[PATCH v1 net-next 00/15] ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.

[PATCH v1 net-next 00/15] ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.

[Kuniyuki Iwashima]

This series removes RTNL from ipmr rtnetlink handlers.

After this series, there are a few RTNL left in net/ipv4/ipmr.c
and such users will be converted to per-netns RTNL in another
series.

Patch 1 adds a selftest to exercise most? of the RTNL paths
 in net/ipv4/ipmr.c

Patch 2 - 6 converts RTM_GETLINK / RTM_GETROUTE handlers
 to RCU.

Patch 7 - 9 converts ->exit_batch() to ->exit_rtnl() to
 save one RTNL in cleanup_net().

Patch 10 - 11 removes unnecessary RTNL during setup_net()
 failure.

Patch 12 is a random cleanup.

Patch 13 - 15 drops RTNL for RTM_NEWROUTE and RTM_DELROUTE.


Kuniyuki Iwashima (15):
  selftest: net: Add basic functionality tests for ipmr.
  ipmr: Annotate access to mrt->mroute_do_{pim,assert,wrvifwhole}.
  ipmr: Convert ipmr_rtm_dumplink() to RCU.
  ipmr: Use MAXVIFS in mroute_msgsize().
  ipmr: Convert ipmr_rtm_getroute() to RCU.
  ipmr: Convert ipmr_rtm_dumproute() to RCU.
  ipmr: Move unregister_netdevice_many() out of mroute_clean_tables().
  ipmr: Move unregister_netdevice_many() out of ipmr_free_table().
  ipmr: Convert ipmr_net_exit_batch() to ->exit_rtnl().
  ipmr: Remove RTNL in ipmr_rules_init() and ipmr_net_init().
  ipmr: Call fib_rules_unregister() without RTNL.
  ipmr: Define net->ipv4.{ipmr_notifier_ops,ipmr_seq} under
    CONFIG_IP_MROUTE.
  ipmr/ip6mr: Convert net->ipv[46].ipmr_seq to atomic_t.
  ipmr: Add dedicated mutex for mrt->{mfc_hash,mfc_cache_list}.
  ipmr: Don't hold RTNL for ipmr_rtm_route().

 include/linux/mroute_base.h                   |   9 +-
 include/net/netns/ipv4.h                      |   6 +-
 include/net/netns/ipv6.h                      |   2 +-
 net/ipv4/ipmr.c                               | 257 ++++++----
 net/ipv4/ipmr_base.c                          |   4 +-
 net/ipv6/ip6mr.c                              |   4 +-
 .../testing/selftests/net/forwarding/Makefile |   4 +
 tools/testing/selftests/net/forwarding/ipmr.c | 455 ++++++++++++++++++
 8 files changed, 630 insertions(+), 111 deletions(-)
 create mode 100644 tools/testing/selftests/net/forwarding/ipmr.c

-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 01/15] selftest: net: Add basic functionality tests for ipmr.

[Kuniyuki Iwashima]

The new test exercise paths, where RTNL is needed, to
catch lockdep splat:

  setsockopt
    MRT_INIT / MRT_DONE
    MRT_ADD_VIF / MRT_DEL_VIF
    MRT_ADD_MFC / MRT_DEL_MFC / MRT_ADD_MFC_PROXY / MRT_DEL_MFC_PROXY
    MRT_TABLE
    MRT_FLUSH

  rtnetlink
    RTM_NEWROUTE
    RTM_DELROUTE

  NETDEV_UNREGISTER

I will extend this to cover IPv6 setsockopt() later.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 .../testing/selftests/net/forwarding/Makefile |   4 +
 tools/testing/selftests/net/forwarding/ipmr.c | 455 ++++++++++++++++++
 2 files changed, 459 insertions(+)
 create mode 100644 tools/testing/selftests/net/forwarding/ipmr.c

diff --git a/tools/testing/selftests/net/forwarding/Makefile b/tools/testing/selftests/net/forwarding/Makefile
index ff4a00d91a26..bbaf4d937dd8 100644
--- a/tools/testing/selftests/net/forwarding/Makefile
+++ b/tools/testing/selftests/net/forwarding/Makefile
@@ -133,6 +133,10 @@ TEST_FILES := \
 	tc_common.sh \
 # end of TEST_FILES
 
