Merge branch 'netlink-fix-a-dump-livelock-with-a-notification-queued'

Jhonata Poma-Hansen says:

====================
netlink: fix a dump livelock with a notification queued

A netlink dump that starts while a notification is still charged to a
socket with a small receive buffer fails with ENOBUFS, and every retry
from recvmsg() fails the same way. A reader that peeks before reading,
as libnl does, never consumes the message at the head of the queue and
spins forever. I hit this with "iw dev wlan0 scan" on an arm64 board.

Patch 1 goes back to checking sk_rcvbuf before charging the dump skb,
as before commit ae8f160e7eb2. Patch 2 adds a selftest; it fails
without patch 1 and is skipped without the privileges to create a
netns.
====================

Link: https://patch.msgid.link/20261027-netlink-dump-livelock-v2-0-c4bb05352a33@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 107 insertions, 1 deletions

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index fec2879c497d..1281c42a3456 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2322,9 +2322,13 @@ static int netlink_dump(struct sock *sk, bool lock_taken)
 	if (!skb)
 		goto errout_skb;
 
+	/* Check the limit before charging the skb: netlink_recvmsg() continues
+	 * the dump at or below half of sk_rcvbuf, and the skb must be queued
+	 * then. Keep sk_rmem_alloc at or below INT_MAX.
+	 */
 	rcvbuf = READ_ONCE(sk->sk_rcvbuf);
 	rmem = atomic_add_return(skb->truesize, &sk->sk_rmem_alloc);
-	if (rmem != skb->truesize && rmem >= rcvbuf) {
+	if (rmem - skb->truesize >= rcvbuf || rmem > INT_MAX) {
 		atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
 		goto errout_skb;
 	}
diff --git a/tools/testing/selftests/net/netlink-dumps.c b/tools/testing/selftests/net/netlink-dumps.c
index 51129c564d0a..4a94a25167e2 100644
--- a/tools/testing/selftests/net/netlink-dumps.c
+++ b/tools/testing/selftests/net/netlink-dumps.c
@@ -2,9 +2,12 @@
 
 #define _GNU_SOURCE
 
+#include <errno.h>
 #include <fcntl.h>
+#include <sched.h>
 #include <stdio.h>
 #include <string.h>
+#include <sys/ioctl.h>
 #include <sys/socket.h>
 #include <sys/stat.h>
 #include <sys/syscall.h>
@@ -260,4 +263,103 @@ TEST(close_with_ref)
 	usleep(100 * 1000);
 }
 
+static int lo_set_up(int sock, bool up)
+{
+	struct ifreq ifr = {};
+
+	strcpy(ifr.ifr_name, "lo");
+	if (ioctl(sock, SIOCGIFFLAGS, &ifr))
+		return -1;
+	if (up)
+		ifr.ifr_flags |= IFF_UP;
+	else
+		ifr.ifr_flags &= ~IFF_UP;
+	return ioctl(sock, SIOCSIFFLAGS, &ifr);
+}
+
+static const struct {
+	struct nlmsghdr nlhdr;
+	struct ifinfomsg ifm;
+} dump_links = {
+	.nlhdr = {
+		.nlmsg_len	= sizeof(dump_links),
+		.nlmsg_type	= RTM_GETLINK,
+		.nlmsg_flags	= NLM_F_REQUEST | NLM_F_ACK | NLM_F_DUMP,
+		.nlmsg_seq	= 1,
+	},
+	.ifm = {
+		.ifi_family	= AF_UNSPEC,
+	},
+};
+
+// A dump started while a notification is still queued must make progress
+// for a reader which peeks before reading, like libnl does
+TEST(dump_with_queued_ntf)
+{
+	struct sockaddr_nl addr = {
+		.nl_family	= AF_NETLINK,
+		.nl_groups	= RTMGRP_LINK,
+	};
+	int netlink_sock, inet_sock, i, ret, links = 0;
+	int rcvbuf = 2048;
+	bool done = false;
+	char buf[32768];
+	ssize_t n;
+
+	ret = unshare(CLONE_NEWNET);
+	if (ret && errno == EPERM)
+		SKIP(return, "Needs CAP_SYS_ADMIN for a netns");
+	ASSERT_EQ(ret, 0);
+
+	inet_sock = socket(AF_INET, SOCK_DGRAM, 0);
+	ASSERT_GE(inet_sock, 0);
+	netlink_sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	ASSERT_GE(netlink_sock, 0);
+	ASSERT_EQ(setsockopt(netlink_sock, SOL_SOCKET, SO_RCVBUF,
+			     &rcvbuf, sizeof(rcvbuf)), 0);
+	ASSERT_EQ(bind(netlink_sock, (struct sockaddr *)&addr,
+		       sizeof(addr)), 0);
+
+	// A large read makes the kernel attempt large dump skbs
+	ASSERT_EQ(lo_set_up(inet_sock, true), 0);
+	n = recv(netlink_sock, buf, sizeof(buf), 0);
+	ASSERT_GE(n, (ssize_t)sizeof(struct nlmsghdr));
+
+	// Leave one notification queued, then start the dump
+	ASSERT_EQ(lo_set_up(inet_sock, false), 0);
+	n = send(netlink_sock, &dump_links, sizeof(dump_links), 0);
+	ASSERT_EQ(n, sizeof(dump_links));
+
+	for (i = 0; i < 100 && !done; i++) {
+		struct nlmsghdr *nlh;
+
+		n = recv(netlink_sock, buf, sizeof(buf),
+			 MSG_PEEK | MSG_TRUNC | MSG_DONTWAIT);
+		if (n < 0)
+			continue;
+		n = recv(netlink_sock, buf, sizeof(buf), MSG_DONTWAIT);
+		if (n < 0)
+			continue;
+
+		for (nlh = (struct nlmsghdr *)buf; NLMSG_OK(nlh, n);
+		     nlh = NLMSG_NEXT(nlh, n)) {
+			if (nlh->nlmsg_seq != dump_links.nlhdr.nlmsg_seq)
+				continue;
+			if (nlh->nlmsg_type == NLMSG_ERROR)
+				EXPECT_EQ(*(int *)NLMSG_DATA(nlh), 0);
+			if (nlh->nlmsg_type == RTM_NEWLINK)
+				links++;
+			if (nlh->nlmsg_type == NLMSG_DONE) {
+				EXPECT_EQ(*(int *)NLMSG_DATA(nlh), 0);
+				done = true;
+			}
+		}
+	}
+	EXPECT_TRUE(done);
+	EXPECT_GE(links, 1);
+
+	close(netlink_sock);
+	close(inet_sock);
+}
+
 TEST_HARNESS_MAIN