summaryrefslogtreecommitdiffstats
path: root/net/core
diff options
context:
space:
mode:
authorCong Wang <cong.wang@bytedance.com>2021-03-30 19:32:33 -0700
committerAlexei Starovoitov <ast@kernel.org>2021-04-01 10:56:14 -0700
commit2bc793e3272a13e337416c057cb81c5396ad91d1 (patch)
tree1a611b3ce3edf032e4f6a9430fa8c5cd719e1728 /net/core
parentd7f571188ecf25c244789b883c878ec7c64b5b08 (diff)
downloadlinux-2bc793e3272a13e337416c057cb81c5396ad91d1.tar.bz2
skmsg: Extract __tcp_bpf_recvmsg() and tcp_bpf_wait_data()
Although these two functions are only used by TCP, they are not specific to TCP at all, both operate on skmsg and ingress_msg, so fit in net/core/skmsg.c very well. And we will need them for non-TCP, so rename and move them to skmsg.c and export them to modules. Signed-off-by: Cong Wang <cong.wang@bytedance.com> Signed-off-by: Alexei Starovoitov <ast@kernel.org> Link: https://lore.kernel.org/bpf/20210331023237.41094-13-xiyou.wangcong@gmail.com
Diffstat (limited to 'net/core')
-rw-r--r--net/core/skmsg.c98
1 files changed, 98 insertions, 0 deletions
diff --git a/net/core/skmsg.c b/net/core/skmsg.c
index 9fc83f7cc1a0..92a83c02562a 100644
--- a/net/core/skmsg.c
+++ b/net/core/skmsg.c
@@ -399,6 +399,104 @@ out:
}
EXPORT_SYMBOL_GPL(sk_msg_memcopy_from_iter);
+int sk_msg_wait_data(struct sock *sk, struct sk_psock *psock, int flags,
+ long timeo, int *err)
+{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
+ int ret = 0;
+
+ if (sk->sk_shutdown & RCV_SHUTDOWN)
+ return 1;
+
+ if (!timeo)
+ return ret;
+
+ add_wait_queue(sk_sleep(sk), &wait);
+ sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ ret = sk_wait_event(sk, &timeo,
+ !list_empty(&psock->ingress_msg) ||
+ !skb_queue_empty(&sk->sk_receive_queue), &wait);
+ sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk);
+ remove_wait_queue(sk_sleep(sk), &wait);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(sk_msg_wait_data);
+
+/* Receive sk_msg from psock->ingress_msg to @msg. */
+int sk_msg_recvmsg(struct sock *sk, struct sk_psock *psock, struct msghdr *msg,
+ int len, int flags)
+{
+ struct iov_iter *iter = &msg->msg_iter;
+ int peek = flags & MSG_PEEK;
+ struct sk_msg *msg_rx;
+ int i, copied = 0;
+
+ msg_rx = sk_psock_peek_msg(psock);
+ while (copied != len) {
+ struct scatterlist *sge;
+
+ if (unlikely(!msg_rx))
+ break;
+
+ i = msg_rx->sg.start;
+ do {
+ struct page *page;
+ int copy;
+
+ sge = sk_msg_elem(msg_rx, i);
+ copy = sge->length;
+ page = sg_page(sge);
+ if (copied + copy > len)
+ copy = len - copied;
+ copy = copy_page_to_iter(page, sge->offset, copy, iter);
+ if (!copy)
+ return copied ? copied : -EFAULT;
+
+ copied += copy;
+ if (likely(!peek)) {
+ sge->offset += copy;
+ sge->length -= copy;
+ if (!msg_rx->skb)
+ sk_mem_uncharge(sk, copy);
+ msg_rx->sg.size -= copy;
+
+ if (!sge->length) {
+ sk_msg_iter_var_next(i);
+ if (!msg_rx->skb)
+ put_page(page);
+ }
+ } else {
+ /* Lets not optimize peek case if copy_page_to_iter
+ * didn't copy the entire length lets just break.
+ */
+ if (copy != sge->length)
+ return copied;
+ sk_msg_iter_var_next(i);
+ }
+
+ if (copied == len)
+ break;
+ } while (i != msg_rx->sg.end);
+
+ if (unlikely(peek)) {
+ msg_rx = sk_psock_next_msg(psock, msg_rx);
+ if (!msg_rx)
+ break;
+ continue;
+ }
+
+ msg_rx->sg.start = i;
+ if (!sge->length && msg_rx->sg.start == msg_rx->sg.end) {
+ msg_rx = sk_psock_dequeue_msg(psock);
+ kfree_sk_msg(msg_rx);
+ }
+ msg_rx = sk_psock_peek_msg(psock);
+ }
+
+ return copied;
+}
+EXPORT_SYMBOL_GPL(sk_msg_recvmsg);
+
static struct sk_msg *sk_psock_create_ingress_msg(struct sock *sk,
struct sk_buff *skb)
{