| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20210915140629.18558-1-liujian56@huawei.com>
Date: Wed, 15 Sep 2021 22:06:29 +0800
From: Liu Jian <liujian56@...wei.com>
To: <john.fastabend@...il.com>, <daniel@...earbox.net>,
<jakub@...udflare.com>, <lmb@...udflare.com>,
<davem@...emloft.net>, <kuba@...nel.org>, <netdev@...r.kernel.org>,
<bpf@...r.kernel.org>
CC: <liujian56@...wei.com>
Subject: [PATCH] skmsg: lose offset info in sk_psock_skb_ingress
If sockmap enable strparser, there are lose offset info in
sk_psock_skb_ingress. If the length determined by parse_msg function
is not skb->len, the skb will be converted to sk_msg multiple times,
and userspace app will get the data multiple times.
Fix this by get the offset and length from strp_msg.
Signed-off-by: Liu Jian <liujian56@...wei.com>
---
net/core/skmsg.c | 49 ++++++++++++++++++++++++++++++++++++++----------
1 file changed, 39 insertions(+), 10 deletions(-)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 2d6249b28928..83f76e568fad 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -9,6 +9,8 @@
#include <net/tcp.h>
#include <net/tls.h>
+static void sk_psock_strp_data_ready(struct sock *sk);
+
static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce)
{
if (msg->sg.end > msg->sg.start &&
@@ -494,6 +496,7 @@ static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
}
static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
+ u32 off, u32 len,
struct sk_psock *psock,
struct sock *sk,
struct sk_msg *msg)
@@ -507,11 +510,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
*/
if (skb_linearize(skb))
return -EAGAIN;
- num_sge = skb_to_sgvec(skb, msg->sg.data, 0, skb->len);
+ num_sge = skb_to_sgvec(skb, msg->sg.data, off, len);
if (unlikely(num_sge < 0))
return num_sge;
- copied = skb->len;
+ copied = len;
msg->sg.start = 0;
msg->sg.size = copied;
msg->sg.end = num_sge;
@@ -522,9 +525,11 @@ static int sk_psock_skb_ingress_enqueue(struct sk_buff *skb,
return copied;
}
-static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb);
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
+ u32 off, u32 len);
-static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
+static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb,
+ u32 off, u32 len)
{
struct sock *sk = psock->sk;
struct sk_msg *msg;
@@ -535,7 +540,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
* correctly.
*/
if (unlikely(skb->sk == sk))
- return sk_psock_skb_ingress_self(psock, skb);
+ return sk_psock_skb_ingress_self(psock, skb, off, len);
msg = sk_psock_create_ingress_msg(sk, skb);
if (!msg)
return -EAGAIN;
@@ -547,7 +552,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
* into user buffers.
*/
skb_set_owner_r(skb, sk);
- err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
if (err < 0)
kfree(msg);
return err;
@@ -557,7 +562,8 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb)
* skb. In this case we do not need to check memory limits or skb_set_owner_r
* because the skb is already accounted for here.
*/
-static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb)
+static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb,
+ u32 off, u32 len)
{
struct sk_msg *msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC);
struct sock *sk = psock->sk;
@@ -567,7 +573,7 @@ static int sk_psock_skb_ingress_self(struct sk_psock *psock, struct sk_buff *skb
return -EAGAIN;
sk_msg_init(msg);
skb_set_owner_r(skb, sk);
- err = sk_psock_skb_ingress_enqueue(skb, psock, sk, msg);
+ err = sk_psock_skb_ingress_enqueue(skb, off, len, psock, sk, msg);
if (err < 0)
kfree(msg);
return err;
@@ -581,7 +587,7 @@ static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb,
return -EAGAIN;
return skb_send_sock(psock->sk, skb, off, len);
}
- return sk_psock_skb_ingress(psock, skb);
+ return sk_psock_skb_ingress(psock, skb, off, len);
}
static void sk_psock_skb_state(struct sk_psock *psock,
@@ -604,6 +610,9 @@ static void sk_psock_backlog(struct work_struct *work)
{
struct sk_psock *psock = container_of(work, struct sk_psock, work);
struct sk_psock_work_state *state = &psock->work_state;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ struct strp_msg *stm = NULL;
+#endif
struct sk_buff *skb = NULL;
bool ingress;
u32 len, off;
@@ -624,6 +633,13 @@ static void sk_psock_backlog(struct work_struct *work)
while ((skb = skb_dequeue(&psock->ingress_skb))) {
len = skb->len;
off = 0;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ if (psock->sk->sk_data_ready == sk_psock_strp_data_ready) {
+ stm = strp_msg(skb);
+ off = stm->offset;
+ len = stm->full_len;
+ }
+#endif
start:
ingress = skb_bpf_ingress(skb);
skb_bpf_redirect_clear(skb);
@@ -930,6 +946,10 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
{
struct sock *sk_other;
int err = 0;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ struct strp_msg *stm = NULL;
+ u32 len, off;
+#endif
switch (verdict) {
case __SK_PASS:
@@ -949,7 +969,16 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb,
* retrying later from workqueue.
*/
if (skb_queue_empty(&psock->ingress_skb)) {
- err = sk_psock_skb_ingress_self(psock, skb);
+ len = skb->len;
+ off = 0;
+#if IS_ENABLED(CONFIG_BPF_STREAM_PARSER)
+ if (psock->sk->sk_data_ready == sk_psock_strp_data_ready) {
+ stm = strp_msg(skb);
+ off = stm->offset;
+ len = stm->full_len;
+ }
+#endif
+ err = sk_psock_skb_ingress_self(psock, skb, off, len);
}
if (err < 0) {
spin_lock_bh(&psock->ingress_lock);
--
2.17.1
Powered by blists - more mailing lists