+TEST_GEN_PROGS := \
+	ipmr
+# end of TEST_GEN_PROGS
+
 TEST_INCLUDES := \
 	$(wildcard ../lib/sh/*.sh) \
 	../lib.sh \
diff --git a/tools/testing/selftests/net/forwarding/ipmr.c b/tools/testing/selftests/net/forwarding/ipmr.c
new file mode 100644
index 000000000000..699d8237d226
--- /dev/null
+++ b/tools/testing/selftests/net/forwarding/ipmr.c
@@ -0,0 +1,455 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright 2026 Google LLC */
+
+#include <linux/if.h>
+#include <linux/mroute.h>
+#include <linux/netlink.h>
+#include <linux/rtnetlink.h>
+#include <linux/socket.h>
+#include <sched.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+
+#include "kselftest_harness.h"
+
+FIXTURE(ipmr)
+{
+	int netlink_sk;
+	int raw_sk;
+	int veth_ifindex;
+};
+
+FIXTURE_VARIANT(ipmr)
+{
+	int family;
+	int protocol;
+	int level;
+	int opts[MRT_MAX - MRT_BASE + 1];
+};
+
+FIXTURE_VARIANT_ADD(ipmr, ipv4)
+{
+	.family = AF_INET,
+	.protocol = IPPROTO_IGMP,
+	.level = IPPROTO_IP,
+	.opts = {
+		MRT_INIT,
+		MRT_DONE,
+		MRT_ADD_VIF,
+		MRT_DEL_VIF,
+		MRT_ADD_MFC,
+		MRT_DEL_MFC,
+		MRT_VERSION,
+		MRT_ASSERT,
+		MRT_PIM,
+		MRT_TABLE,
+		MRT_ADD_MFC_PROXY,
+		MRT_DEL_MFC_PROXY,
+		MRT_FLUSH,
+	},
+};
+
+struct mfc_attr {
+	int table;
+	__u32 origin;
+	__u32 group;
+	int ifindex;
+	bool proxy;
+};
+
+static struct rtattr *nl_add_rtattr(struct nlmsghdr *nlmsg, struct rtattr *rta,
+				    int type, const void *data, int len)
+{
+	int unused;
+
+	rta->rta_type = type;
+	rta->rta_len = RTA_LENGTH(len);
+	memcpy(RTA_DATA(rta), data, len);
+
+	nlmsg->nlmsg_len += NLMSG_ALIGN(rta->rta_len);
+
+	return RTA_NEXT(rta, unused);
+}
+
+static int nl_sendmsg_mfc(struct __test_metadata *_metadata, FIXTURE_DATA(ipmr) *self,
+			  __u16 nlmsg_type, struct mfc_attr *mfc_attr)
+{
+	struct {
+		struct nlmsghdr nlmsg;
+		struct rtmsg rtm;
+		char buf[4096];
+	} req = {
+		.nlmsg = {
+			/* ipmr does not care about NLM_F_CREATE and NLM_F_EXCL ... */
+			.nlmsg_len = NLMSG_LENGTH(sizeof(req.rtm)),
+			.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK,
+			.nlmsg_type = nlmsg_type,
+		},
+		.rtm = {
+			/* hard requirements in rtm_to_ipmr_mfcc() */
+			.rtm_family = RTNL_FAMILY_IPMR,
+			.rtm_dst_len = 32,
+			.rtm_type = RTN_MULTICAST,
+			.rtm_scope = RT_SCOPE_UNIVERSE,
+			.rtm_protocol = RTPROT_MROUTED,
+		},
+	};
+	struct nlmsghdr *nlmsg = &req.nlmsg;
+	struct nlmsgerr *errmsg;
+	struct rtattr *rta;
+	int err;
+
+	rta = (struct rtattr *)&req.buf;
+	rta = nl_add_rtattr(nlmsg, rta, RTA_TABLE, &mfc_attr->table, sizeof(mfc_attr->table));
+	rta = nl_add_rtattr(nlmsg, rta, RTA_SRC, &mfc_attr->origin, sizeof(mfc_attr->origin));
+	rta = nl_add_rtattr(nlmsg, rta, RTA_DST, &mfc_attr->group, sizeof(mfc_attr->group));
+	if (mfc_attr->ifindex)
+		rta = nl_add_rtattr(nlmsg, rta, RTA_IIF, &mfc_attr->ifindex, sizeof(mfc_attr->ifindex));
+	if (mfc_attr->proxy)
+		rta = nl_add_rtattr(nlmsg, rta, RTA_PREFSRC, NULL, 0);
+
+	err = send(self->netlink_sk, &req, req.nlmsg.nlmsg_len, 0);
+	ASSERT_EQ(err, req.nlmsg.nlmsg_len);
+
+	memset(&req, 0, sizeof(req));
+
+	err = recv(self->netlink_sk, &req, sizeof(req), 0);
+	ASSERT_TRUE(NLMSG_OK(nlmsg, err));
+	ASSERT_EQ(NLMSG_ERROR, nlmsg->nlmsg_type);
+
+	errmsg = (struct nlmsgerr *)NLMSG_DATA(nlmsg);
+	return errmsg->error;
+}
+
+FIXTURE_SETUP(ipmr)
+{
+	struct ifreq ifr = {
+		.ifr_name = "veth0",
+	};
+	int err;
+
+	err = unshare(CLONE_NEWNET);
+	ASSERT_EQ(0, err);
+
+	self->netlink_sk = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	ASSERT_LE(0, self->netlink_sk);
+
+	self->raw_sk = socket(variant->family, SOCK_RAW, variant->protocol);
+	ASSERT_LT(0, self->raw_sk);
+
+	err = system("ip link add veth0 type veth peer veth1");
+	ASSERT_EQ(0, err);
+
+	err = ioctl(self->raw_sk, SIOCGIFINDEX, &ifr);
+	ASSERT_EQ(0, err);
+
+	self->veth_ifindex = ifr.ifr_ifindex;
+}
+
+FIXTURE_TEARDOWN(ipmr)
+{
+	close(self->raw_sk);
+	close(self->netlink_sk);
+}
+
+TEST_F(ipmr, mrt_init)
+{
+	int err, val = 0;  /* any value is ok, but size must be int for MRT_INIT. */
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_INIT - MRT_BASE],
+			 &val,  sizeof(val));
+	ASSERT_EQ(0, err);
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_DONE - MRT_BASE],
+			 &val,  sizeof(val));
+	ASSERT_EQ(0, err);
+}
+
+TEST_F(ipmr, mrt_add_vif_register)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_REGISTER,
+	};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_vif | grep -q pimreg");
+	ASSERT_EQ(0, err);
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_DEL_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+}
+
+TEST_F(ipmr, mrt_del_vif_unreg)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_USE_IFINDEX,
+		.vifc_lcl_ifindex = self->veth_ifindex,
+	};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_vif | grep -q veth0");
+	ASSERT_EQ(0, err);
+
+	/* VIF is removed along with its device. */
+	err = system("ip link del veth0");
+	ASSERT_EQ(0, err);
+
+	/* mrt->vif_table[veth_ifindex]->dev is NULL. */
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_DEL_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(-1, err);
+	ASSERT_EQ(EADDRNOTAVAIL, errno);
+}
+
+TEST_F(ipmr, mrt_del_vif_netns_dismantle)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_USE_IFINDEX,
+		.vifc_lcl_ifindex = self->veth_ifindex,
+	};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	/* Let cleanup_net() remove veth0 and VIF. */
+}
+
+TEST_F(ipmr, mrt_add_mfc)
+{
+	struct mfcctl mfc = {};
+	int err;
+
+	/* MRT_ADD_MFC / MRT_ADD_MFC_PROXY does not need vif to exist (unlike netlink). */
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_MFC - MRT_BASE],
+			 &mfc,  sizeof(mfc));
+	ASSERT_EQ(0, err);
+
+	/* (0.0.0.0 -> 0.0.0.0) */
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_DEL_MFC - MRT_BASE],
+			 &mfc,  sizeof(mfc));
+}
+
+TEST_F(ipmr, mrt_add_mfc_proxy)
+{
+	struct mfcctl mfc = {};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_MFC_PROXY - MRT_BASE],
+			 &mfc,  sizeof(mfc));
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_DEL_MFC_PROXY - MRT_BASE],
+			 &mfc,  sizeof(mfc));
+}
+
+TEST_F(ipmr, mrt_add_mfc_netlink)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_USE_IFINDEX,
+		.vifc_lcl_ifindex = self->veth_ifindex,
+	};
+	struct mfc_attr mfc_attr = {
+		.table = RT_TABLE_DEFAULT,
+		.origin = 0,
+		.group = 0,
+		.ifindex = self->veth_ifindex,
+		.proxy = false,
+	};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+}
+
+TEST_F(ipmr, mrt_add_mfc_netlink_proxy)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_USE_IFINDEX,
+		.vifc_lcl_ifindex = self->veth_ifindex,
+	};
+	struct mfc_attr mfc_attr = {
+		.table = RT_TABLE_DEFAULT,
+		.origin = 0,
+		.group = 0,
+		.ifindex = self->veth_ifindex,
+		.proxy = true,
+	};
+	int err;
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+}
+
+TEST_F(ipmr, mrt_add_mfc_netlink_no_vif)
+{
+	struct mfc_attr mfc_attr = {
+		.table = RT_TABLE_DEFAULT,
+		.origin = 0,
+		.group = 0,
+		.proxy = false,
+	};
+	int err;
+
+	/* netlink always requires RTA_IIF of an existing vif. */
+	mfc_attr.ifindex = 0;
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(-ENFILE, err);
+
+	/* netlink always requires RTA_IIF of an existing vif. */
+	mfc_attr.ifindex = self->veth_ifindex;
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(-ENFILE, err);
+}
+
+TEST_F(ipmr, mrt_del_mfc_netlink_netns_dismantle)
+{
+	struct vifctl vifs[2] = {
+		{
+			.vifc_vifi = 0,
+			.vifc_flags = VIFF_USE_IFINDEX,
+			.vifc_lcl_ifindex = self->veth_ifindex,
+		},
+		{
+			.vifc_vifi = 1,
+			.vifc_flags = VIFF_REGISTER,
+		}
+	};
+	struct mfc_attr mfc_attr = {
+		.table = RT_TABLE_DEFAULT,
+		.origin = 0,
+		.group = 0,
+		.ifindex = self->veth_ifindex,
+		.proxy = false,
+	};
+	int i, err;
+
+	for (i = 0; i < 2; i++) {
+		/* Create 2 VIFs just to avoid -ENFILE later. */
+		err = setsockopt(self->raw_sk,
+				 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+				 &vifs[i],  sizeof(vifs[i]));
+		ASSERT_EQ(0, err);
+	}
+
+	/* Create a MFC for mrt->vif_table[0]. */
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	/* Remove mrt->vif_table[0]. */
+	err = system("ip link del veth0");
+	ASSERT_EQ(0, err);
+
+	/* MFC entry is NOT removed even if the tied VIF is removed... */
+	err = system("cat /proc/net/ip_mr_cache | grep -q '00000000 00000000' ");
+	ASSERT_EQ(0, err);
+
+	/* ... and netlink is not capable of removing such an entry
+	 * because netlink always requires a valid RTA_IIF ... :/
+	 */
+	err = nl_sendmsg_mfc(_metadata, self, RTM_DELROUTE, &mfc_attr);
+	ASSERT_EQ(-ENODEV, err);
+
+	/* It can be removed by setsockopt(), but let cleanup_net() remove this time. */
+}
+
+TEST_F(ipmr, mrt_table_flush)
+{
+	struct vifctl vif = {
+		.vifc_vifi = 0,
+		.vifc_flags = VIFF_USE_IFINDEX,
+		.vifc_lcl_ifindex = self->veth_ifindex,
+	};
+	struct mfc_attr mfc_attr = {
+		.origin = 0,
+		.group = 0,
+		.ifindex = self->veth_ifindex,
+		.proxy = false,
+	};
+	int table_id = 92;
+	int err, flags;
+
+	/* Set a random table id rather than RT_TABLE_DEFAULT.
+	 * Note that /proc/net/ip_mr_{vif,cache} only supports RT_TABLE_DEFAULT.
+	 */
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_TABLE - MRT_BASE],
+			 &table_id,  sizeof(table_id));
+	ASSERT_EQ(0, err);
+
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_ADD_VIF - MRT_BASE],
+			 &vif,  sizeof(vif));
+	ASSERT_EQ(0, err);
+
+	mfc_attr.table = table_id;
+	err = nl_sendmsg_mfc(_metadata, self, RTM_NEWROUTE, &mfc_attr);
+	ASSERT_EQ(0, err);
+
+	/* Flush mrt->vif_table[] and all caches. */
+	flags = MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
+		MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC;
+	err = setsockopt(self->raw_sk,
+			 variant->level, variant->opts[MRT_FLUSH - MRT_BASE],
+			 &flags,  sizeof(flags));
+	ASSERT_EQ(0, err);
+}
+
+TEST_HARNESS_MAIN
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 02/15] ipmr: Annotate access to mrt->mroute_do_{pim,assert,wrvifwhole}.

[Kuniyuki Iwashima]

These fields in struct mr_table are updated in ip_mroute_setsockopt()
under RTNL:

  * mroute_do_pim
  * mroute_do_assert
  * mroute_do_wrvifwhole

However, ip_mroute_getsockopt() does not hold RTNL and read the first
two fields locklessly, and ip_mr_forward() reads the latter two under
RCU.

