One of our in-house projects, bpf-based NAT, hits a kernel BUG_ON at
function skb_segment(), line 3667. The bpf program attaches to
clsact ingress, calls bpf_skb_change_proto to change protocol
from ipv4 to ipv6 or from ipv6 to ipv4, and then calls bpf_redirect
to send the changed packet out.
3472 struct sk_buff *skb_segment(struct sk_buff *head_skb,
3473 netdev_features_t features)
3474 {
3475 struct sk_buff *segs = NULL;
3476 struct sk_buff *tail = NULL;
...
3665 while (pos < offset + len) {
3666 if (i >= nfrags) {
3667 BUG_ON(skb_headlen(list_skb));
3668
3669 i = 0;
3670 nfrags = skb_shinfo(list_skb)->nr_frags;
3671 frag = skb_shinfo(list_skb)->frags;
3672 frag_skb = list_skb;
...
call stack:
...
#1 [ffff883ffef03558] __crash_kexec at ffffffff8110c525
#2 [ffff883ffef03620] crash_kexec at ffffffff8110d5cc
#3 [ffff883ffef03640] oops_end at ffffffff8101d7e7
#4 [ffff883ffef03668] die at ffffffff8101deb2
#5 [ffff883ffef03698] do_trap at ffffffff8101a700
#6 [ffff883ffef036e8] do_error_trap at ffffffff8101abfe
#7 [ffff883ffef037a0] do_invalid_op at ffffffff8101acd0
#8 [ffff883ffef037b0] invalid_op at ffffffff81a00bab
[exception RIP: skb_segment+3044]
RIP: ffffffff817e4dd4 RSP: ffff883ffef03860 RFLAGS: 00010216
RAX: 0000000000002bf6 RBX: ffff883feb7aaa00 RCX: 0000000000000011
RDX: ffff883fb87910c0 RSI: 0000000000000011 RDI: ffff883feb7ab500
RBP: ffff883ffef03928 R8: 0000000000002ce2 R9: 00000000000027da
R10: 000001ea00000000 R11: 0000000000002d82 R12: ffff883f90a1ee80
R13: ffff883fb8791120 R14: ffff883feb7abc00 R15: 0000000000002ce2
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
#9 [ffff883ffef03930] tcp_gso_segment at ffffffff818713e7
--- <IRQ stack> ---
...
The triggering input skb has the following properties:
list_skb = skb->frag_list;
skb->nfrags != NULL && skb_headlen(list_skb) != 0
and skb_segment() is not able to handle a frag_list skb
if its headlen (list_skb->len - list_skb->data_len) is not 0.
This patch addressed the issue by handling skb_headlen(list_skb) != 0
case properly if list_skb->head_frag is true, which is expected in
most cases. The head frag is processed before list_skb->frags
are processed.
Reported-by: Diptanu Gon Choudhury <dipt...@fb.com>
Signed-off-by: Yonghong Song <y...@fb.com>
---
net/core/skbuff.c | 26 ++++++++++++++++++++------
1 file changed, 20 insertions(+), 6 deletions(-)
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 715c134..23b317a 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3460,6 +3460,19 @@ void *skb_pull_rcsum(struct sk_buff *skb, unsigned int
len)
}
EXPORT_SYMBOL_GPL(skb_pull_rcsum);
+static inline skb_frag_t skb_head_frag_to_page_desc(struct sk_buff *frag_skb)
+{
+ skb_frag_t head_frag;
+ struct page *page;
+
+ page = virt_to_head_page(frag_skb->head);
+ head_frag.page.p = page;
+ head_frag.page_offset = frag_skb->data -
+ (unsigned char *)page_address(page);
+ head_frag.size = skb_headlen(frag_skb);
+ return head_frag;
+}
+
/**
* skb_segment - Perform protocol segmentation on skb.
* @head_skb: buffer to segment
@@ -3664,15 +3677,16 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
while (pos < offset + len) {
if (i >= nfrags) {
- BUG_ON(skb_headlen(list_skb));
-
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
- frag_skb = list_skb;
-
- BUG_ON(!nfrags);
+ if (skb_headlen(list_skb)) {
+ BUG_ON(!list_skb->head_frag);
+ /* to make room for head_frag. */
+ i--; frag--;
+ }
+ frag_skb = list_skb;
if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
skb_zerocopy_clone(nskb, frag_skb,
GFP_ATOMIC))
@@ -3689,7 +3703,7 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb,
goto err;
}
- *nskb_frag = *frag;
+ *nskb_frag = (i < 0) ?
skb_head_frag_to_page_desc(frag_skb) : *frag;
__skb_frag_ref(nskb_frag);
size = skb_frag_size(nskb_frag);
--
2.9.5
