From 4f47e8ab6ab796b5380f74866fa5287aca4dcc58 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 22 Jun 2020 16:40:29 +0800 Subject: xfrm: policy: match with both mark and mask on user interfaces In commit ed17b8d377ea ("xfrm: fix a warning in xfrm_policy_insert_list"), it would take 'priority' to make a policy unique, and allow duplicated policies with different 'priority' to be added, which is not expected by userland, as Tobias reported in strongswan. To fix this duplicated policies issue, and also fix the issue in commit ed17b8d377ea ("xfrm: fix a warning in xfrm_policy_insert_list"), when doing add/del/get/update on user interfaces, this patch is to change to look up a policy with both mark and mask by doing: mark.v == pol->mark.v && mark.m == pol->mark.m and leave the check: (mark & pol->mark.m) == pol->mark.v for tx/rx path only. As the userland expects an exact mark and mask match to manage policies. v1->v2: - make xfrm_policy_mark_match inline and fix the changelog as Tobias suggested. Fixes: 295fae568885 ("xfrm: Allow user space manipulation of SPD mark") Fixes: ed17b8d377ea ("xfrm: fix a warning in xfrm_policy_insert_list") Reported-by: Tobias Brunner Tested-by: Tobias Brunner Signed-off-by: Xin Long Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index c7d213c9f9d8..5c20953c8deb 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1630,13 +1630,16 @@ int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, void *); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net); int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl); -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, +struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, + const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, u8, - int dir, u32 id, int delete, int *err); +struct xfrm_policy *xfrm_policy_byid(struct net *net, + const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, + int *err); int xfrm_policy_flush(struct net *net, u8 type, bool task_valid); void xfrm_policy_hash_rebuild(struct net *net); u32 xfrm_get_acqseq(void); -- cgit v1.2.3 From 101dde4207f1daa1fda57d714814a03835dccc3f Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Fri, 17 Jul 2020 10:34:27 +0200 Subject: xfrm: Fix crash when the hold queue is used. The commits "xfrm: Move dst->path into struct xfrm_dst" and "net: Create and use new helper xfrm_dst_child()." changed xfrm bundle handling under the assumption that xdst->path and dst->child are not a NULL pointer only if dst->xfrm is not a NULL pointer. That is true with one exception. If the xfrm hold queue is used to wait until a SA is installed by the key manager, we create a dummy bundle without a valid dst->xfrm pointer. The current xfrm bundle handling crashes in that case. Fix this by extending the NULL check of dst->xfrm with a test of the DST_XFRM_QUEUE flag. Fixes: 0f6c480f23f4 ("xfrm: Move dst->path into struct xfrm_dst") Fixes: b92cf4aab8e6 ("net: Create and use new helper xfrm_dst_child().") Signed-off-by: Steffen Klassert --- include/net/xfrm.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/net') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 5c20953c8deb..51f65d23ebaf 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -941,7 +941,7 @@ struct xfrm_dst { static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { const struct xfrm_dst *xdst = (const struct xfrm_dst *) dst; return xdst->path; @@ -953,7 +953,7 @@ static inline struct dst_entry *xfrm_dst_path(const struct dst_entry *dst) static inline struct dst_entry *xfrm_dst_child(const struct dst_entry *dst) { #ifdef CONFIG_XFRM - if (dst->xfrm) { + if (dst->xfrm || (dst->flags & DST_XFRM_QUEUE)) { struct xfrm_dst *xdst = (struct xfrm_dst *) dst; return xdst->child; } -- cgit v1.2.3 From ec4f5b3617049d474b3263792785b638640f2dbe Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 29 Jul 2020 12:26:44 +0300 Subject: mlxsw: spectrum: Use different trap group for externally routed packets Cited commit mistakenly removed the trap group for externally routed packets (e.g., via the management interface) and grouped locally routed and externally routed packet traps under the same group, thereby subjecting them to the same policer. This can result in problems, for example, when FRR is restarted and suddenly all transient traffic is trapped to the CPU because of a default route through the management interface. Locally routed packets required to re-establish a BGP connection will never reach the CPU and the routing tables will not be re-populated. Fix this by using a different trap group for externally routed packets. Fixes: 8110668ecd9a ("mlxsw: spectrum_trap: Register layer 3 control traps") Reported-by: Alex Veber Tested-by: Alex Veber Signed-off-by: Ido Schimmel Reviewed-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink/devlink-trap.rst | 4 ++++ drivers/net/ethernet/mellanox/mlxsw/reg.h | 1 + drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 14 +++++++++++--- include/net/devlink.h | 3 +++ net/core/devlink.c | 1 + 5 files changed, 20 insertions(+), 3 deletions(-) (limited to 'include/net') diff --git a/Documentation/networking/devlink/devlink-trap.rst b/Documentation/networking/devlink/devlink-trap.rst index 1e3f3ffee248..2014307fbe63 100644 --- a/Documentation/networking/devlink/devlink-trap.rst +++ b/Documentation/networking/devlink/devlink-trap.rst @@ -486,6 +486,10 @@ narrow. The description