Let's use WRITE_ONCE() and READ_ONCE() for them.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 131382c388e9..377b5848f99c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1506,7 +1506,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 			ret = -EFAULT;
 			break;
 		}
-		mrt->mroute_do_assert = val;
+		WRITE_ONCE(mrt->mroute_do_assert, val);
 		break;
 	case MRT_PIM:
 		if (!ipmr_pimsm_enabled()) {
@@ -1525,9 +1525,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 		do_wrvifwhole = (val == IGMPMSG_WRVIFWHOLE);
 		val = !!val;
 		if (val != mrt->mroute_do_pim) {
-			mrt->mroute_do_pim = val;
-			mrt->mroute_do_assert = val;
-			mrt->mroute_do_wrvifwhole = do_wrvifwhole;
+			WRITE_ONCE(mrt->mroute_do_pim, val);
+			WRITE_ONCE(mrt->mroute_do_assert, val);
+			WRITE_ONCE(mrt->mroute_do_wrvifwhole, do_wrvifwhole);
 		}
 		break;
 	case MRT_TABLE:
@@ -1610,10 +1610,10 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
 	case MRT_PIM:
 		if (!ipmr_pimsm_enabled())
 			return -ENOPROTOOPT;
-		val = mrt->mroute_do_pim;
+		val = READ_ONCE(mrt->mroute_do_pim);
 		break;
 	case MRT_ASSERT:
-		val = mrt->mroute_do_assert;
+		val = READ_ONCE(mrt->mroute_do_assert);
 		break;
 	default:
 		return -ENOPROTOOPT;
@@ -2037,7 +2037,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
 
 		atomic_long_inc(&c->_c.mfc_un.res.wrong_if);
 
-		if (true_vifi >= 0 && mrt->mroute_do_assert &&
+		if (true_vifi >= 0 && READ_ONCE(mrt->mroute_do_assert) &&
 		    /* pimsm uses asserts, when switching from RPT to SPT,
 		     * so that we cannot check that packet arrived on an oif.
 		     * It is bad, but otherwise we would need to move pretty
@@ -2050,7 +2050,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
 			       MFC_ASSERT_THRESH)) {
 			c->_c.mfc_un.res.last_assert = jiffies;
 			ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
-			if (mrt->mroute_do_wrvifwhole)
+			if (READ_ONCE(mrt->mroute_do_wrvifwhole))
 				ipmr_cache_report(mrt, skb, true_vifi,
 						  IGMPMSG_WRVIFWHOLE);
 		}
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 03/15] ipmr: Convert ipmr_rtm_dumplink() to RCU.

[Kuniyuki Iwashima]

net->ipv4.mr_tables is updated under RTNL and can be read
safely under RCU.

Once created, the multicast route tables are not removed
until netns dismantle.

ipmr_rtm_dumplink() does not need RTNL protection for
ipmr_for_each_table() and ipmr_fill_table() if RCU is held.

Let's convert it to RCU.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 377b5848f99c..a4bc653e04ed 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2901,12 +2901,13 @@ static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb)
 	if (nla_put_u32(skb, IPMRA_TABLE_ID, mrt->id) ||
 	    nla_put_u32(skb, IPMRA_TABLE_CACHE_RES_QUEUE_LEN, queue_len) ||
 	    nla_put_s32(skb, IPMRA_TABLE_MROUTE_REG_VIF_NUM,
-			mrt->mroute_reg_vif_num) ||
+			READ_ONCE(mrt->mroute_reg_vif_num)) ||
 	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_ASSERT,
-		       mrt->mroute_do_assert) ||
-	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM, mrt->mroute_do_pim) ||
+		       READ_ONCE(mrt->mroute_do_assert)) ||
+	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_PIM,
+		       READ_ONCE(mrt->mroute_do_pim)) ||
 	    nla_put_u8(skb, IPMRA_TABLE_MROUTE_DO_WRVIFWHOLE,
-		       mrt->mroute_do_wrvifwhole))
+		       READ_ONCE(mrt->mroute_do_wrvifwhole)))
 		return false;
 
 	return true;
@@ -2919,7 +2920,7 @@ static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb)
 	struct vif_device *vif;
 
 	vif = &mrt->vif_table[vifid];
-	vif_dev = rtnl_dereference(vif->dev);
+	vif_dev = vif_dev_read(vif);
 	/* if the VIF doesn't exist just continue */
 	if (!vif_dev)
 		return true;
@@ -2928,16 +2929,16 @@ static bool ipmr_fill_vif(struct mr_table *mrt, u32 vifid, struct sk_buff *skb)
 	if (!vif_nest)
 		return false;
 
-	if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, vif_dev->ifindex) ||
+	if (nla_put_u32(skb, IPMRA_VIFA_IFINDEX, READ_ONCE(vif_dev->ifindex)) ||
 	    nla_put_u32(skb, IPMRA_VIFA_VIF_ID, vifid) ||
 	    nla_put_u16(skb, IPMRA_VIFA_FLAGS, vif->flags) ||
-	    nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, vif->bytes_in,
+	    nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_IN, READ_ONCE(vif->bytes_in),
 			      IPMRA_VIFA_PAD) ||
-	    nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, vif->bytes_out,
+	    nla_put_u64_64bit(skb, IPMRA_VIFA_BYTES_OUT, READ_ONCE(vif->bytes_out),
 			      IPMRA_VIFA_PAD) ||
-	    nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, vif->pkt_in,
+	    nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_IN, READ_ONCE(vif->pkt_in),
 			      IPMRA_VIFA_PAD) ||
-	    nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, vif->pkt_out,
+	    nla_put_u64_64bit(skb, IPMRA_VIFA_PACKETS_OUT, READ_ONCE(vif->pkt_out),
 			      IPMRA_VIFA_PAD) ||
 	    nla_put_be32(skb, IPMRA_VIFA_LOCAL_ADDR, vif->local) ||
 	    nla_put_be32(skb, IPMRA_VIFA_REMOTE_ADDR, vif->remote)) {
@@ -2992,6 +2993,8 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
 	s_t = cb->args[0];
 	s_e = cb->args[1];
 
+	rcu_read_lock();
+
 	ipmr_for_each_table(mrt, net) {
 		struct nlattr *vifs, *af;
 		struct ifinfomsg *hdr;
@@ -3048,6 +3051,8 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
 	}
 
 out:
+	rcu_read_unlock();
+
 	cb->args[1] = e;
 	cb->args[0] = t;
 
@@ -3287,7 +3292,7 @@ static struct pernet_operations ipmr_net_ops = {
 
 static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = {
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETLINK,
-	 .dumpit = ipmr_rtm_dumplink},
+	 .dumpit = ipmr_rtm_dumplink, .flags = RTNL_FLAG_DUMP_UNLOCKED},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_NEWROUTE,
 	 .doit = ipmr_rtm_route},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE,
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 04/15] ipmr: Use MAXVIFS in mroute_msgsize().

[Kuniyuki Iwashima]

mroute_msgsize() calculates skb size needed for ipmr_fill_mroute().

The size differs based on mrt->maxvif.

We will drop RTNL for ipmr_rtm_getroute() and mrt->maxvif may
change under RCU.

To avoid -EMSGSIZE, let's calculate the size with the maximum
value of mrt->maxvif, MAXVIFS.

struct rtnexthop is 8 bytes and MAXVIFS is 32, so the maximum delta
is 256 bytes, which is small enough.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index a4bc653e04ed..7b5177b673d3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2510,7 +2510,7 @@ static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 				cmd, flags);
 }
 
-static size_t mroute_msgsize(bool unresolved, int maxvif)
+static size_t mroute_msgsize(bool unresolved)
 {
 	size_t len =
 		NLMSG_ALIGN(sizeof(struct rtmsg))
@@ -2523,7 +2523,7 @@ static size_t mroute_msgsize(bool unresolved, int maxvif)
 		len = len
 		      + nla_total_size(4)	/* RTA_IIF */
 		      + nla_total_size(0)	/* RTA_MULTIPATH */
-		      + maxvif * NLA_ALIGN(sizeof(struct rtnexthop))
+		      + MAXVIFS * NLA_ALIGN(sizeof(struct rtnexthop))
 						/* RTA_MFC_STATS */
 		      + nla_total_size_64bit(sizeof(struct rta_mfc_stats))
 		;
@@ -2538,8 +2538,7 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS,
-				       mrt->maxvif),
+	skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS),
 			GFP_ATOMIC);
 	if (!skb)
 		goto errout;
@@ -2711,7 +2710,7 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		goto errout_free;
 	}
 
-	skb = nlmsg_new(mroute_msgsize(false, mrt->maxvif), GFP_KERNEL);
+	skb = nlmsg_new(mroute_msgsize(false), GFP_KERNEL);
 	if (!skb) {
 		err = -ENOBUFS;
 		goto errout_free;
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 05/15] ipmr: Convert ipmr_rtm_getroute() to RCU.

[Kuniyuki Iwashima]

ipmr_rtm_getroute() calls __ipmr_get_table(), ipmr_cache_find(),
and ipmr_fill_mroute().

The table is not removed until netns dismantle, and net->ipv4.mr_tables
is managed with RCU list API, so __ipmr_get_table() is safe under RCU.

struct mfc_cache is freed by mr_cache_put() after RCU grace period,
so we can use ipmr_cache_find() under RCU.  rcu_read_lock() around
it was just to avoid lockdep splat for rhl_for_each_entry_rcu().

ipmr_fill_mroute() calls mr_fill_mroute(), which properly uses RCU.

