diff options
Diffstat (limited to 'net/ceph/messenger_v1.c')
-rw-r--r-- | net/ceph/messenger_v1.c | 58 |
1 files changed, 37 insertions, 21 deletions
diff --git a/net/ceph/messenger_v1.c b/net/ceph/messenger_v1.c index 814579f27f04..3d57bb48a2b4 100644 --- a/net/ceph/messenger_v1.c +++ b/net/ceph/messenger_v1.c @@ -74,6 +74,39 @@ static int ceph_tcp_sendmsg(struct socket *sock, struct kvec *iov, return r; } +/* + * @more: MSG_MORE or 0. + */ +static int ceph_tcp_sendpage(struct socket *sock, struct page *page, + int offset, size_t size, int more) +{ + struct msghdr msg = { + .msg_flags = MSG_DONTWAIT | MSG_NOSIGNAL | more, + }; + struct bio_vec bvec; + int ret; + + /* + * MSG_SPLICE_PAGES cannot properly handle pages with page_count == 0, + * we need to fall back to sendmsg if that's the case. + * + * Same goes for slab pages: skb_can_coalesce() allows + * coalescing neighboring slab objects into a single frag which + * triggers one of hardened usercopy checks. + */ + if (sendpage_ok(page)) + msg.msg_flags |= MSG_SPLICE_PAGES; + + bvec_set_page(&bvec, page, size, offset); + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); + + ret = sock_sendmsg(sock, &msg); + if (ret == -EAGAIN) + ret = 0; + + return ret; +} + static void con_out_kvec_reset(struct ceph_connection *con) { BUG_ON(con->v1.out_skip); @@ -450,10 +483,6 @@ static int write_partial_message_data(struct ceph_connection *con) */ crc = do_datacrc ? le32_to_cpu(msg->footer.data_crc) : 0; while (cursor->total_resid) { - struct bio_vec bvec; - struct msghdr msghdr = { - .msg_flags = MSG_SPLICE_PAGES, - }; struct page *page; size_t page_offset; size_t length; @@ -465,13 +494,8 @@ static int write_partial_message_data(struct ceph_connection *con) } page = ceph_msg_data_next(cursor, &page_offset, &length); - if (length != cursor->total_resid) - msghdr.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, length, page_offset); - iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, length); - - ret = sock_sendmsg(con->sock, &msghdr); + ret = ceph_tcp_sendpage(con->sock, page, page_offset, length, + MSG_MORE); if (ret <= 0) { if (do_datacrc) msg->footer.data_crc = cpu_to_le32(crc); @@ -501,22 +525,14 @@ static int write_partial_message_data(struct ceph_connection *con) */ static int write_partial_skip(struct ceph_connection *con) { - struct bio_vec bvec; - struct msghdr msghdr = { - .msg_flags = MSG_SPLICE_PAGES | MSG_MORE, - }; int ret; dout("%s %p %d left\n", __func__, con, con->v1.out_skip); while (con->v1.out_skip > 0) { size_t size = min(con->v1.out_skip, (int)PAGE_SIZE); - if (size == con->v1.out_skip) - msghdr.msg_flags &= ~MSG_MORE; - bvec_set_page(&bvec, ZERO_PAGE(0), size, 0); - iov_iter_bvec(&msghdr.msg_iter, ITER_SOURCE, &bvec, 1, size); - - ret = sock_sendmsg(con->sock, &msghdr); + ret = ceph_tcp_sendpage(con->sock, ceph_zero_page, 0, size, + MSG_MORE); if (ret <= 0) goto out; con->v1.out_skip -= ret; |