diff options
author | David Howells <dhowells@redhat.com> | 2023-06-27 14:49:48 +0100 |
---|---|---|
committer | Jakub Kicinski <kuba@kernel.org> | 2023-06-27 09:32:40 -0700 |
commit | 5da4d7b8e6dfd5bd7d61f7fe1338b1e5d5b4f76c (patch) | |
tree | 801376fb6d1cf15d76806968cf02ed946ff16b11 /net/ceph/messenger_v2.c | |
parent | 528a08bcd820d07887edeae706df88ceb06db109 (diff) |
libceph: Partially revert changes to support MSG_SPLICE_PAGES
Fix the mishandling of MSG_DONTWAIT and also reinstates the per-page
checking of the source pages (which might have come from a DIO write by
userspace) by partially reverting the changes to support MSG_SPLICE_PAGES
and doing things a little differently. In messenger_v1:
(1) The ceph_tcp_sendpage() is resurrected and the callers reverted to use
that.
(2) The callers now pass MSG_MORE unconditionally. Previously, they were
passing in MSG_MORE|MSG_SENDPAGE_NOTLAST and then degrading that to
just MSG_MORE on the last call to ->sendpage().
(3) Make ceph_tcp_sendpage() a wrapper around sendmsg() rather than
sendpage(), setting MSG_SPLICE_PAGES if sendpage_ok() returns true on
the page.
In messenger_v2:
(4) Bring back do_try_sendpage() and make the callers use that.
(5) Make do_try_sendpage() use sendmsg() for both cases and set
MSG_SPLICE_PAGES if sendpage_ok() is set.
Fixes: 40a8c17aa770 ("ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage")
Fixes: fa094ccae1e7 ("ceph: Use sendmsg(MSG_SPLICE_PAGES) rather than sendpage()")
Reported-by: Ilya Dryomov <idryomov@gmail.com>
Link: https://lore.kernel.org/r/CAOi1vP9vjLfk3W+AJFeexC93jqPaPUn2dD_4NrzxwoZTbYfOnw@mail.gmail.com/
Link: https://lore.kernel.org/r/CAOi1vP_Bn918j24S94MuGyn+Gxk212btw7yWeDrRcW1U8pc_BA@mail.gmail.com/
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Xiubo Li <xiubli@redhat.com>
cc: Jeff Layton <jlayton@kernel.org>
cc: Jens Axboe <axboe@kernel.dk>
cc: Matthew Wilcox <willy@infradead.org>
Link: https://lore.kernel.org/r/3101881.1687801973@warthog.procyon.org.uk/ # v1
Link: https://lore.kernel.org/r/3111635.1687813501@warthog.procyon.org.uk/ # v2
Reviewed-by: Ilya Dryomov <idryomov@gmail.com>
Link: https://lore.kernel.org/r/3199652.1687873788@warthog.procyon.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ceph/messenger_v2.c')
-rw-r--r-- | net/ceph/messenger_v2.c | 88 |
1 files changed, 70 insertions, 18 deletions
diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 87ac97073e75..1a888b86a494 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -117,38 +117,90 @@ static int ceph_tcp_recv(struct ceph_connection *con) return ret; } +static int do_sendmsg(struct socket *sock, struct iov_iter *it) +{ + struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS }; + int ret; + + msg.msg_iter = *it; + while (iov_iter_count(it)) { + ret = sock_sendmsg(sock, &msg); + if (ret <= 0) { + if (ret == -EAGAIN) + ret = 0; + return ret; + } + + iov_iter_advance(it, ret); + } + + WARN_ON(msg_data_left(&msg)); + return 1; +} + +static int do_try_sendpage(struct socket *sock, struct iov_iter *it) +{ + struct msghdr msg = { .msg_flags = CEPH_MSG_FLAGS }; + struct bio_vec bv; + int ret; + + if (WARN_ON(!iov_iter_is_bvec(it))) + return -EINVAL; + + while (iov_iter_count(it)) { + /* iov_iter_iovec() for ITER_BVEC */ + bvec_set_page(&bv, it->bvec->bv_page, + min(iov_iter_count(it), + it->bvec->bv_len - it->iov_offset), + it->bvec->bv_offset + it->iov_offset); + + /* + * 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(bv.bv_page)) + msg.msg_flags |= MSG_SPLICE_PAGES; + else + msg.msg_flags &= ~MSG_SPLICE_PAGES; + + iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bv, 1, bv.bv_len); + ret = sock_sendmsg(sock, &msg); + if (ret <= 0) { + if (ret == -EAGAIN) + ret = 0; + return ret; + } + + iov_iter_advance(it, ret); + } + + return 1; +} + /* * Write as much as possible. The socket is expected to be corked, * so we don't bother with MSG_MORE here. * * Return: - * >0 - done, nothing (else) to write + * 1 - done, nothing (else) to write * 0 - socket is full, need to wait * <0 - error */ static int ceph_tcp_send(struct ceph_connection *con) { - struct msghdr msg = { - .msg_iter = con->v2.out_iter, - .msg_flags = CEPH_MSG_FLAGS, - }; int ret; - if (WARN_ON(!iov_iter_is_bvec(&con->v2.out_iter))) - return -EINVAL; - - if (con->v2.out_iter_sendpage) - msg.msg_flags |= MSG_SPLICE_PAGES; - dout("%s con %p have %zu try_sendpage %d\n", __func__, con, iov_iter_count(&con->v2.out_iter), con->v2.out_iter_sendpage); - - ret = sock_sendmsg(con->sock, &msg); - if (ret > 0) - iov_iter_advance(&con->v2.out_iter, ret); - else if (ret == -EAGAIN) - ret = 0; - + if (con->v2.out_iter_sendpage) + ret = do_try_sendpage(con->sock, &con->v2.out_iter); + else + ret = do_sendmsg(con->sock, &con->v2.out_iter); dout("%s con %p ret %d left %zu\n", __func__, con, ret, iov_iter_count(&con->v2.out_iter)); return ret; |