of these groups must be added to the following table: - Contains packet traps for packets that should be locally delivered after routing, but do not match more specific packet traps (e.g., ``ipv4_bgp``) + * - ``external_delivery`` + - Contains packet traps for packets that should be routed through an + external interface (e.g., management interface) that does not belong to + the same device (e.g., switch ASIC) as the ingress interface * - ``ipv6`` - Contains packet traps for various IPv6 control packets (e.g., Router Advertisements) diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index fcb88d4271bf..8ac987c8c8bc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -5536,6 +5536,7 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_MULTICAST, MLXSW_REG_HTGT_TRAP_GROUP_SP_NEIGH_DISCOVERY, MLXSW_REG_HTGT_TRAP_GROUP_SP_ROUTER_EXP, + MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, MLXSW_REG_HTGT_TRAP_GROUP_SP_DHCP, MLXSW_REG_HTGT_TRAP_GROUP_SP_EVENT, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c index 157a42c63066..1e38dfe7cf64 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -328,6 +328,9 @@ mlxsw_sp_trap_policer_items_arr[] = { { .policer = MLXSW_SP_TRAP_POLICER(18, 1024, 128), }, + { + .policer = MLXSW_SP_TRAP_POLICER(19, 1024, 512), + }, }; static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { @@ -421,6 +424,11 @@ static const struct mlxsw_sp_trap_group_item mlxsw_sp_trap_group_items_arr[] = { .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IP2ME, .priority = 2, }, + { + .group = DEVLINK_TRAP_GROUP_GENERIC(EXTERNAL_DELIVERY, 19), + .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_EXTERNAL_ROUTE, + .priority = 1, + }, { .group = DEVLINK_TRAP_GROUP_GENERIC(IPV6, 15), .hw_group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_IPV6, @@ -882,11 +890,11 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = { }, }, { - .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, LOCAL_DELIVERY, + .trap = MLXSW_SP_TRAP_CONTROL(EXTERNAL_ROUTE, EXTERNAL_DELIVERY, TRAP), .listeners_arr = { - MLXSW_SP_RXL_MARK(RTR_INGRESS0, IP2ME, TRAP_TO_CPU, - false), + MLXSW_SP_RXL_MARK(RTR_INGRESS0, EXTERNAL_ROUTE, + TRAP_TO_CPU, false), }, }, { diff --git a/include/net/devlink.h b/include/net/devlink.h index 1df6dfec26c2..95b0322a2a82 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -718,6 +718,7 @@ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_PIM, DEVLINK_TRAP_GROUP_GENERIC_ID_UC_LB, DEVLINK_TRAP_GROUP_GENERIC_ID_LOCAL_DELIVERY, + DEVLINK_TRAP_GROUP_GENERIC_ID_EXTERNAL_DELIVERY, DEVLINK_TRAP_GROUP_GENERIC_ID_IPV6, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_EVENT, DEVLINK_TRAP_GROUP_GENERIC_ID_PTP_GENERAL, @@ -915,6 +916,8 @@ enum devlink_trap_group_generic_id { "uc_loopback" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_LOCAL_DELIVERY \ "local_delivery" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_EXTERNAL_DELIVERY \ + "external_delivery" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_IPV6 \ "ipv6" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_PTP_EVENT \ diff --git a/net/core/devlink.c b/net/core/devlink.c index 2cafbc808b09..dc2b18475956 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -8567,6 +8567,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PIM), DEVLINK_TRAP_GROUP(UC_LB), DEVLINK_TRAP_GROUP(LOCAL_DELIVERY), + DEVLINK_TRAP_GROUP(EXTERNAL_DELIVERY), DEVLINK_TRAP_GROUP(IPV6), DEVLINK_TRAP_GROUP(PTP_EVENT), DEVLINK_TRAP_GROUP(PTP_GENERAL), -- cgit v1.2.3 From 8c0de6e96c9794cb523a516c465991a70245da1c Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Sat, 25 Jul 2020 15:40:53 -0700 Subject: ipv6: fix memory leaks on IPV6_ADDRFORM path IPV6_ADDRFORM causes resource leaks when converting an IPv6 socket to IPv4, particularly struct ipv6_ac_socklist. Similar to struct ipv6_mc_socklist, we should just close it on this path. This bug can be easily reproduced with the following C program: #include #include #include #include #include int main() { int s, value; struct sockaddr_in6 addr; struct ipv6_mreq m6; s = socket(AF_INET6, SOCK_DGRAM, 0); addr.sin6_family = AF_INET6; addr.sin6_port = htons(5000); inet_pton(AF_INET6, "::ffff:192.168.122.194", &addr.sin6_addr); connect(s, (struct sockaddr *)&addr, sizeof(addr)); inet_pton(AF_INET6, "fe80::AAAA", &m6.ipv6mr_multiaddr); m6.ipv6mr_interface = 5; setsockopt(s, SOL_IPV6, IPV6_JOIN_ANYCAST, &m6, sizeof(m6)); value = AF_INET; setsockopt(s, SOL_IPV6, IPV6_ADDRFORM, &value, sizeof(value)); close(s); return 0; } Reported-by: ch3332xr@gmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- include/net/addrconf.h | 1 + net/ipv6/anycast.c | 17 ++++++++++++----- net/ipv6/ipv6_sockglue.c | 1 + 3 files changed, 14 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/addrconf.h b/include/net/addrconf.h index fdb07105384c..8418b7d38468 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -274,6 +274,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); +void __ipv6_sock_ac_close(struct sock *sk); void ipv6_sock_ac_close(struct sock *sk); int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr); diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 893261230ffc..dacdea7fcb62 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 20576e87a5f7..76f9e41859a2 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -240,6 +240,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so -- cgit v1.2.3