On Sat, Feb 12, 2022 at 01:21:00AM IST, Toke Høiland-Jørgensen wrote:
> When receiving netlink messages, libbpf was using a statically allocated
> stack buffer of 4k bytes. This happened to work fine on systems with a 4k
> page size, but on systems with larger page sizes it can lead to truncated
> messages. The user-visible impact of this was that libbpf would insist no
> XDP program was attached to some interfaces because that bit of the netlink
> message got chopped off.
>
> Fix this by switching to a dynamically allocated buffer; we borrow the
> approach from iproute2 of using recvmsg() with MSG_PEEK|MSG_TRUNC to get
> the actual size of the pending message before receiving it, adjusting the
> buffer as necessary. While we're at it, also add retries on interrupted
> system calls around the recvmsg() call.
>
> Reported-by: Zhiqian Guan <zhguan@xxxxxxxxxx>
> Fixes: 8bbb77b7c7a2 ("libbpf: Add various netlink helpers")
> Signed-off-by: Toke Høiland-Jørgensen <toke@xxxxxxxxxx>
> ---
Thanks for the fix!
Acked-by: Kumar Kartikeya Dwivedi <memxor@xxxxxxxxx>
> tools/lib/bpf/netlink.c | 55 ++++++++++++++++++++++++++++++++++++++---
> 1 file changed, 52 insertions(+), 3 deletions(-)
>
> diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
> index c39c37f99d5c..9a6e95206bf0 100644
> --- a/tools/lib/bpf/netlink.c
> +++ b/tools/lib/bpf/netlink.c
> @@ -87,22 +87,70 @@ enum {
> NL_DONE,
> };
>
> +static int __libbpf_netlink_recvmsg(int sock, struct msghdr *mhdr, int flags)
> +{
> + int len;
> +
> + do {
> + len = recvmsg(sock, mhdr, flags);
> + } while (len < 0 && (errno == EINTR || errno == EAGAIN));
> +
> + if (len < 0)
> + return -errno;
> + return len;
> +}
> +
> +static int libbpf_netlink_recvmsg(int sock, struct msghdr *mhdr, char **buf)
> +{
> + struct iovec *iov = mhdr->msg_iov;
> + void *nbuf;
> + int len;
> +
> + len = __libbpf_netlink_recvmsg(sock, mhdr, MSG_PEEK | MSG_TRUNC);
> + if (len < 0)
> + return len;
> +
> + if (len < 4096)
> + len = 4096;
> +
> + if (len > iov->iov_len) {
> + nbuf = realloc(iov->iov_base, len);
> + if (!nbuf) {
> + free(iov->iov_base);
> + return -ENOMEM;
> + }
> + iov->iov_base = nbuf;
> + iov->iov_len = len;
> + }
> +
> + len = __libbpf_netlink_recvmsg(sock, mhdr, 0);
> + if (len > 0)
> + *buf = iov->iov_base;
> + return len;
> +}
> +
> static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
> __dump_nlmsg_t _fn, libbpf_dump_nlmsg_t fn,
> void *cookie)
> {
> + struct iovec iov = {};
> + struct msghdr mhdr = {
> + .msg_iov = &iov,
> + .msg_iovlen = 1,
> + };
> bool multipart = true;
> struct nlmsgerr *err;
> struct nlmsghdr *nh;
> - char buf[4096];
> int len, ret;
> + char *buf;
> +
>
> while (multipart) {
> start:
> multipart = false;
> - len = recv(sock, buf, sizeof(buf), 0);
> + len = libbpf_netlink_recvmsg(sock, &mhdr, &buf);
> if (len < 0) {
> - ret = -errno;
> + ret = len;
> goto done;
> }
>
> @@ -151,6 +199,7 @@ static int libbpf_netlink_recv(int sock, __u32 nl_pid, int seq,
> }
> ret = 0;
> done:
> + free(iov.iov_base);
> return ret;
> }
>
> --
> 2.35.1
>
--
Kartikeya