Let's drop RTNL for ipmr_rtm_getroute() and use RCU instead.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c      | 34 ++++++++++++++++++----------------
 net/ipv4/ipmr_base.c |  4 ++--
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7b5177b673d3..53dda438ba32 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2680,9 +2680,9 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 {
 	struct net *net = sock_net(in_skb->sk);
 	struct nlattr *tb[RTA_MAX + 1];
-	struct sk_buff *skb = NULL;
 	struct mfc_cache *cache;
 	struct mr_table *mrt;
+	struct sk_buff *skb;
 	__be32 src, grp;
 	u32 tableid;
 	int err;
@@ -2695,39 +2695,40 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	grp = nla_get_in_addr_default(tb[RTA_DST], 0);
 	tableid = nla_get_u32_default(tb[RTA_TABLE], 0);
 
+	skb = nlmsg_new(mroute_msgsize(false), GFP_KERNEL);
+	if (!skb) {
+		err = -ENOBUFS;
+		goto errout;
+	}
+
+	rcu_read_lock();
+
 	mrt = __ipmr_get_table(net, tableid ? tableid : RT_TABLE_DEFAULT);
 	if (!mrt) {
 		err = -ENOENT;
-		goto errout_free;
+		goto errout_unlock;
 	}
 
-	/* entries are added/deleted only under RTNL */
-	rcu_read_lock();
 	cache = ipmr_cache_find(mrt, src, grp);
-	rcu_read_unlock();
 	if (!cache) {
 		err = -ENOENT;
-		goto errout_free;
-	}
-
-	skb = nlmsg_new(mroute_msgsize(false), GFP_KERNEL);
-	if (!skb) {
-		err = -ENOBUFS;
-		goto errout_free;
+		goto errout_unlock;
 	}
 
 	err = ipmr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid,
 			       nlh->nlmsg_seq, cache,
 			       RTM_NEWROUTE, 0);
 	if (err < 0)
-		goto errout_free;
+		goto errout_unlock;
 
-	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
+	rcu_read_unlock();
 
+	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
 errout:
 	return err;
 
-errout_free:
+errout_unlock:
+	rcu_read_unlock();
 	kfree_skb(skb);
 	goto errout;
 }
@@ -3297,7 +3298,8 @@ static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = {
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE,
 	 .doit = ipmr_rtm_route},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE,
-	 .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute},
+	 .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute,
+	 .flags = RTNL_FLAG_DOIT_UNLOCKED},
 };
 
 int __init ip_mr_init(void)
diff --git a/net/ipv4/ipmr_base.c b/net/ipv4/ipmr_base.c
index 28d77d454d44..9a38419e0f26 100644
--- a/net/ipv4/ipmr_base.c
+++ b/net/ipv4/ipmr_base.c
@@ -223,7 +223,7 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 	rcu_read_lock();
 	vif_dev = rcu_dereference(mrt->vif_table[c->mfc_parent].dev);
-	if (vif_dev && nla_put_u32(skb, RTA_IIF, vif_dev->ifindex) < 0) {
+	if (vif_dev && nla_put_u32(skb, RTA_IIF, READ_ONCE(vif_dev->ifindex)) < 0) {
 		rcu_read_unlock();
 		return -EMSGSIZE;
 	}
@@ -252,7 +252,7 @@ int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
 
 			nhp->rtnh_flags = 0;
 			nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
-			nhp->rtnh_ifindex = vif_dev->ifindex;
+			nhp->rtnh_ifindex = READ_ONCE(vif_dev->ifindex);
 			nhp->rtnh_len = sizeof(*nhp);
 		}
 	}
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 06/15] ipmr: Convert ipmr_rtm_dumproute() to RCU.

[Kuniyuki Iwashima]

ipmr_rtm_dumproute() calls mr_table_dump() or mr_rtm_dumproute(),
and mr_rtm_dumproute() finally calls mr_table_dump().

mr_table_dump() calls the passed function, _ipmr_fill_mroute().

_ipmr_fill_mroute() is a wrapper of ipmr_fill_mroute() to cast
struct mr_mfc * to struct mfc_cache *.

ipmr_fill_mroute() can be already called safely under RCU.

Let's convert ipmr_rtm_dumproute() to RCU.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 29 ++++++++++++++++++++---------
 1 file changed, 20 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 53dda438ba32..3af6b3d33cc8 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2736,15 +2736,17 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct fib_dump_filter filter = {
-		.rtnl_held = true,
+		.rtnl_held = false,
 	};
 	int err;
 
+	rcu_read_lock();
+
 	if (cb->strict_check) {
 		err = ip_valid_fib_dump_req(sock_net(skb->sk), cb->nlh,
 					    &filter, cb);
 		if (err < 0)
-			return err;
+			goto out;
 	}
 
 	if (filter.table_id) {
@@ -2752,19 +2754,28 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = __ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
-			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR)
-				return skb->len;
+			if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) {
+				err = skb->len;
+				goto out;
+			}
 
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
-			return -ENOENT;
+			err = -ENOENT;
+			goto out;
 		}
+
 		err = mr_table_dump(mrt, skb, cb, _ipmr_fill_mroute,
 				    &mfc_unres_lock, &filter);
-		return skb->len ? : err;
+		err = skb->len ? : err;
+		goto out;
 	}
 
-	return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter,
-				_ipmr_fill_mroute, &mfc_unres_lock, &filter);
+	err = mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter,
+			       _ipmr_fill_mroute, &mfc_unres_lock, &filter);
+out:
+	rcu_read_unlock();
+
+	return err;
 }
 
 static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = {
@@ -3299,7 +3310,7 @@ static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = {
 	 .doit = ipmr_rtm_route},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE,
 	 .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute,
-	 .flags = RTNL_FLAG_DOIT_UNLOCKED},
+	 .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
 };
 
 int __init ip_mr_init(void)
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 07/15] ipmr: Move unregister_netdevice_many() out of mroute_clean_tables().

[Kuniyuki Iwashima]

This is a prep commit to convert ipmr_net_exit_batch() to
->exit_rtnl().

Let's move unregister_netdevice_many() in mroute_clean_tables()
to its callers.

As a bonus, mrtsock_destruct() can do batching for all tables.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 34 ++++++++++++++++++++++++----------
 1 file changed, 24 insertions(+), 10 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3af6b3d33cc8..f8bbb88f5784 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -112,7 +112,8 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
 				 int cmd);
 static void igmpmsg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt);
-static void mroute_clean_tables(struct mr_table *mrt, int flags);
+static void mroute_clean_tables(struct mr_table *mrt, int flags,
+				struct list_head *dev_kill_list);
 static void ipmr_expire_process(struct timer_list *t);
 
 #ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -427,12 +428,15 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt)
 {
 	struct net *net = read_pnet(&mrt->net);
+	LIST_HEAD(dev_kill_list);
 
 	WARN_ON_ONCE(!mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
-				 MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC);
+			    MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC,
+			    &dev_kill_list);
+	unregister_netdevice_many(&dev_kill_list);
 	rhltable_destroy(&mrt->mfc_hash);
 	kfree(mrt);
 }
@@ -1293,12 +1297,12 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 }
 
 /* Close the multicast socket, and clear the vif tables etc */
-static void mroute_clean_tables(struct mr_table *mrt, int flags)
+static void mroute_clean_tables(struct mr_table *mrt, int flags,
+				struct list_head *dev_kill_list)
 {
 	struct net *net = read_pnet(&mrt->net);
-	struct mr_mfc *c, *tmp;
 	struct mfc_cache *cache;
-	LIST_HEAD(list);
+	struct mr_mfc *c, *tmp;
 	int i;
 
 	/* Shut down all active vif entries */
@@ -1308,9 +1312,8 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags)
 			     !(flags & MRT_FLUSH_VIFS_STATIC)) ||
 			    (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT_FLUSH_VIFS)))
 				continue;
-			vif_delete(mrt, i, 0, &list);
+			vif_delete(mrt, i, 0, dev_kill_list);
 		}
-		unregister_netdevice_many(&list);
 	}
 
 	/* Wipe the cache */
@@ -1349,9 +1352,11 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags)
 static void mrtsock_destruct(struct sock *sk)
 {
 	struct net *net = sock_net(sk);
+	LIST_HEAD(dev_kill_list);
 	struct mr_table *mrt;
 
 	rtnl_lock();
+
 	ipmr_for_each_table(mrt, net) {
 		if (sk == rtnl_dereference(mrt->mroute_sk)) {
 			IPV4_DEVCONF_ALL(net, MC_FORWARDING)--;
@@ -1360,9 +1365,13 @@ static void mrtsock_destruct(struct sock *sk)
 						    NETCONFA_IFINDEX_ALL,
 						    net->ipv4.devconf_all);
 			RCU_INIT_POINTER(mrt->mroute_sk, NULL);
-			mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC);
+			mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_MFC,
+					    &dev_kill_list);
 		}
 	}
+
+	unregister_netdevice_many(&dev_kill_list);
+
 	rtnl_unlock();
 }
 
@@ -1485,7 +1494,9 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 					   sk == rtnl_dereference(mrt->mroute_sk),
 					   parent);
 		break;
-	case MRT_FLUSH:
+	case MRT_FLUSH: {
+		LIST_HEAD(dev_kill_list);
+
 		if (optlen != sizeof(val)) {
 			ret = -EINVAL;
 			break;
@@ -1494,8 +1505,11 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 			ret = -EFAULT;
 			break;
 		}
-		mroute_clean_tables(mrt, val);
+
+		mroute_clean_tables(mrt, val, &dev_kill_list);
+		unregister_netdevice_many(&dev_kill_list);
 		break;
+	}
 	/* Control PIM assert. */
 	case MRT_ASSERT:
 		if (optlen != sizeof(val)) {
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 08/15] ipmr: Move unregister_netdevice_many() out of ipmr_free_table().

[Kuniyuki Iwashima]

This is a prep commit to convert ipmr_net_exit_batch() to
->exit_rtnl().

Let's move unregister_netdevice_many() in ipmr_free_table()
to its callers.

Now ipmr_rules_exit() can do batching all tables per netns.

