From: John Fastabend john.fastabend@gmail.com
[ Upstream commit 36cd0e696a832a00247fca522034703566ac8885 ]
Fix sockmap sk_skb programs so that they observe sk_rcvbuf limits. This allows users to tune SO_RCVBUF and sockmap will honor them.
We can refactor the if(charge) case out in later patches. But, keep this fix to the point.
Fixes: 51199405f9672 ("bpf: skb_verdict, support SK_PASS on RX BPF path") Suggested-by: Jakub Sitnicki jakub@cloudflare.com Signed-off-by: John Fastabend john.fastabend@gmail.com Signed-off-by: Daniel Borkmann daniel@iogearbox.net Reviewed-by: Jakub Sitnicki jakub@cloudflare.com Link: https://lore.kernel.org/bpf/160556568657.73229.8404601585878439060.stgit@joh... Signed-off-by: Sasha Levin sashal@kernel.org --- net/core/skmsg.c | 20 ++++++++++++++++---- net/ipv4/tcp_bpf.c | 3 ++- 2 files changed, 18 insertions(+), 5 deletions(-)
diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 30ddca6db6c6b..f41b06e60ad90 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -170,10 +170,12 @@ static int sk_msg_free_elem(struct sock *sk, struct sk_msg *msg, u32 i, struct scatterlist *sge = sk_msg_elem(msg, i); u32 len = sge->length;
- if (charge) - sk_mem_uncharge(sk, len); - if (!msg->skb) + /* When the skb owns the memory we free it from consume_skb path. */ + if (!msg->skb) { + if (charge) + sk_mem_uncharge(sk, len); put_page(sg_page(sge)); + } memset(sge, 0, sizeof(*sge)); return len; } @@ -403,6 +405,9 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) int copied = 0, num_sge; struct sk_msg *msg;
+ if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) + return -EAGAIN; + msg = kzalloc(sizeof(*msg), __GFP_NOWARN | GFP_ATOMIC); if (unlikely(!msg)) return -EAGAIN; @@ -418,7 +423,14 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) return num_sge; }
- sk_mem_charge(sk, skb->len); + /* This will transition ownership of the data from the socket where + * the BPF program was run initiating the redirect to the socket + * we will eventually receive this data on. The data will be released + * from skb_consume found in __tcp_bpf_recvmsg() after its been copied + * into user buffers. + */ + skb_set_owner_r(skb, sk); + copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index d85ba32dc6e7a..24e1be45d4cd7 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -45,7 +45,8 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, if (likely(!peek)) { sge->offset += copy; sge->length -= copy; - sk_mem_uncharge(sk, copy); + if (!msg_rx->skb) + sk_mem_uncharge(sk, copy); msg_rx->sg.size -= copy;
if (!sge->length) {