From: Liu Jian liujian56@huawei.com
[ Upstream commit 7303524e04af49a47991e19f895c3b8cdc3796c7 ]
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. And as Cong suggested, add one bit in skb->_sk_redir to distinguish enable or disable strparser.
Fixes: 604326b41a6fb ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian liujian56@huawei.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Cong Wang cong.wang@bytedance.com Acked-by: John Fastabend john.fastabend@gmail.com Link: https://lore.kernel.org/bpf/20211029141216.211899-1-liujian56@huawei.com Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/skmsg.h | 18 ++++++++++++++++-- net/core/skmsg.c | 43 +++++++++++++++++++++++++++++++++---------- 2 files changed, 49 insertions(+), 12 deletions(-)
diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1ce9a9eb223b6..b4256847c7079 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -509,8 +509,22 @@ static inline bool sk_psock_strp_enabled(struct sk_psock *psock)
#if IS_ENABLED(CONFIG_NET_SOCK_MSG)
-/* We only have one bit so far. */ -#define BPF_F_PTR_MASK ~(BPF_F_INGRESS) +#define BPF_F_STRPARSER (1UL << 1) + +/* We only have two bits so far. */ +#define BPF_F_PTR_MASK ~(BPF_F_INGRESS | BPF_F_STRPARSER) + +static inline bool skb_bpf_strparser(const struct sk_buff *skb) +{ + unsigned long sk_redir = skb->_sk_redir; + + return sk_redir & BPF_F_STRPARSER; +} + +static inline void skb_bpf_set_strparser(struct sk_buff *skb) +{ + skb->_sk_redir |= BPF_F_STRPARSER; +}
static inline bool skb_bpf_ingress(const struct sk_buff *skb) { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index a86ef7e844f8c..1ae52ac943f62 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -508,6 +508,7 @@ 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) @@ -521,11 +522,11 @@ 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; @@ -536,9 +537,11 @@ 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; @@ -549,7 +552,7 @@ 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; @@ -561,7 +564,7 @@ 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; @@ -571,7 +574,8 @@ 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; @@ -581,7 +585,7 @@ 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; @@ -595,7 +599,7 @@ 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, @@ -638,6 +642,12 @@ static void sk_psock_backlog(struct work_struct *work) while ((skb = skb_dequeue(&psock->ingress_skb))) { len = skb->len; off = 0; + if (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } start: ingress = skb_bpf_ingress(skb); skb_bpf_redirect_clear(skb); @@ -877,6 +887,7 @@ static int sk_psock_skb_redirect(struct sk_psock *from, struct sk_buff *skb) * return code, but then didn't set a redirect interface. */ if (unlikely(!sk_other)) { + skb_bpf_redirect_clear(skb); sock_drop(from->sk, skb); return -EIO; } @@ -944,6 +955,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, { struct sock *sk_other; int err = 0; + u32 len, off;
switch (verdict) { case __SK_PASS: @@ -951,6 +963,7 @@ static int sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, sk_other = psock->sk; if (sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { + skb_bpf_redirect_clear(skb); goto out_free; }
@@ -963,7 +976,15 @@ 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 (skb_bpf_strparser(skb)) { + struct strp_msg *stm = strp_msg(skb); + + off = stm->offset; + len = stm->full_len; + } + err = sk_psock_skb_ingress_self(psock, skb, off, len); } if (err < 0) { spin_lock_bh(&psock->ingress_lock); @@ -1029,6 +1050,8 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) skb_dst_drop(skb); skb_bpf_redirect_clear(skb); ret = bpf_prog_run_pin_on_cpu(prog, skb); + if (ret == SK_PASS) + skb_bpf_set_strparser(skb); ret = sk_psock_map_verd(ret, skb_bpf_redirect_fetch(skb)); skb->sk = NULL; }