Note that later we will remove RTNL and unregister_netdevice_many()
in ipmr_rules_init().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index f8bbb88f5784..3fb50307fc2f 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -102,7 +102,8 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
 static struct kmem_cache *mrt_cachep __ro_after_init;
 
 static struct mr_table *ipmr_new_table(struct net *net, u32 id);
-static void ipmr_free_table(struct mr_table *mrt);
+static void ipmr_free_table(struct mr_table *mrt,
+			    struct list_head *dev_kill_list);
 
 static void ip_mr_forward(struct net *net, struct mr_table *mrt,
 			  struct net_device *dev, struct sk_buff *skb,
@@ -251,6 +252,7 @@ static const struct fib_rules_ops __net_initconst ipmr_rules_ops_template = {
 static int __net_init ipmr_rules_init(struct net *net)
 {
 	struct fib_rules_ops *ops;
+	LIST_HEAD(dev_kill_list);
 	struct mr_table *mrt;
 	int err;
 
@@ -275,7 +277,8 @@ static int __net_init ipmr_rules_init(struct net *net)
 
 err2:
 	rtnl_lock();
-	ipmr_free_table(mrt);
+	ipmr_free_table(mrt, &dev_kill_list);
+	unregister_netdevice_many(&dev_kill_list);
 	rtnl_unlock();
 err1:
 	fib_rules_unregister(ops);
@@ -285,12 +288,15 @@ static int __net_init ipmr_rules_init(struct net *net)
 static void __net_exit ipmr_rules_exit(struct net *net)
 {
 	struct mr_table *mrt, *next;
+	LIST_HEAD(dev_kill_list);
 
 	ASSERT_RTNL();
 	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
 		list_del(&mrt->list);
-		ipmr_free_table(mrt);
+		ipmr_free_table(mrt, &dev_kill_list);
 	}
+
+	unregister_netdevice_many(&dev_kill_list);
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 }
 
@@ -349,8 +355,13 @@ static int __net_init ipmr_rules_init(struct net *net)
 
 static void __net_exit ipmr_rules_exit(struct net *net)
 {
+	LIST_HEAD(dev_kill_list);
+
 	ASSERT_RTNL();
-	ipmr_free_table(net->ipv4.mrt);
+
+	ipmr_free_table(net->ipv4.mrt, &dev_kill_list);
+	unregister_netdevice_many(&dev_kill_list);
+
 	net->ipv4.mrt = NULL;
 }
 
@@ -425,18 +436,16 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 			      ipmr_expire_process, ipmr_new_table_set);
 }
 
-static void ipmr_free_table(struct mr_table *mrt)
+static void ipmr_free_table(struct mr_table *mrt, struct list_head *dev_kill_list)
 {
 	struct net *net = read_pnet(&mrt->net);
-	LIST_HEAD(dev_kill_list);
 
 	WARN_ON_ONCE(!mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
 			    MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC,
-			    &dev_kill_list);
-	unregister_netdevice_many(&dev_kill_list);
+			    dev_kill_list);
 	rhltable_destroy(&mrt->mfc_hash);
 	kfree(mrt);
 }
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 09/15] ipmr: Convert ipmr_net_exit_batch() to ->exit_rtnl().

[Kuniyuki Iwashima]

ipmr_net_ops uses ->exit_batch() to acquire RTNL only once
for dying network namespaces.

ipmr does not depend on the ordering of ->exit_rtnl() and
->exit_batch() of other pernet_operations (unlike fib_net_ops).

Once ipmr_free_table() is called and all devices are
queued for destruction in ->exit_rtnl(), later during
NETDEV_UNREGISTER, ipmr_device_event() will not see anything
in vif table and just do nothing.

Let's convert ipmr_net_exit_batch() to ->exit_rtnl().

Note that fib_rules_unregister() does not need RTNL and
we will remove RTNL and unregister_netdevice_many() in
ipmr_net_init().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 31 +++++++++++++------------------
 1 file changed, 13 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3fb50307fc2f..3526c9afcb03 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -285,18 +285,17 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return err;
 }
 
-static void __net_exit ipmr_rules_exit(struct net *net)
+static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
+					    struct list_head *dev_kill_list)
 {
 	struct mr_table *mrt, *next;
-	LIST_HEAD(dev_kill_list);
 
 	ASSERT_RTNL();
 	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
 		list_del(&mrt->list);
-		ipmr_free_table(mrt, &dev_kill_list);
+		ipmr_free_table(mrt, dev_kill_list);
 	}
 
-	unregister_netdevice_many(&dev_kill_list);
 	fib_rules_unregister(net->ipv4.mr_rules_ops);
 }
 
@@ -353,14 +352,12 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return 0;
 }
 
-static void __net_exit ipmr_rules_exit(struct net *net)
+static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
+					    struct list_head *dev_kill_list)
 {
-	LIST_HEAD(dev_kill_list);
-
 	ASSERT_RTNL();
 
-	ipmr_free_table(net->ipv4.mrt, &dev_kill_list);
-	unregister_netdevice_many(&dev_kill_list);
+	ipmr_free_table(net->ipv4.mrt, dev_kill_list);
 
 	net->ipv4.mrt = NULL;
 }
@@ -3264,6 +3261,7 @@ static void __net_exit ipmr_notifier_exit(struct net *net)
 /* Setup for IP multicast routing */
 static int __net_init ipmr_net_init(struct net *net)
 {
+	LIST_HEAD(dev_kill_list);
 	int err;
 
 	err = ipmr_notifier_init(net);
@@ -3290,7 +3288,8 @@ static int __net_init ipmr_net_init(struct net *net)
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 proc_vif_fail:
 	rtnl_lock();
-	ipmr_rules_exit(net);
+	ipmr_rules_exit_rtnl(net, &dev_kill_list);
+	unregister_netdevice_many(&dev_kill_list);
 	rtnl_unlock();
 #endif
 ipmr_rules_fail:
@@ -3308,20 +3307,16 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	ipmr_notifier_exit(net);
 }
 
-static void __net_exit ipmr_net_exit_batch(struct list_head *net_list)
+static void __net_exit ipmr_net_exit_rtnl(struct net *net,
+					  struct list_head *dev_kill_list)
 {
-	struct net *net;
-
-	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list)
-		ipmr_rules_exit(net);
-	rtnl_unlock();
+	ipmr_rules_exit_rtnl(net, dev_kill_list);
 }
 
 static struct pernet_operations ipmr_net_ops = {
 	.init = ipmr_net_init,
 	.exit = ipmr_net_exit,
-	.exit_batch = ipmr_net_exit_batch,
+	.exit_rtnl = ipmr_net_exit_rtnl,
 };
 
 static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = {
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 10/15] ipmr: Remove RTNL in ipmr_rules_init() and ipmr_net_init().

[Kuniyuki Iwashima]

When ipmr_free_table() is called from ipmr_rules_init() or
ipmr_net_init(), the netns is not yet published.

Thus, no device should have been registered, and
mroute_clean_tables() will not call vif_delete(), so
unregister_netdevice_many() is unnecessary.

unregister_netdevice_many() does nothing if the list is empty,
but it requires RTNL due to the unconditional ASSERT_RTNL()
at the entry of unregister_netdevice_many_notify().

Let's remove unnecessary RTNL and ASSERT_RTNL() and instead
add WARN_ON_ONCE() in ipmr_free_table().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 11 ++---------
 1 file changed, 2 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3526c9afcb03..537be40af9e0 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -276,10 +276,7 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return 0;
 
 err2:
-	rtnl_lock();
 	ipmr_free_table(mrt, &dev_kill_list);
-	unregister_netdevice_many(&dev_kill_list);
-	rtnl_unlock();
 err1:
 	fib_rules_unregister(ops);
 	return err;
@@ -290,7 +287,6 @@ static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
 {
 	struct mr_table *mrt, *next;
 
-	ASSERT_RTNL();
 	list_for_each_entry_safe(mrt, next, &net->ipv4.mr_tables, list) {
 		list_del(&mrt->list);
 		ipmr_free_table(mrt, dev_kill_list);
@@ -355,8 +351,6 @@ static int __net_init ipmr_rules_init(struct net *net)
 static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
 					    struct list_head *dev_kill_list)
 {
-	ASSERT_RTNL();
-
 	ipmr_free_table(net->ipv4.mrt, dev_kill_list);
 
 	net->ipv4.mrt = NULL;
@@ -445,6 +439,8 @@ static void ipmr_free_table(struct mr_table *mrt, struct list_head *dev_kill_lis
 			    dev_kill_list);
 	rhltable_destroy(&mrt->mfc_hash);
 	kfree(mrt);
+
+	WARN_ON_ONCE(!net_initialized(net) && !list_empty(dev_kill_list));
 }
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */
@@ -3287,10 +3283,7 @@ static int __net_init ipmr_net_init(struct net *net)
 proc_cache_fail:
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 proc_vif_fail:
-	rtnl_lock();
 	ipmr_rules_exit_rtnl(net, &dev_kill_list);
-	unregister_netdevice_many(&dev_kill_list);
-	rtnl_unlock();
 #endif
 ipmr_rules_fail:
 	ipmr_notifier_exit(net);
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 11/15] ipmr: Call fib_rules_unregister() without RTNL.

