5.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Mohamed Khalfella <mkhalfella@xxxxxxxxxxxxxxx>
commit 2ea35288c83b3d501a88bc17f2df8f176b5cc96f upstream.
Commit bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions
once per nskb") added the call to zero copy functions in skb_segment().
The change introduced a bug in skb_segment() because skb_orphan_frags()
may possibly change the number of fragments or allocate new fragments
altogether leaving nrfrags and frag to point to the old values. This can
cause a panic with stacktrace like the one below.
[ 193.894380] BUG: kernel NULL pointer dereference, address: 00000000000000bc
[ 193.895273] CPU: 13 PID: 18164 Comm: vh-net-17428 Kdump: loaded Tainted: G O 5.15.123+ #26
[ 193.903919] RIP: 0010:skb_segment+0xb0e/0x12f0
[ 194.021892] Call Trace:
[ 194.027422] <TASK>
[ 194.072861] tcp_gso_segment+0x107/0x540
[ 194.082031] inet_gso_segment+0x15c/0x3d0
[ 194.090783] skb_mac_gso_segment+0x9f/0x110
[ 194.095016] __skb_gso_segment+0xc1/0x190
[ 194.103131] netem_enqueue+0x290/0xb10 [sch_netem]
[ 194.107071] dev_qdisc_enqueue+0x16/0x70
[ 194.110884] __dev_queue_xmit+0x63b/0xb30
[ 194.121670] bond_start_xmit+0x159/0x380 [bonding]
[ 194.128506] dev_hard_start_xmit+0xc3/0x1e0
[ 194.131787] __dev_queue_xmit+0x8a0/0xb30
[ 194.138225] macvlan_start_xmit+0x4f/0x100 [macvlan]
[ 194.141477] dev_hard_start_xmit+0xc3/0x1e0
[ 194.144622] sch_direct_xmit+0xe3/0x280
[ 194.147748] __dev_queue_xmit+0x54a/0xb30
[ 194.154131] tap_get_user+0x2a8/0x9c0 [tap]
[ 194.157358] tap_sendmsg+0x52/0x8e0 [tap]
[ 194.167049] handle_tx_zerocopy+0x14e/0x4c0 [vhost_net]
[ 194.173631] handle_tx+0xcd/0xe0 [vhost_net]
[ 194.176959] vhost_worker+0x76/0xb0 [vhost]
[ 194.183667] kthread+0x118/0x140
[ 194.190358] ret_from_fork+0x1f/0x30
[ 194.193670] </TASK>
In this case calling skb_orphan_frags() updated nr_frags leaving nrfrags
local variable in skb_segment() stale. This resulted in the code hitting
i >= nrfrags prematurely and trying to move to next frag_skb using
list_skb pointer, which was NULL, and caused kernel panic. Move the call
to zero copy functions before using frags and nr_frags.
Fixes: bf5c25d60861 ("skbuff: in skb_segment, call zerocopy functions once per nskb")
Signed-off-by: Mohamed Khalfella <mkhalfella@xxxxxxxxxxxxxxx>
Reported-by: Amit Goyal <agoyal@xxxxxxxxxxxxxxx>
Cc: stable@xxxxxxxxxxxxxxx
Reviewed-by: Eric Dumazet <edumazet@xxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
net/core/skbuff.c | 34 ++++++++++++++++++++--------------
1 file changed, 20 insertions(+), 14 deletions(-)
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3686,21 +3686,20 @@ struct sk_buff *skb_segment(struct sk_bu
struct sk_buff *segs = NULL;
struct sk_buff *tail = NULL;
struct sk_buff *list_skb = skb_shinfo(head_skb)->frag_list;
- skb_frag_t *frag = skb_shinfo(head_skb)->frags;
unsigned int mss = skb_shinfo(head_skb)->gso_size;
unsigned int doffset = head_skb->data - skb_mac_header(head_skb);
- struct sk_buff *frag_skb = head_skb;
unsigned int offset = doffset;
unsigned int tnl_hlen = skb_tnl_header_len(head_skb);
unsigned int partial_segs = 0;
unsigned int headroom;
unsigned int len = head_skb->len;
+ struct sk_buff *frag_skb;
+ skb_frag_t *frag;
__be16 proto;
bool csum, sg;
- int nfrags = skb_shinfo(head_skb)->nr_frags;
int err = -ENOMEM;
int i = 0;
- int pos;
+ int nfrags, pos;
int dummy;
if ((skb_shinfo(head_skb)->gso_type & SKB_GSO_DODGY) &&
@@ -3778,6 +3777,13 @@ normal:
headroom = skb_headroom(head_skb);
pos = skb_headlen(head_skb);
+ if (skb_orphan_frags(head_skb, GFP_ATOMIC))
+ return ERR_PTR(-ENOMEM);
+
+ nfrags = skb_shinfo(head_skb)->nr_frags;
+ frag = skb_shinfo(head_skb)->frags;
+ frag_skb = head_skb;
+
do {
struct sk_buff *nskb;
skb_frag_t *nskb_frag;
@@ -3802,6 +3808,10 @@ normal:
(skb_headlen(list_skb) == len || sg)) {
BUG_ON(skb_headlen(list_skb) > len);
+ nskb = skb_clone(list_skb, GFP_ATOMIC);
+ if (unlikely(!nskb))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3820,12 +3830,8 @@ normal:
frag++;
}
- nskb = skb_clone(list_skb, GFP_ATOMIC);
list_skb = list_skb->next;
- if (unlikely(!nskb))
- goto err;
-
if (unlikely(pskb_trim(nskb, len))) {
kfree_skb(nskb);
goto err;
@@ -3890,12 +3896,16 @@ normal:
skb_shinfo(nskb)->tx_flags |= skb_shinfo(head_skb)->tx_flags &
SKBTX_SHARED_FRAG;
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
+ if (skb_zerocopy_clone(nskb, frag_skb, GFP_ATOMIC))
goto err;
while (pos < offset + len) {
if (i >= nfrags) {
+ if (skb_orphan_frags(list_skb, GFP_ATOMIC) ||
+ skb_zerocopy_clone(nskb, list_skb,
+ GFP_ATOMIC))
+ goto err;
+
i = 0;
nfrags = skb_shinfo(list_skb)->nr_frags;
frag = skb_shinfo(list_skb)->frags;
@@ -3909,10 +3919,6 @@ normal:
i--;
frag--;
}
- if (skb_orphan_frags(frag_skb, GFP_ATOMIC) ||
- skb_zerocopy_clone(nskb, frag_skb,
- GFP_ATOMIC))
- goto err;
list_skb = list_skb->next;
}
