diff options
author | Toke Høiland-Jørgensen <toke@redhat.com> | 2022-02-12 00:48:19 +0100 |
---|---|---|
committer | Andrii Nakryiko <andrii@kernel.org> | 2022-02-12 07:57:44 -0800 |
commit | 9c3de619e13ee6693ec5ac74f50b7aa89056a70e (patch) | |
tree | c0830fc53155a8c1ae9730332305fd31ea94c39c /tools/lib | |
parent | d130e954a002b901391037c33b9ae11bae5aaa91 (diff) | |
download | linux-9c3de619e13ee6693ec5ac74f50b7aa89056a70e.tar.bz2 |
libbpf: Use dynamically allocated buffer when receiving netlink messages
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.
v2:
- Move peek logic to libbpf_netlink_recv(), don't double free on ENOMEM.
Fixes: 8bbb77b7c7a2 ("libbpf: Add various netlink helpers")
Reported-by: Zhiqian Guan <zhguan@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/bpf/20220211234819.612288-1-toke@redhat.com
Diffstat (limited to 'tools/lib')
-rw-r--r-- | tools/lib/bpf/netlink.c | 55 |
1 files changed, 51 insertions, 4 deletions
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c index c39c37f99d5c..a598061f6fea 100644 --- a/tools/lib/bpf/netlink.c +++ b/tools/lib/bpf/netlink.c @@ -87,29 +87,75 @@ enum { NL_DONE, }; +static int 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 alloc_iov(struct iovec *iov, int len) +{ + void *nbuf; + + nbuf = realloc(iov->iov_base, len); + if (!nbuf) + return -ENOMEM; + + iov->iov_base = nbuf; + iov->iov_len = len; + return 0; +} + 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; + ret = alloc_iov(&iov, 4096); + if (ret) + goto done; + while (multipart) { start: multipart = false; - len = recv(sock, buf, sizeof(buf), 0); + len = netlink_recvmsg(sock, &mhdr, MSG_PEEK | MSG_TRUNC); + if (len < 0) { + ret = len; + goto done; + } + + if (len > iov.iov_len) { + ret = alloc_iov(&iov, len); + if (ret) + goto done; + } + + len = netlink_recvmsg(sock, &mhdr, 0); if (len < 0) { - ret = -errno; + ret = len; goto done; } if (len == 0) break; - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + for (nh = (struct nlmsghdr *)iov.iov_base; NLMSG_OK(nh, len); nh = NLMSG_NEXT(nh, len)) { if (nh->nlmsg_pid != nl_pid) { ret = -LIBBPF_ERRNO__WRNGPID; @@ -151,6 +197,7 @@ start: } ret = 0; done: + free(iov.iov_base); return ret; } |