[Kuniyuki Iwashima]

fib_rules_unregister() removes ops from net->rules_ops under
spinlock, calls ops->delete() for each rule, and frees the ops.

ipmr_rules_ops_template does not have ->delete(), and any
operation does not require RTNL there.

Let's move fib_rules_unregister() from ipmr_rules_exit_rtnl()
to ipmr_net_exit().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 net/ipv4/ipmr.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 537be40af9e0..0dd683932d2b 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -282,6 +282,11 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return err;
 }
 
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+	fib_rules_unregister(net->ipv4.mr_rules_ops);
+}
+
 static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
 					    struct list_head *dev_kill_list)
 {
@@ -291,8 +296,6 @@ static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
 		list_del(&mrt->list);
 		ipmr_free_table(mrt, dev_kill_list);
 	}
-
-	fib_rules_unregister(net->ipv4.mr_rules_ops);
 }
 
 static int ipmr_rules_dump(struct net *net, struct notifier_block *nb,
@@ -348,6 +351,10 @@ static int __net_init ipmr_rules_init(struct net *net)
 	return 0;
 }
 
+static void __net_exit ipmr_rules_exit(struct net *net)
+{
+}
+
 static void __net_exit ipmr_rules_exit_rtnl(struct net *net,
 					    struct list_head *dev_kill_list)
 {
@@ -3284,6 +3291,7 @@ static int __net_init ipmr_net_init(struct net *net)
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 proc_vif_fail:
 	ipmr_rules_exit_rtnl(net, &dev_kill_list);
+	ipmr_rules_exit(net);
 #endif
 ipmr_rules_fail:
 	ipmr_notifier_exit(net);
@@ -3297,6 +3305,7 @@ static void __net_exit ipmr_net_exit(struct net *net)
 	remove_proc_entry("ip_mr_cache", net->proc_net);
 	remove_proc_entry("ip_mr_vif", net->proc_net);
 #endif
+	ipmr_rules_exit(net);
 	ipmr_notifier_exit(net);
 }
 
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 12/15] ipmr: Define net->ipv4.{ipmr_notifier_ops,ipmr_seq} under CONFIG_IP_MROUTE.

[Kuniyuki Iwashima]

net->ipv4.ipmr_notifier_ops and net->ipv4.ipmr_seq are used
only in net/ipv4/ipmr.c.

Let's move these definitions under CONFIG_IP_MROUTE.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 include/net/netns/ipv4.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 8e971c7bf164..380ff34c0233 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -279,6 +279,8 @@ struct netns_ipv4 {
 	struct list_head	mr_tables;
 	struct fib_rules_ops	*mr_rules_ops;
 #endif
+	struct fib_notifier_ops	*ipmr_notifier_ops;
+	unsigned int		ipmr_seq;	/* protected by rtnl_mutex */
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed;
@@ -290,9 +292,6 @@ struct netns_ipv4 {
 	struct fib_notifier_ops	*notifier_ops;
 	unsigned int	fib_seq;	/* writes protected by rtnl_mutex */
 
-	struct fib_notifier_ops	*ipmr_notifier_ops;
-	unsigned int	ipmr_seq;	/* protected by rtnl_mutex */
-
 	atomic_t	rt_genid;
 	siphash_key_t	ip_id_key;
 	struct hlist_head	*inet_addr_lst;
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 13/15] ipmr/ip6mr: Convert net->ipv[46].ipmr_seq to atomic_t.

[Kuniyuki Iwashima]

We will no longer hold RTNL for ipmr_mfc_add() and ipmr_mfc_delete().

MFC entry can be loosely connected with VIF by its index for
mrt->vif_table[] (stored in mfc_parent), but the two tables are
not synchronised.  i.e. Even if VIF 1 is removed, MFC for VIF 1
is not automatically removed.

The only field that the MFC/VIF interfaces share is
net->ipv[46].ipmr_seq, which is protected by RTNL.

Adding a new mutex for both just to protect a single field is overkill.

Let's convert the field to atomic_t.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 include/linux/mroute_base.h | 8 ++++----
 include/net/netns/ipv4.h    | 2 +-
 include/net/netns/ipv6.h    | 2 +-
 net/ipv4/ipmr.c             | 4 ++--
 net/ipv6/ip6mr.c            | 4 ++--
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 0075f6e5c3da..0baa6f994da9 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -76,7 +76,7 @@ static inline int mr_call_vif_notifiers(struct net *net,
 					struct vif_device *vif,
 					struct net_device *vif_dev,
 					unsigned short vif_index, u32 tb_id,
-					unsigned int *ipmr_seq)
+					atomic_t *ipmr_seq)
 {
 	struct vif_entry_notifier_info info = {
 		.info = {
@@ -89,7 +89,7 @@ static inline int mr_call_vif_notifiers(struct net *net,
 	};
 
 	ASSERT_RTNL();
-	(*ipmr_seq)++;
+	atomic_inc(ipmr_seq);
 	return call_fib_notifiers(net, event_type, &info.info);
 }
 
@@ -198,7 +198,7 @@ static inline int mr_call_mfc_notifiers(struct net *net,
 					unsigned short family,
 					enum fib_event_type event_type,
 					struct mr_mfc *mfc, u32 tb_id,
-					unsigned int *ipmr_seq)
+					atomic_t *ipmr_seq)
 {
 	struct mfc_entry_notifier_info info = {
 		.info = {
@@ -209,7 +209,7 @@ static inline int mr_call_mfc_notifiers(struct net *net,
 	};
 
 	ASSERT_RTNL();
-	(*ipmr_seq)++;
+	atomic_inc(ipmr_seq);
 	return call_fib_notifiers(net, event_type, &info.info);
 }
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 380ff34c0233..94dca64fec41 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -280,7 +280,7 @@ struct netns_ipv4 {
 	struct fib_rules_ops	*mr_rules_ops;
 #endif
 	struct fib_notifier_ops	*ipmr_notifier_ops;
-	unsigned int		ipmr_seq;	/* protected by rtnl_mutex */
+	atomic_t		ipmr_seq;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed;
diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h
index 34bdb1308e8f..499e4288170f 100644
--- a/include/net/netns/ipv6.h
+++ b/include/net/netns/ipv6.h
@@ -118,7 +118,7 @@ struct netns_ipv6 {
 	struct seg6_pernet_data *seg6_data;
 	struct fib_notifier_ops	*notifier_ops;
 	struct fib_notifier_ops	*ip6mr_notifier_ops;
-	unsigned int ipmr_seq; /* protected by rtnl_mutex */
+	atomic_t		ipmr_seq;
 	struct {
 		struct hlist_head head;
 		spinlock_t	lock;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 0dd683932d2b..bcb3f920e8c3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -3224,7 +3224,7 @@ static const struct net_protocol pim_protocol = {
 
 static unsigned int ipmr_seq_read(const struct net *net)
 {
-	return READ_ONCE(net->ipv4.ipmr_seq) + ipmr_rules_seq_read(net);
+	return atomic_read(&net->ipv4.ipmr_seq) + ipmr_rules_seq_read(net);
 }
 
 static int ipmr_dump(struct net *net, struct notifier_block *nb,
@@ -3245,7 +3245,7 @@ static int __net_init ipmr_notifier_init(struct net *net)
 {
 	struct fib_notifier_ops *ops;
 
-	net->ipv4.ipmr_seq = 0;
+	atomic_set(&net->ipv4.ipmr_seq, 0);
 
 	ops = fib_notifier_ops_register(&ipmr_notifier_ops_template, net);
 	if (IS_ERR(ops))
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index e047a4680ab0..85010ff21c98 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1280,7 +1280,7 @@ static int ip6mr_device_event(struct notifier_block *this,
 
 static unsigned int ip6mr_seq_read(const struct net *net)
 {
-	return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net);
+	return atomic_read(&net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net);
 }
 
 static int ip6mr_dump(struct net *net, struct notifier_block *nb,
@@ -1305,7 +1305,7 @@ static int __net_init ip6mr_notifier_init(struct net *net)
 {
 	struct fib_notifier_ops *ops;
 
-	net->ipv6.ipmr_seq = 0;
+	atomic_set(&net->ipv6.ipmr_seq, 0);
 
 	ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net);
 	if (IS_ERR(ops))
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 14/15] ipmr: Add dedicated mutex for mrt->{mfc_hash,mfc_cache_list}.

[Kuniyuki Iwashima]

We will no longer hold RTNL for ipmr_rtm_route() to modify the
MFC hash table.

Only __dev_get_by_index() in rtm_to_ipmr_mfcc() is the RTNL
dependant, otherwise, we just need protection for mrt->mfc_hash
and mrt->mfc_cache_list.

Let's add a new mutex for ipmr_mfc_add(), ipmr_mfc_delete(),
and mroute_clean_tables() (setsockopt(MRT_FLUSH or MRT_DONE)).

