers that can be TSO offloaded.
Signed-off-by: Steffen Klassert
---
Changes since v1:
- Use the assumption that all buffers in the chain excluding the last
containing the same amount of data.
- Simplify some checks against gso partial.
- Fix the generation of IP IDs.
Changes since v2:
- Merge common code of gso partial and frag_list pointer splitting.
Changes since v3:
- Fix the checks for doing frag_list pointer splitting.
Changes since v4:
- Whitespace fix.
- Fix size calculations of the tail packet.
net/core/skbuff.c | 51 +++---
net/ipv4/af_inet.c | 14 ++
net/ipv4/gre_offload.c | 6 --
net/ipv4/tcp_offload.c | 13 +++--
net/ipv4/udp_offload.c | 6 --
net/ipv6/ip6_offload.c | 5 -
6 files changed, 69 insertions(+), 26 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3864b4b6..51e761a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3078,11 +3078,31 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
sg = !!(features & NETIF_F_SG);
csum = !!can_checksum_protocol(features, proto);
- /* GSO partial only requires that we trim off any excess that
-* doesn't fit into an MSS sized block, so take care of that
-* now.
-*/
- if (sg && csum && (features & NETIF_F_GSO_PARTIAL)) {
+ if (sg && csum && (mss != GSO_BY_FRAGS)) {
+ if (!(features & NETIF_F_GSO_PARTIAL)) {
+ struct sk_buff *iter;
+
+ if (!list_skb ||
+ !net_gso_ok(features,
skb_shinfo(head_skb)->gso_type))
+ goto normal;
+
+ /* Split the buffer at the frag_list pointer.
+* This is based on the assumption that all
+* buffers in the chain excluding the last
+* containing the same amount of data.
+*/
+ skb_walk_frags(head_skb, iter) {
+ if (skb_headlen(iter))
+ goto normal;
+
+ len -= iter->len;
+ }
+ }
+
+ /* GSO partial only requires that we trim off any excess that
+* doesn't fit into an MSS sized block, so take care of that
+* now.
+*/
partial_segs = len / mss;
if (partial_segs > 1)
mss *= partial_segs;
@@ -3090,6 +3110,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
partial_segs = 0;
}
+normal:
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
@@ -3281,21 +3302,29 @@ perform_csum_check:
*/
segs->prev = tail;
- /* Update GSO info on first skb in partial sequence. */
if (partial_segs) {
+ struct sk_buff *iter;
int type = skb_shinfo(head_skb)->gso_type;
+ unsigned short gso_size = skb_shinfo(head_skb)->gso_size;
/* Update type to add partial and then remove dodgy if set */
- type |= SKB_GSO_PARTIAL;
+ type |= (features & NETIF_F_GSO_PARTIAL) / NETIF_F_GSO_PARTIAL
* SKB_GSO_PARTIAL;
type &= ~SKB_GSO_DODGY;
/* Update GSO info and prepare to start updating headers on
* our way back down the stack of protocols.
*/
- skb_shinfo(segs)->gso_size = skb_shinfo(head_skb)->gso_size;
- skb_shinfo(segs)->gso_segs = partial_segs;
- skb_shinfo(segs)->gso_type = type;
- SKB_GSO_CB(segs)->data_offset = skb_headroom(segs) + doffset;
+ for (iter = segs; iter; iter = iter->next) {
+ skb_shinfo(iter)->gso_size = gso_size;
+ skb_shinfo(iter)->gso_segs = partial_segs;
+ skb_shinfo(iter)->gso_type = type;
+ SKB_GSO_CB(iter)->data_offset = skb_headroom(iter) +
doffset;
+ }
+
+ if (tail->len <= gso_size)
+ skb_shinfo(tail)->gso_size = 0;
+ else if (tail != segs)
+ skb_shinfo(tail)->gso_segs = DIV_ROUND_UP(tail->len -
doffset, gso_size);
}
/* Following permits correct backpressure, for protocols
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e94b47b..1effc98 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1192,7 +1192,7 @@ EXPORT_SYMBOL(inet_sk_rebuild