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 include/net/netns/ipv4.h |  1 +
 net/ipv4/ipmr.c          | 28 ++++++++++++++++++++++------
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 94dca64fec41..4c249aeaf7f1 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -281,6 +281,7 @@ struct netns_ipv4 {
 #endif
 	struct fib_notifier_ops	*ipmr_notifier_ops;
 	atomic_t		ipmr_seq;
+	struct mutex		mfc_mutex;
 #endif
 #ifdef CONFIG_IP_ROUTE_MULTIPATH
 	struct sysctl_fib_multipath_hash_seed sysctl_fib_multipath_hash_seed;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index bcb3f920e8c3..0dd7d088de50 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1327,6 +1327,8 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags,
 
 	/* Wipe the cache */
 	if (flags & (MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC)) {
+		mutex_lock(&net->ipv4.mfc_mutex);
+
 		list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
 			if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC_STATIC)) ||
 			    (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT_FLUSH_MFC)))
@@ -1339,6 +1341,8 @@ static void mroute_clean_tables(struct mr_table *mrt, int flags,
 			mroute_netlink_event(mrt, cache, RTM_DELROUTE);
 			mr_cache_put(c);
 		}
+
+		mutex_unlock(&net->ipv4.mfc_mutex);
 	}
 
 	if (flags & MRT_FLUSH_MFC) {
@@ -1496,12 +1500,17 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
 		}
 		if (parent == 0)
 			parent = mfc.mfcc_parent;
+
+		mutex_lock(&net->ipv4.mfc_mutex);
+
 		if (optname == MRT_DEL_MFC || optname == MRT_DEL_MFC_PROXY)
 			ret = ipmr_mfc_delete(mrt, &mfc, parent);
 		else
 			ret = ipmr_mfc_add(net, mrt, &mfc,
 					   sk == rtnl_dereference(mrt->mroute_sk),
 					   parent);
+
+		mutex_unlock(&net->ipv4.mfc_mutex);
 		break;
 	case MRT_FLUSH: {
 		LIST_HEAD(dev_kill_list);
@@ -2911,21 +2920,26 @@ static int ipmr_rtm_route(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(skb->sk);
-	int ret, mrtsock, parent;
-	struct mr_table *tbl;
+	int ret, mrtsock = 0, parent;
+	struct mr_table *tbl = NULL;
 	struct mfcctl mfcc;
 
-	mrtsock = 0;
-	tbl = NULL;
 	ret = rtm_to_ipmr_mfcc(net, nlh, &mfcc, &mrtsock, &tbl, extack);
 	if (ret < 0)
 		return ret;
 
 	parent = ret ? mfcc.mfcc_parent : -1;
+
+	mutex_lock(&net->ipv4.mfc_mutex);
+
 	if (nlh->nlmsg_type == RTM_NEWROUTE)
-		return ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent);
+		ret = ipmr_mfc_add(net, tbl, &mfcc, mrtsock, parent);
 	else
-		return ipmr_mfc_delete(tbl, &mfcc, parent);
+		ret = ipmr_mfc_delete(tbl, &mfcc, parent);
+
+	mutex_unlock(&net->ipv4.mfc_mutex);
+
+	return ret;
 }
 
 static bool ipmr_fill_table(struct mr_table *mrt, struct sk_buff *skb)
@@ -3267,6 +3281,8 @@ static int __net_init ipmr_net_init(struct net *net)
 	LIST_HEAD(dev_kill_list);
 	int err;
 
+	mutex_init(&net->ipv4.mfc_mutex);
+
 	err = ipmr_notifier_init(net);
 	if (err)
 		goto ipmr_notifier_fail;
-- 
2.53.0.414.gf7e9f6c205-goog

[PATCH v1 net-next 15/15] ipmr: Don't hold RTNL for ipmr_rtm_route().

[Kuniyuki Iwashima]

ipmr_mfc_add() and ipmr_mfc_delete() are already protected
by a dedicated mutex.

rtm_to_ipmr_mfcc() calls __ipmr_get_table(), __dev_get_by_index(),
amd ipmr_find_vif().

Once __dev_get_by_index() is converted to dev_get_by_index_rcu(),
we can move the other two functions under that same RCU section
and drop RTNL for ipmr_rtm_route().

Let's do that conversion and drop ASSERT_RTNL() in
mr_call_mfc_notifiers().

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
---
 include/linux/mroute_base.h |  1 -
 net/ipv4/ipmr.c             | 34 +++++++++++++++++++++-------------
 2 files changed, 21 insertions(+), 14 deletions(-)

diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 0baa6f994da9..cf3374580f74 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -208,7 +208,6 @@ static inline int mr_call_mfc_notifiers(struct net *net,
 		.tb_id = tb_id
 	};
 
-	ASSERT_RTNL();
 	atomic_inc(ipmr_seq);
 	return call_fib_notifiers(net, event_type, &info.info);
 }
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 0dd7d088de50..4e645a87dc6c 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1209,7 +1209,6 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
 	struct net *net = read_pnet(&mrt->net);
 	struct mfc_cache *c;
 
-	/* The entries are added/deleted only under RTNL */
 	rcu_read_lock();
 	c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr,
 				   mfc->mfcc_mcastgrp.s_addr, parent);
@@ -1236,7 +1235,6 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
 	if (mfc->mfcc_parent >= MAXVIFS)
 		return -ENFILE;
 
-	/* The entries are added/deleted only under RTNL */
 	rcu_read_lock();
 	c = ipmr_cache_find_parent(mrt, mfc->mfcc_origin.s_addr,
 				   mfc->mfcc_mcastgrp.s_addr, parent);
@@ -2851,10 +2849,10 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 {
 	struct net_device *dev = NULL;
 	u32 tblid = RT_TABLE_DEFAULT;
+	int ret, rem, iif = 0;
 	struct mr_table *mrt;
 	struct nlattr *attr;
 	struct rtmsg *rtm;
-	int ret, rem;
 
 	ret = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX,
 					rtm_ipmr_policy, extack);
@@ -2881,11 +2879,7 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 			mfcc->mfcc_mcastgrp.s_addr = nla_get_be32(attr);
 			break;
 		case RTA_IIF:
-			dev = __dev_get_by_index(net, nla_get_u32(attr));
-			if (!dev) {
-				ret = -ENODEV;
-				goto out;
-			}
+			iif = nla_get_u32(attr);
 			break;
 		case RTA_MULTIPATH:
 			if (ipmr_nla_get_ttls(attr, mfcc) < 0) {
@@ -2901,16 +2895,30 @@ static int rtm_to_ipmr_mfcc(struct net *net, struct nlmsghdr *nlh,
 			break;
 		}
 	}
+
+	rcu_read_lock();
+
 	mrt = __ipmr_get_table(net, tblid);
 	if (!mrt) {
 		ret = -ENOENT;
-		goto out;
+		goto unlock;
 	}
+
+	if (iif) {
+		dev = dev_get_by_index_rcu(net, iif);
+		if (!dev) {
+			ret = -ENODEV;
+			goto unlock;
+		}
+
+		mfcc->mfcc_parent = ipmr_find_vif(mrt, dev);
+	}
+
 	*mrtret = mrt;
 	*mrtsock = rtm->rtm_protocol == RTPROT_MROUTED ? 1 : 0;
-	if (dev)
-		mfcc->mfcc_parent = ipmr_find_vif(mrt, dev);
 
+unlock:
+	rcu_read_unlock();
 out:
 	return ret;
 }
@@ -3341,9 +3349,9 @@ static const struct rtnl_msg_handler ipmr_rtnl_msg_handlers[] __initconst = {
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETLINK,
 	 .dumpit = ipmr_rtm_dumplink, .flags = RTNL_FLAG_DUMP_UNLOCKED},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_NEWROUTE,
-	 .doit = ipmr_rtm_route},
+	 .doit = ipmr_rtm_route, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_DELROUTE,
-	 .doit = ipmr_rtm_route},
+	 .doit = ipmr_rtm_route, .flags = RTNL_FLAG_DOIT_UNLOCKED},
 	{.protocol = RTNL_FAMILY_IPMR, .msgtype = RTM_GETROUTE,
 	 .doit = ipmr_rtm_getroute, .dumpit = ipmr_rtm_dumproute,
 	 .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
-- 
2.53.0.414.gf7e9f6c205-goog

[syzbot ci] Re: ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.

[syzbot ci]

syzbot ci has tested the following series

[v1] ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.
https://lore.kernel.org/all/20260226023637.1335854-1-kuniyu@google.com
* [PATCH v1 net-next 01/15] selftest: net: Add basic functionality tests for ipmr.
* [PATCH v1 net-next 02/15] ipmr: Annotate access to mrt->mroute_do_{pim,assert,wrvifwhole}.
* [PATCH v1 net-next 03/15] ipmr: Convert ipmr_rtm_dumplink() to RCU.
* [PATCH v1 net-next 04/15] ipmr: Use MAXVIFS in mroute_msgsize().
* [PATCH v1 net-next 05/15] ipmr: Convert ipmr_rtm_getroute() to RCU.
* [PATCH v1 net-next 06/15] ipmr: Convert ipmr_rtm_dumproute() to RCU.
* [PATCH v1 net-next 07/15] ipmr: Move unregister_netdevice_many() out of mroute_clean_tables().
* [PATCH v1 net-next 08/15] ipmr: Move unregister_netdevice_many() out of ipmr_free_table().
* [PATCH v1 net-next 09/15] ipmr: Convert ipmr_net_exit_batch() to ->exit_rtnl().
* [PATCH v1 net-next 10/15] ipmr: Remove RTNL in ipmr_rules_init() and ipmr_net_init().
* [PATCH v1 net-next 11/15] ipmr: Call fib_rules_unregister() without RTNL.
* [PATCH v1 net-next 12/15] ipmr: Define net->ipv4.{ipmr_notifier_ops,ipmr_seq} under CONFIG_IP_MROUTE.
* [PATCH v1 net-next 13/15] ipmr/ip6mr: Convert net->ipv[46].ipmr_seq to atomic_t.
* [PATCH v1 net-next 14/15] ipmr: Add dedicated mutex for mrt->{mfc_hash,mfc_cache_list}.
* [PATCH v1 net-next 15/15] ipmr: Don't hold RTNL for ipmr_rtm_route().

and found the following issue:
WARNING in ipmr_free_table

Full report is available here:
https://ci.syzbot.org/series/d7068eba-72b1-4110-aeb0-d4528e03fd24

***

WARNING in ipmr_free_table

tree:      net-next
URL:       https://kernel.googlesource.com/pub/scm/linux/kernel/git/netdev/net-next.git
base:      c7f5c6fb0f2b1a44490a36582a251f0a304d6b0c
arch:      amd64
compiler:  Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
config:    https://ci.syzbot.org/builds/0afa280b-14ff-4aec-8a20-7f8507025dd8/config
C repro:   https://ci.syzbot.org/findings/e38687c7-5a8b-4c68-909c-a0ffdd17a674/c_repro
syz repro: https://ci.syzbot.org/findings/e38687c7-5a8b-4c68-909c-a0ffdd17a674/syz_repro

------------[ cut here ]------------
!net_initialized(net) && !list_empty(dev_kill_list)
WARNING: net/ipv4/ipmr.c:450 at ipmr_free_table+0x150/0x180 net/ipv4/ipmr.c:450, CPU#1: syz.1.18/6004
Modules linked in:
CPU: 1 UID: 0 PID: 6004 Comm: syz.1.18 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014
RIP: 0010:ipmr_free_table+0x150/0x180 net/ipv4/ipmr.c:450
Code: 23 e8 f4 5c 95 f7 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc cc e8 df 5c 95 f7 90 0f 0b 90 e9 64 ff ff ff e8 d1 5c 95 f7 90 <0f> 0b 90 eb d7 44 89 e1 80 e1 07 80 c1 03 38 c1 0f 8c 03 ff ff ff
RSP: 0018:ffffc900037afa70 EFLAGS: 00010293
RAX: ffffffff8a302fbf RBX: ffffc900037afb60 RCX: ffff888172a70000
RDX: 0000000000000000 RSI: ffffffff8def033c RDI: ffffffff8c27a480
RBP: 0000000000000001 R08: ffffffff901166b7 R09: 1ffffffff2022cd6
R10: dffffc0000000000 R11: fffffbfff2022cd7 R12: ffff88816a392758
R13: dffffc0000000000 R14: ffff8881b8960000 R15: ffff88816a392758
FS:  00007f5a2d24e6c0(0000) GS:ffff8882a9469000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f7b7544e9d3 CR3: 0000000172316000 CR4: 00000000000006f0
Call Trace:
 <TASK>
 ipmr_rules_exit_rtnl net/ipv4/ipmr.c:297 [inline]
 ipmr_net_exit_rtnl+0x156/0x1a0 net/ipv4/ipmr.c:3339
 ops_exit_rtnl_list net/core/net_namespace.c:181 [inline]
 ops_undo_list+0x347/0x940 net/core/net_namespace.c:248
 setup_net+0x2f0/0x340 net/core/net_namespace.c:462
 copy_net_ns+0x50e/0x730 net/core/net_namespace.c:581
 create_new_namespaces+0x3e7/0x6a0 kernel/nsproxy.c:130
 unshare_nsproxy_namespaces+0x11a/0x160 kernel/nsproxy.c:226
 ksys_unshare+0x4f4/0x900 kernel/fork.c:3174
 __do_sys_unshare kernel/fork.c:3245 [inline]
 __se_sys_unshare kernel/fork.c:3243 [inline]
 __x64_sys_unshare+0x38/0x50 kernel/fork.c:3243
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f5a2c39c629
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f5a2d24e028 EFLAGS: 00000246 ORIG_RAX: 0000000000000110
RAX: ffffffffffffffda RBX: 00007f5a2c615fa0 RCX: 00007f5a2c39c629
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 000000006a040000
RBP: 00007f5a2c432b39 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007f5a2c616038 R14: 00007f5a2c615fa0 R15: 00007fffb0e41968
 </TASK>


***

If these findings have caused you to resend the series or submit a
separate fix, please add the following tag to your commit message:
  Tested-by: syzbot@syzkaller.appspotmail.com

---
This report is generated by a bot. It may contain errors.
syzbot ci engineers can be reached at syzkaller@googlegroups.com.

Re: [syzbot ci] Re: ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.

[Kuniyuki Iwashima]

From: syzbot ci <syzbot+ci7bfbcdccdcddd61f@syzkaller.appspotmail.com>
Date: Thu, 26 Feb 2026 09:00:11 -0800
> syzbot ci has tested the following series
> 
> [v1] ipmr: No RTNL for RTNL_FAMILY_IPMR rtnetlink.
> https://lore.kernel.org/all/20260226023637.1335854-1-kuniyu@google.com
> * [PATCH v1 net-next 01/15] selftest: net: Add basic functionality tests for ipmr.
> * [PATCH v1 net-next 02/15] ipmr: Annotate access to mrt->mroute_do_{pim,assert,wrvifwhole}.
> * [PATCH v1 net-next 03/15] ipmr: Convert ipmr_rtm_dumplink() to RCU.
> * [PATCH v1 net-next 04/15] ipmr: Use MAXVIFS in mroute_msgsize().
> * [PATCH v1 net-next 05/15] ipmr: Convert ipmr_rtm_getroute() to RCU.
> * [PATCH v1 net-next 06/15] ipmr: Convert ipmr_rtm_dumproute() to RCU.
> * [PATCH v1 net-next 07/15] ipmr: Move unregister_netdevice_many() out of mroute_clean_tables().
> * [PATCH v1 net-next 08/15] ipmr: Move unregister_netdevice_many() out of ipmr_free_table().
> * [PATCH v1 net-next 09/15] ipmr: Convert ipmr_net_exit_batch() to ->exit_rtnl().
> * [PATCH v1 net-next 10/15] ipmr: Remove RTNL in ipmr_rules_init() and ipmr_net_init().
> * [PATCH v1 net-next 11/15] ipmr: Call fib_rules_unregister() without RTNL.
> * [PATCH v1 net-next 12/15] ipmr: Define net->ipv4.{ipmr_notifier_ops,ipmr_seq} under CONFIG_IP_MROUTE.
> * [PATCH v1 net-next 13/15] ipmr/ip6mr: Convert net->ipv[46].ipmr_seq to atomic_t.
> * [PATCH v1 net-next 14/15] ipmr: Add dedicated mutex for mrt->{mfc_hash,mfc_cache_list}.
> * [PATCH v1 net-next 15/15] ipmr: Don't hold RTNL for ipmr_rtm_route().
> 
> and found the following issue:
> WARNING in ipmr_free_table
> 
> Full report is available here:
> https://ci.syzbot.org/series/d7068eba-72b1-4110-aeb0-d4528e03fd24
> 
> ***
> 
> WARNING in ipmr_free_table
> 
> tree:      net-next
> URL:       https://kernel.googlesource.com/pub/scm/linux/kernel/git/netdev/net-next.git
> base:      c7f5c6fb0f2b1a44490a36582a251f0a304d6b0c
> arch:      amd64
> compiler:  Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8
> config:    https://ci.syzbot.org/builds/0afa280b-14ff-4aec-8a20-7f8507025dd8/config
> C repro:   https://ci.syzbot.org/findings/e38687c7-5a8b-4c68-909c-a0ffdd17a674/c_repro
> syz repro: https://ci.syzbot.org/findings/e38687c7-5a8b-4c68-909c-a0ffdd17a674/syz_repro
> 
> ------------[ cut here ]------------
> !net_initialized(net) && !list_empty(dev_kill_list)
> WARNING: net/ipv4/ipmr.c:450 at ipmr_free_table+0x150/0x180 net/ipv4/ipmr.c:450, CPU#1: syz.1.18/6004

I forgot dev_kill_list could have some devices collected
from _other_ ->rtnl_exit() _after_ successful ipmr init.

My assumption in patch 10 is still correct, and I'll squash
this in v2.

diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 4e645a87dc6c..89e151121cea 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -437,17 +437,19 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
 static void ipmr_free_table(struct mr_table *mrt, struct list_head *dev_kill_list)
 {
 	struct net *net = read_pnet(&mrt->net);
+	LIST_HEAD(ipmr_dev_kill_list);
 
 	WARN_ON_ONCE(!mr_can_free_table(net));
 
 	timer_shutdown_sync(&mrt->ipmr_expire_timer);
 	mroute_clean_tables(mrt, MRT_FLUSH_VIFS | MRT_FLUSH_VIFS_STATIC |
 			    MRT_FLUSH_MFC | MRT_FLUSH_MFC_STATIC,
-			    dev_kill_list);
+			    &ipmr_dev_kill_list);
 	rhltable_destroy(&mrt->mfc_hash);
 	kfree(mrt);
 
-	WARN_ON_ONCE(!net_initialized(net) && !list_empty(dev_kill_list));
+	WARN_ON_ONCE(!net_initialized(net) && !list_empty(&ipmr_dev_kill_list));
+	list_splice(&ipmr_dev_kill_list, dev_kill_list);
 }
 
 /* Service routines creating virtual interfaces: DVMRP tunnels and PIMREG */